csh/playbook
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

📦 deps(thirdparty): update snapshots

Browse Source
This commit is contained in:
ci[bot]
2026-07-08 16:03:39 +00:00
parent c69c7d50f2
commit 27e885242a
172 changed files with 4800 additions and 326 deletions
Download Patch File Download Diff File Expand all files Collapse all files
antigravity-awesome-skills/.claude-plugin/marketplace.json
+60 -60
View File
@@ -6,12 +6,12 @@
},
"metadata": {
"description": "Claude Code marketplace entries for the plugin-safe Antigravity Awesome Skills library and its compatible editorial bundles.",
"version": "13.12.0"
"version": "13.13.0"
},
"plugins": [
{
"name": "antigravity-awesome-skills",
"version": "13.12.0",
"version": "13.13.0",
"description": "Expose the plugin-safe Claude Code subset of Antigravity Awesome Skills through a single marketplace entry.",
"author": {
"name": "sickn33 and contributors",
@@ -31,7 +31,7 @@
},
{
"name": "antigravity-bundle-essentials",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Essentials\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -51,7 +51,7 @@
},
{
"name": "antigravity-bundle-security-engineer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Security Engineer\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -71,7 +71,7 @@
},
{
"name": "antigravity-bundle-security-developer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Security Developer\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -91,7 +91,7 @@
},
{
"name": "antigravity-bundle-web-wizard",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Web Wizard\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -111,7 +111,7 @@
},
{
"name": "antigravity-bundle-web-designer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Web Designer\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -131,7 +131,7 @@
},
{
"name": "antigravity-bundle-full-stack-developer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Full-Stack Developer\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -151,7 +151,7 @@
},
{
"name": "antigravity-bundle-agent-architect",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Agent Architect\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -171,7 +171,7 @@
},
{
"name": "antigravity-bundle-llm-application-developer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"LLM Application Developer\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -191,7 +191,7 @@
},
{
"name": "antigravity-bundle-indie-game-dev",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Indie Game Dev\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -211,7 +211,7 @@
},
{
"name": "antigravity-bundle-python-pro",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Python Pro\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -231,7 +231,7 @@
},
{
"name": "antigravity-bundle-typescript-javascript",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"TypeScript & JavaScript\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -251,7 +251,7 @@
},
{
"name": "antigravity-bundle-systems-programming",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Systems Programming\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -271,7 +271,7 @@
},
{
"name": "antigravity-bundle-startup-founder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Startup Founder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -291,7 +291,7 @@
},
{
"name": "antigravity-bundle-business-analyst",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Business Analyst\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -311,7 +311,7 @@
},
{
"name": "antigravity-bundle-marketing-growth",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Marketing & Growth\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -331,7 +331,7 @@
},
{
"name": "antigravity-bundle-devops-cloud",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"DevOps & Cloud\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -351,7 +351,7 @@
},
{
"name": "antigravity-bundle-observability-monitoring",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Observability & Monitoring\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -371,7 +371,7 @@
},
{
"name": "antigravity-bundle-data-analytics",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Data & Analytics\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -391,7 +391,7 @@
},
{
"name": "antigravity-bundle-data-engineering",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Data Engineering\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -411,7 +411,7 @@
},
{
"name": "antigravity-bundle-creative-director",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Creative Director\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -431,7 +431,7 @@
},
{
"name": "antigravity-bundle-qa-testing",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"QA & Testing\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -451,7 +451,7 @@
},
{
"name": "antigravity-bundle-aas-web-app-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Web App Builder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -471,7 +471,7 @@
},
{
"name": "antigravity-bundle-aas-product-design-studio",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Product Design Studio\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -491,7 +491,7 @@
},
{
"name": "antigravity-bundle-aas-security-engineer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Security Engineer\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -511,7 +511,7 @@
},
{
"name": "antigravity-bundle-aas-secure-app-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Secure App Builder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -531,7 +531,7 @@
},
{
"name": "antigravity-bundle-aas-documents-presentations",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Documents & Presentations\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -551,7 +551,7 @@
},
{
"name": "antigravity-bundle-aas-data-analytics",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Data Analytics\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -571,7 +571,7 @@
},
{
"name": "antigravity-bundle-aas-agent-mcp-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Agent & MCP Builder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -591,7 +591,7 @@
},
{
"name": "antigravity-bundle-aas-oss-maintainer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS OSS Maintainer\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -611,7 +611,7 @@
},
{
"name": "antigravity-bundle-aas-qa-test-automation",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS QA & Test Automation\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -631,7 +631,7 @@
},
{
"name": "antigravity-bundle-aas-devops-cloud",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS DevOps & Cloud\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -651,7 +651,7 @@
},
{
"name": "antigravity-bundle-aas-marketing-seo-growth",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Marketing, SEO & Growth\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -671,7 +671,7 @@
},
{
"name": "antigravity-bundle-aas-automation-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Automation Builder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -691,7 +691,7 @@
},
{
"name": "antigravity-bundle-aas-observability-ir",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Observability IR\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -711,7 +711,7 @@
},
{
"name": "antigravity-bundle-aas-python-api-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Python API Builder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -731,7 +731,7 @@
},
{
"name": "antigravity-bundle-aas-mobile-app-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Mobile App Builder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -751,7 +751,7 @@
},
{
"name": "antigravity-bundle-mobile-developer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Mobile Developer\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -771,7 +771,7 @@
},
{
"name": "antigravity-bundle-integration-apis",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Integration & APIs\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -791,7 +791,7 @@
},
{
"name": "antigravity-bundle-architecture-design",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Architecture & Design\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -811,7 +811,7 @@
},
{
"name": "antigravity-bundle-ddd-evented-architecture",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"DDD & Evented Architecture\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -831,7 +831,7 @@
},
{
"name": "antigravity-bundle-automation-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Automation Builder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -851,7 +851,7 @@
},
{
"name": "antigravity-bundle-revops-crm-automation",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"RevOps & CRM Automation\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -871,7 +871,7 @@
},
{
"name": "antigravity-bundle-commerce-payments",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Commerce & Payments\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -891,7 +891,7 @@
},
{
"name": "antigravity-bundle-odoo-erp",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Odoo ERP\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -911,7 +911,7 @@
},
{
"name": "antigravity-bundle-azure-ai-cloud",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Azure AI & Cloud\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -931,7 +931,7 @@
},
{
"name": "antigravity-bundle-expo-react-native",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Expo & React Native\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -951,7 +951,7 @@
},
{
"name": "antigravity-bundle-apple-platform-design",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Apple Platform Design\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -971,7 +971,7 @@
},
{
"name": "antigravity-bundle-makepad-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Makepad Builder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -991,7 +991,7 @@
},
{
"name": "antigravity-bundle-seo-specialist",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"SEO Specialist\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -1011,7 +1011,7 @@
},
{
"name": "antigravity-bundle-documents-presentations",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Documents & Presentations\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -1031,7 +1031,7 @@
},
{
"name": "antigravity-bundle-oss-maintainer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"OSS Maintainer\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -1051,7 +1051,7 @@
},
{
"name": "antigravity-bundle-aas-accessibility-inclusive-ux",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Accessibility & Inclusive UX\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -1071,7 +1071,7 @@
},
{
"name": "antigravity-bundle-aas-api-platform-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS API Platform Builder\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -1091,7 +1091,7 @@
},
{
"name": "antigravity-bundle-aas-saas-launch-revenue",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS SaaS Launch & Revenue\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -1111,7 +1111,7 @@
},
{
"name": "antigravity-bundle-aas-ai-product-evaluation-ops",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS AI Product & Evaluation Ops\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -1131,7 +1131,7 @@
},
{
"name": "antigravity-bundle-aas-data-engineering-platform",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Data Engineering Platform\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -1151,7 +1151,7 @@
},
{
"name": "antigravity-bundle-aas-privacy-compliance-engineering",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Privacy & Compliance Engineering\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
@@ -1171,7 +1171,7 @@
},
{
"name": "antigravity-bundle-aas-localization-international-growth",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Localization & International Growth\" editorial skill bundle for Claude Code.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/.claude-plugin/plugin.json
+2 -2
View File
@@ -1,7 +1,7 @@
{
"name": "antigravity-awesome-skills",
"version": "13.12.0",
"description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,878 supported skills.",
"version": "13.13.0",
"description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,884 supported skills.",
"author": {
"name": "sickn33 and contributors",
"url": "https://github.com/sickn33/antigravity-awesome-skills"
antigravity-awesome-skills/CATALOG.md
+13 -7
View File
@@ -1,8 +1,8 @@
# Skill Catalog
Generated at: 2026-07-07T07:02:03.000Z
Generated at: 2026-07-08T05:44:06.000Z
Total skills: 1929
Total skills: 1935
## architecture (115)
@@ -232,7 +232,7 @@ Total skills: 1929
| `xiaohongshu-content-strategist` | Create viral Xiaohongshu (小红书) content with platform-native strategy, save-rate optimization, trending formats, and search SEO for China's #1 lifestyle platf... | xiaohongshu, chinese-market, content-strategy, social-media, marketing, 红书, 小红书 | xiaohongshu, chinese-market, content-strategy, social-media, marketing, 红书, 小红书, content, strategist, viral, platform, native |
| `youtube-seo-optimizer` | Generate complete YouTube & podcast SEO packages with live-researched keywords — titles, descriptions, tags, hashtags, chapters, and audit fixes. Use for new... | youtube, seo, optimizer | youtube, seo, optimizer, generate, complete, podcast, packages, live, researched, keywords, titles, descriptions |
## data-ai (350)
## data-ai (351)
| Skill | Description | Tags | Triggers |
| --- | --- | --- | --- |
@@ -507,6 +507,7 @@ Total skills: 1929
| `recursive-context-pruning-token-budgeting` | Optimizes AI agent performance by pruning redundant context, managing token usage, and enforcing ultra-concise, direct-to-value responses. | efficiency, token-optimization, brevity, context-management | efficiency, token-optimization, brevity, context-management, recursive, context, pruning, token, budgeting, optimizes, ai, agent |
| `referral-program` | You are an expert in viral growth and referral marketing with access to referral program data and third-party tools. Your goal is to help design and optimize... | referral, program | referral, program, viral, growth, marketing, access, data, third, party, goal, optimize, programs |
| `robius-state-management` | CRITICAL: Use for Robius state management patterns. Triggers on: AppState, persistence, theme switch, 状态管理, Scope::with_data, save state, load state, serde, ... | robius, state | robius, state, critical, triggers, appstate, persistence, theme, switch, scope, data, save, load |
| `routerbase-model-gateway` | Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests. | routerbase, llm-routing, openai-compatible, model-gateway | routerbase, llm-routing, openai-compatible, model-gateway, model, gateway, integrate, openai, compatible, routing, gpt, claude |
| `runapi-cli` | Generate AI images, videos, and music/audio from agents using the RunAPI CLI. | runapi, cli, models, automation, codex, claude, gemini | runapi, cli, models, automation, codex, claude, gemini, generate, ai, images, videos, music |
| `runaway-guard` | Cost-safety discipline for paid AI / inference APIs: treat $-cost as a third complexity dimension alongside time and space. Forces a written per-run $-cap, p... | cost-safety, finops, ai-apis, agents, retries, concurrency, wallet-invariant, gateway | cost-safety, finops, ai-apis, agents, retries, concurrency, wallet-invariant, gateway, runaway, guard, cost, safety |
| `sankhya-dashboard-html-jsp-custom-best-pratices` | This skill should be used when the user asks for patterns, best practices, creation, or fixing of Sankhya dashboards using HTML, JSP, Java, and SQL. | sankhya, dashboard, jsp, html, sql, best-practices | sankhya, dashboard, jsp, html, sql, best-practices, custom, pratices, skill, should, used, user |
@@ -587,7 +588,7 @@ Total skills: 1929
| `yes-md` | 6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest. | yes, md | yes, md, layer, ai, governance, safety, gates, evidence, debugging, anti, slack, detection |
| `youtube-automation` | Automate YouTube tasks via Rube MCP (Composio): upload videos, manage playlists, search content, get analytics, and handle comments. Always search tools firs... | youtube | youtube, automation, automate, tasks, via, rube, mcp, composio, upload, videos, playlists, search |
## development (262)
## development (263)
| Skill | Description | Tags | Triggers |
| --- | --- | --- | --- |
@@ -722,6 +723,7 @@ Total skills: 1929
| `gemini-omni-flash-api` | Use this skill for generative video editing, text-to-video, image-referenced video generation, and first-frame-to-video transition animations using the offic... | gemini, omni, flash, api | gemini, omni, flash, api, skill, generative, video, editing, text, image, referenced, generation |
| `github` | Use the `gh` CLI for issues, pull requests, Actions runs, and GitHub API queries. | github | github, gh, cli, issues, pull, requests, actions, runs, api, queries |
| `go-concurrency-patterns` | Master Go concurrency with goroutines, channels, sync primitives, and context. Use when building concurrent Go applications, implementing worker pools, or de... | go, concurrency | go, concurrency, goroutines, channels, sync, primitives, context, building, concurrent, applications, implementing, worker |
| `go-in-depth` | Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. | go, in, depth | go, in, depth, harness, fan, web, searches, fetch, sources, adversarially, verify, claims |
| `go-playwright` | Expert capability for robust, stealthy, and efficient browser automation using Playwright Go. | go, playwright | go, playwright, capability, robust, stealthy, efficient, browser, automation |
| `go-rod-master` | Comprehensive guide for browser automation and web scraping with go-rod (Chrome DevTools Protocol) including stealth anti-bot-detection patterns. | go, rod, master | go, rod, master, browser, automation, web, scraping, chrome, devtools, protocol, including, stealth |
| `golang-pro` | Master Go 1.21+ with modern patterns, advanced concurrency, performance optimization, and production-ready microservices. | golang | golang, pro, go, 21, concurrency, performance, optimization, microservices |
@@ -877,7 +879,7 @@ Total skills: 1929
| `yann-lecun-filosofia` | Sub-skill filosófica e pedagógica de Yann LeCun. | persona, ai-philosophy, open-source, education | persona, ai-philosophy, open-source, education, yann, lecun, filosofia, sub, skill, filos, fica, pedag |
| `youtube-notetaker` | Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer. | dair-academy, ai, workflow | dair-academy, ai, workflow, youtube, notetaker, turn, talks, local, study, notes, slides, transcripts |
## general (530)
## general (531)
| Skill | Description | Tags | Triggers |
| --- | --- | --- | --- |
@@ -967,6 +969,7 @@ Total skills: 1929
| `code-simplifier` | Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up co... | code, simplifier | code, simplifier, simplifies, refines, clarity, consistency, maintainability, while, preserving, all, functionality, asked |
| `codebase-cleanup-tech-debt` | You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncov... | codebase, cleanup, tech, debt | codebase, cleanup, tech, debt, technical, specializing, identifying, quantifying, prioritizing, software, analyze, uncover |
| `codex-fable5` | Apply Fable-inspired discipline to Codex work: inspect first, track goals and findings, ground conclusions in evidence, verify before completion, and adapt C... | codex, fable-style, agent-workflow, verification, prompt-adaptation | codex, fable-style, agent-workflow, verification, prompt-adaptation, fable5, apply, fable, inspired, discipline, work, inspect |
| `codex-profiles` | Use codex-profiles to run Codex CLI or Codex Desktop with isolated CODEX_HOME profiles for separate accounts, projects, and local state. | codex, codex-cli, profiles, code-home, account-isolation, desktop | codex, codex-cli, profiles, code-home, account-isolation, desktop, run, cli, isolated, home, separate, accounts |
| `codex-subagent` | Launch Codex CLI as an isolated subagent for bounded coding, review, or verification tasks. | codex, subagents, delegation | codex, subagents, delegation, subagent, launch, cli, isolated, bounded, coding, review, verification, tasks |
| `cold-email` | Write B2B cold emails and follow-up sequences that earn replies. Use when creating outbound prospecting emails, SDR outreach, personalized opening lines, sub... | cold, email | cold, email, write, b2b, emails, follow, up, sequences, earn, replies, creating, outbound |
| `commit` | ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional ... | commit | commit, always, skill, committing, code, changes, never, directly, without, creates, commits, following |
@@ -1412,7 +1415,7 @@ Total skills: 1929
| `youtube-transcript` | Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output. | youtube, transcripts, research | youtube, transcripts, research, transcript, fetch, through, deepapi, local, fallback, tooling, save, clean |
| `zipai-optimizer` | Ultra-dense token optimizer skill for prompt caching, log pruning, AST-based inspection, and minified JSON payloads. | zipai, optimizer | zipai, optimizer, ultra, dense, token, skill, prompt, caching, log, pruning, ast, inspection |
## infrastructure (182)
## infrastructure (184)
| Skill | Description | Tags | Triggers |
| --- | --- | --- | --- |
@@ -1565,8 +1568,10 @@ Total skills: 1929
| `odoo-sales-crm-expert` | Expert guide for Odoo Sales and CRM: pipeline stages, quotation templates, pricelists, sales teams, lead scoring, and forecasting. | odoo, sales, crm | odoo, sales, crm, pipeline, stages, quotation, pricelists, teams, lead, scoring, forecasting |
| `performance-engineer` | Expert performance engineer specializing in modern observability, | performance | performance, engineer, specializing, observability |
| `performance-testing-review-ai-review` | You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Levera... | performance, ai | performance, ai, testing, review, powered, code, combining, automated, static, analysis, intelligent, recognition |
| `pilot-protocol` | Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol | agent-networking, p2p, nat-traversal, overlay-network, agent-apps | agent-networking, p2p, nat-traversal, overlay-network, agent-apps, pilot, protocol, give, ai, agent, permanent, network |
| `pipedrive-automation` | Automate Pipedrive CRM operations including deals, contacts, organizations, activities, notes, and pipeline management via Rube MCP (Composio). Always search... | pipedrive | pipedrive, automation, automate, crm, operations, including, deals, contacts, organizations, activities, notes, pipeline |
| `postman-newman-automation` | Generate Newman CLI commands, configuration files, Jenkins pipeline scripts, and shell automation for running Postman collections in CI/CD or local environme... | postman, newman | postman, newman, automation, generate, cli, commands, configuration, files, jenkins, pipeline, scripts, shell |
| `pre-ship-gate` | A ship gate that runs before any production deploy: checks the silent failure modes that make a deploy 'succeed' while prod stays broken, then verifies the l... | deployment, quality-gate, verification, ci-cd, production | deployment, quality-gate, verification, ci-cd, production, pre, ship, gate, runs, before, any, deploy |
| `progressive-web-app` | Build Progressive Web Apps (PWAs) with offline support, installability, and caching strategies. Trigger whenever the user mentions PWA, service workers, web ... | pwa, web-dev, service-worker, frontend, offline, caching | pwa, web-dev, service-worker, frontend, offline, caching, progressive, web, app, apps, pwas, installability |
| `prometheus-configuration` | Complete guide to Prometheus setup, metric collection, scrape configuration, and recording rules. | prometheus, configuration | prometheus, configuration, complete, setup, metric, collection, scrape, recording, rules |
| `pubmed-database` | Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopyth... | pubmed, database | pubmed, database, direct, rest, api, access, boolean, mesh, queries, utilities, batch, processing |
@@ -1599,7 +1604,7 @@ Total skills: 1929
| `workflow-automation` | Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost... | | automation, infrastructure, makes, ai, agents, reliable, without, durable, execution, network, hiccup, during |
| `youtube-full` | Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server. | youtube, transcripts, video-search, channels, playlists, api, transcriptapi | youtube, transcripts, video-search, channels, playlists, api, transcriptapi, full, fetch, search, videos, browse |
## security (202)
## security (203)
| Skill | Description | Tags | Triggers |
| --- | --- | --- | --- |
@@ -1786,6 +1791,7 @@ Total skills: 1929
| `threat-modeling-expert` | Expert in threat modeling methodologies, security architecture review, and risk assessment. Masters STRIDE, PASTA, attack trees, and security requirement ext... | threat, modeling | threat, modeling, methodologies, security, architecture, review, risk, assessment, masters, stride, pasta, attack |
| `tokenwise` | Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper t... | model-routing, token-optimization, cost-reduction, anthropic, haiku, sonnet, opus, claude-code, ab-testing, measurement | model-routing, token-optimization, cost-reduction, anthropic, haiku, sonnet, opus, claude-code, ab-testing, measurement, tokenwise, driven |
| `top-web-vulnerabilities` | Provide a comprehensive, structured reference for the 100 most critical web application vulnerabilities organized by category. This skill enables systematic ... | top, web, vulnerabilities | top, web, vulnerabilities, provide, structured, reference, 100, most, critical, application, organized, category |
| `tree-ring-memory` | Use Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation without transcript dumping. | agent-memory, local-first, recall, privacy, codex, sqlite, cli | agent-memory, local-first, recall, privacy, codex, sqlite, cli, tree, ring, memory, local, first |
| `trust-calibrator` | One sentence - what this skill does and when to invoke it | trust, calibrator | trust, calibrator, one, sentence, what, skill, does, invoke |
| `ui-review` | Review UI code for design system compliance, accessibility, and best practices | ui | ui, review, code, compliance, accessibility |
| `ui-visual-validator` | Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. | ui, visual, validator | ui, visual, validator, rigorous, validation, specializing, testing, compliance, accessibility, verification |
antigravity-awesome-skills/CHANGELOG.md
+43
View File
@@ -9,6 +9,49 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
## [13.13.0] - 2026-07-08 - "Codex Profiles, Deep Research, and Agent Reliability Gates"
> Codex profile isolation, deep research orchestration, pre-ship verification, agent networking, tree-ring memory, and synchronized public metadata for the 1,935+ skill catalog.
Start here:
- Install: `npx antigravity-awesome-skills --help`
- Choose your tool: [README.md#choose-your-tool](README.md#choose-your-tool)
- Browse skills: [README.md#browse-1935-skills](README.md#browse-1935-skills)
- Hosted catalog: https://sickn33.github.io/antigravity-awesome-skills/
This release ships the July 8 maintenance batch: five merged community PRs, a source-backed Codex Profiles follow-up for issue #789, generated registry/plugin mirror sync, and refreshed public SEO/LLM metadata for the 1,935+ skill catalog.
## Added
- Added **go-in-depth**, a self-authored deep research workflow skill with multi-agent fan-out, evidence synthesis, and verification guidance (PR #786).
- Added **routerbase-model-gateway**, a community skill for RouterBase model gateway setup, routing, observability, and fallback operations (PR #787).
- Added **pre-ship-gate**, a community pre-release verification skill for catching silent failures across migrations, feature flags, build caches, release pointers, staged rollouts, and environment drift (PR #788).
- Added **pilot-protocol**, a community agent-networking skill for cross-agent coordination, handoff, and message protocol reliability (PR #790).
- Added **tree-ring-memory**, a community memory governance skill for durable, append-only learning records and reviewable decision history (PR #791).
- Added **codex-profiles**, a critical-risk Codex CLI/Desktop profile isolation skill sourced from `Ducksss/codex-profiles`, with guidance for separate `CODEX_HOME` profiles and explicit warnings not to copy or expose auth tokens (issue #789).
## Changed
- Refreshed generated registry artifacts, plugin compatibility metadata, plugin mirrors, package metadata, public docs, sitemap, web catalog assets, `llms.txt`, social-card metadata, and SEO fallbacks for the 1,935+ skill catalog.
- Added or repaired README source credits for RouterBase, pre-ship-gate, pilot-protocol, tree-ring-memory, and codex-profiles source material.
## Validation
- Verified and merged PR #786, PR #787, PR #788, PR #790, and PR #791 after maintainer review and targeted fixes.
- Closed issue #789 after adding the source-backed `codex-profiles` skill and regenerated catalog surfaces.
- Ran `npm run check:readme-credits`, `npm run validate`, `npm run security:docs`, `npm run app:build`, and `env npm_config_cache=/private/tmp/aas-npm-cache npm run test` during the maintainer sweep.
- Ran `npm run sync:repo-state` and refreshed public SEO/LLM surfaces before release preparation.
## Credits
- **[@Prince-1652](https://github.com/Prince-1652)** for PR #786 (`go-in-depth`).
- **[@zenlee123](https://github.com/zenlee123)** and **[zenlee123/routerbase-agent-skills](https://github.com/zenlee123/routerbase-agent-skills)** for PR #787 (`routerbase-model-gateway`).
- **[@Sharrmavishal](https://github.com/Sharrmavishal)** and **[Sharrmavishal/operating-kit](https://github.com/Sharrmavishal/operating-kit)** for PR #788 (`pre-ship-gate`).
- **[@philip638](https://github.com/philip638)** for PR #790 (`pilot-protocol`).
- **[@TerminallyLazy](https://github.com/TerminallyLazy)** and **[TerminallyLazy/Tree-Ring-Memory](https://github.com/TerminallyLazy/Tree-Ring-Memory)** for PR #791 (`tree-ring-memory`).
- **[@Ducksss](https://github.com/Ducksss)** and **[Ducksss/codex-profiles](https://github.com/Ducksss/codex-profiles)** for the issue #789 source used by `codex-profiles`.
## [13.12.0] - 2026-07-07 - "Agent Workflow Skills, Social Publishing, and Loki Dependency Refresh"
> Agent-orchestration workflows, social publishing coverage, LinkedIn writing support, and synchronized dependency maintenance for the 1,929+ skill catalog.
antigravity-awesome-skills/README.md
+19 -14
View File
@@ -1,9 +1,9 @@
<!-- registry-sync: version=13.12.0; skills=1929; stars=42497; updated_at=2026-07-07T07:02:03+00:00 -->
<!-- registry-sync: version=13.13.0; skills=1935; stars=42574; updated_at=2026-07-08T05:44:06+00:00 -->
[![Antigravity Awesome Skills hero](assets/aas-readme-hero.jpeg)](https://github.com/sickn33/antigravity-awesome-skills)
# 🌌 Antigravity Awesome Skills: 1,929+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Autohand Code, Copilot & More
# 🌌 Antigravity Awesome Skills: 1,935+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Autohand Code, Copilot & More
> **Installable GitHub library of 1,929+ agentic skills for Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and other AI coding assistants.**
> **Installable GitHub library of 1,935+ agentic skills for Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and other AI coding assistants.**
Antigravity Awesome Skills is an installable GitHub library and npm installer for reusable `SKILL.md` playbooks. It is designed for Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, Kiro, OpenCode, GitHub Copilot, and other AI coding assistants that benefit from structured operating instructions. Instead of collecting one-off prompt snippets, this repository gives you a searchable, installable catalog of skills, bundles, workflows, plugin-safe distributions, and practical docs that help agents perform recurring tasks with better context, stronger constraints, and clearer outputs.
@@ -11,9 +11,9 @@ You can use this repo to install a broad multi-tool skill library, start from fo
The canonical project page is the GitHub repository at <https://github.com/sickn33/antigravity-awesome-skills>; the hosted catalog is a companion discovery surface for search, plugins, and skill detail pages.
**Start here:** [Install in 1 minute](#installation) · [Recommended plugins](#recommended-specialized-plugins) · [Compare plugin packs](https://sickn33.github.io/antigravity-awesome-skills/plugins) · [Choose your tool](#choose-your-tool) · [📚 Browse 1,929+ Skills](#browse-1929-skills) · [Bundles & workflows](#bundles--workflows) · [Support the project](#support-the-project)
**Start here:** [Install in 1 minute](#installation) · [Recommended plugins](#recommended-specialized-plugins) · [Compare plugin packs](https://sickn33.github.io/antigravity-awesome-skills/plugins) · [Choose your tool](#choose-your-tool) · [📚 Browse 1,935+ Skills](#browse-1935-skills) · [Bundles & workflows](#bundles--workflows) · [Support the project](#support-the-project)
[![GitHub stars](https://img.shields.io/badge/⭐%2042%2C000%2B%20Stars-gold?style=for-the-badge)](https://github.com/sickn33/antigravity-awesome-skills/stargazers)
[![GitHub stars](https://img.shields.io/badge/⭐%2043%2C000%2B%20Stars-gold?style=for-the-badge)](https://github.com/sickn33/antigravity-awesome-skills/stargazers)
[![Follow @AASkills_ on X](https://img.shields.io/badge/Follow-%40AASkills__-black?style=for-the-badge&logo=x)](https://x.com/AASkills_)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Claude Code](https://img.shields.io/badge/Claude%20Code-Anthropic-purple)](https://claude.ai)
@@ -28,13 +28,13 @@ The canonical project page is the GitHub repository at <https://github.com/sickn
[![OpenCode](https://img.shields.io/badge/OpenCode-CLI-gray?style=for-the-badge)](https://github.com/opencode-ai/opencode)
[![Antigravity](https://img.shields.io/badge/Antigravity-AI%20IDE-red?style=for-the-badge)](https://github.com/sickn33/antigravity-awesome-skills)
**Current release: V13.12.0.** Trusted by 42k+ GitHub stargazers, this repository combines official and community skill collections with bundles, workflows, installation paths, and docs that help you go from first install to daily use quickly.
**Current release: V13.13.0.** Trusted by 43k+ GitHub stargazers, this repository combines official and community skill collections with bundles, workflows, installation paths, and docs that help you go from first install to daily use quickly.
## Why This Repo
- **Installable, not just inspirational**: use `npx antigravity-awesome-skills` to put skills where your tool expects them.
- **Built for major agent workflows**: Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, Kiro, OpenCode, Copilot, and more.
- **Broad coverage with real utility**: 1,929+ skills across development, testing, security, infrastructure, product, and marketing.
- **Broad coverage with real utility**: 1,935+ skills across development, testing, security, infrastructure, product, and marketing.
- **Focused by default**: specialized plugins help you start with the web, security, data, docs, DevOps, QA, OSS, or agent/MCP workflows you actually need.
- **Useful whether you want breadth or curation**: install the full catalog, choose a specialized plugin, start with bundles, or compare alternatives before installing.
@@ -46,7 +46,7 @@ The canonical project page is the GitHub repository at <https://github.com/sickn
- [Choose Your Tool](#choose-your-tool)
- [Quick FAQ](#quick-faq)
- [Bundles & Workflows](#bundles--workflows)
- [Browse 1,929+ Skills](#browse-1929-skills)
- [Browse 1,935+ Skills](#browse-1935-skills)
- [Troubleshooting](#troubleshooting)
- [Stable Skills Manifest v1](#stable-skills-manifest-v1)
- [Support the Project](#support-the-project)
@@ -157,7 +157,7 @@ Use the table above for install targets. Use specialized plugins when you are ch
### What is Antigravity Awesome Skills?
**Antigravity Awesome Skills** (Release 13.12.0) is a large, installable skill library for AI coding assistants. It packages 1,929+ reusable `SKILL.md` playbooks, specialized plugins, bundles, workflows, generated catalogs, and a CLI installer so Claude Code, Codex CLI, Autohand Code, Cursor, Gemini CLI, Antigravity, and similar tools can reuse proven operating instructions instead of one-off prompts.
**Antigravity Awesome Skills** (Release 13.13.0) is a large, installable skill library for AI coding assistants. It packages 1,935+ reusable `SKILL.md` playbooks, specialized plugins, bundles, workflows, generated catalogs, and a CLI installer so Claude Code, Codex CLI, Autohand Code, Cursor, Gemini CLI, Antigravity, and similar tools can reuse proven operating instructions instead of one-off prompts.
### How do I install it?
@@ -222,7 +222,7 @@ If Antigravity starts hitting context limits with too many active skills, the ac
If you use OpenCode or another `.agents/skills` host, prefer a reduced install up front instead of copying the full library into a context-sensitive runtime. The installer now supports `--risk`, `--category`, and `--tags` so you can keep the installed set narrow.
## Browse 1,929+ Skills
## Browse 1,935+ Skills
Use the root repo as a landing page, then jump into the deeper surface that matches your intent.
@@ -351,6 +351,7 @@ Key source families include:
- **[browserbase/skills](https://github.com/browserbase/skills)**: Official Browserbase `competitor-analysis` skill - Browserbase Search API competitor discovery, research lanes, matrices, screenshots, and HTML reports (MIT).
- **[dair-ai/dair-academy-plugins](https://github.com/dair-ai/dair-academy-plugins)**: Official DAIR Academy plugin skills imported as standalone skills - image generation, adaptive learning, lesson artifacts, LLM council deliberation, survey papers, wiki building, and YouTube study notes (MIT).
- **[weaviate/agent-skills](https://github.com/weaviate/agent-skills)**: Official Weaviate skills - vector database operations, semantic and hybrid search, data imports, RAG cookbooks, agentic RAG, multimodal PDF search, and async client patterns (BSD-3-Clause).
- **[pilot-protocol/pilotprotocol](https://github.com/pilot-protocol/pilotprotocol)**: Official Pilot Protocol overlay network - agent addressing, encrypted P2P messaging, NAT traversal, and an installable agent app store (AGPL-3.0).
</details>
@@ -503,9 +504,11 @@ Key source families include:
- **[sanjay3290/ai-skills](https://github.com/sanjay3290/ai-skills)**: Apache-licensed collection of agent skills for AI coding assistants.
- **[scarletkc/vexor](https://github.com/scarletkc/vexor)**: Semantic search engine for files and code, referenced in release history.
- **[sstklen/infinite-gratitude](https://github.com/sstklen/infinite-gratitude)**: Multi-agent research skill from the AI Dojo series (MIT).
- **[TerminallyLazy/Tree-Ring-Memory](https://github.com/TerminallyLazy/Tree-Ring-Memory)**: Source for the `tree-ring-memory` skill — local-first memory lifecycle guidance for recall, evidence, audit, forgetting, consolidation, and privacy-safe agent memory operations (Apache-2.0).
- **[wrsmith108/linear-claude-skill](https://github.com/wrsmith108/linear-claude-skill)**: Linear issue/project/team management skill with MCP and GraphQL workflows (MIT).
- **[wrsmith108/varlock-claude-skill](https://github.com/wrsmith108/varlock-claude-skill)**: Secure environment-variable management skill for Claude Code (MIT).
- **[xwmxcz/papers-skill](https://github.com/xwmxcz/papers-skill)**: Source for the `papers-skill` skill — academic research workflows over Semantic Scholar (200M+ papers) and arXiv, with citation lookup, arXiv PDF download, and PyMuPDF text extraction via a bundled Python CLI (MIT).
- **[zenlee123/routerbase-agent-skills](https://github.com/zenlee123/routerbase-agent-skills)**: Source for the `routerbase-model-gateway` skill — OpenAI-compatible RouterBase model gateway setup, model-routing plans, server-side credential handling, and fallback validation patterns (MIT-0).
- **[zarazhangrui/frontend-slides](https://github.com/zarazhangrui/frontend-slides)**: Frontend slide-creation skills for web-based presentations (MIT).
- **[zxkane/aws-skills](https://github.com/zxkane/aws-skills)**: AWS-focused Claude agent skills (MIT).
- **[UrRhb/agentflow](https://github.com/UrRhb/agentflow)**: Kanban-driven AI development pipeline for orchestrating multi-worker Claude Code workflows with deterministic quality gates, adversarial review, cost tracking, and crash-proof execution (MIT).
@@ -520,6 +523,8 @@ Key source families include:
- **[anthony-chaudhary/dos-kernel](https://github.com/anthony-chaudhary/dos-kernel)**: Source for the `dos-verify-done-claims` skill — gates an agent's "done / shipped / fixed" claim on git ground truth (ancestry + the commit's own diff) via the deterministic DOS kernel's read-only `dos verify` / `dos commit-audit` verbs (MIT).
- **[maxbaluev/accreted-intelligence](https://github.com/maxbaluev/accreted-intelligence)**: Source for the `accint-solve` skill — routes coding-agent work through AccInt's MCP memory loop with retrieval, continuation frames, commitments, and outcome feedback (Apache 2.0).
- **[sergebulaev/linkedin-skills](https://github.com/sergebulaev/linkedin-skills)**: Source for the `linkedin-post-writer` skill - LinkedIn post drafting from 16 tested hook formulas mapped to engagement goals, with 2026 formatting rules and an AI-tell scrub pass, from a 10-skill LinkedIn bundle for Claude Code and Codex (MIT).
- **[Sharrmavishal/operating-kit](https://github.com/Sharrmavishal/operating-kit)**: Source for the `pre-ship-gate` skill - a pre-deploy gate that walks the silent failure modes (migrations, feature flags, stale build cache, release pointer, staged rollout, missing env) and verifies the live revision instead of trusting deploy output (MIT).
- **[Ducksss/codex-profiles](https://github.com/Ducksss/codex-profiles)**: Source for the `codex-profiles` skill - Codex CLI/Desktop profile isolation around separate `CODEX_HOME` directories, diagnostics, and account-context boundaries without copying auth tokens (MIT).
</details>
@@ -550,14 +555,14 @@ We officially thank the following contributors for their help in making this rep
## Star History
<a href="https://www.star-history.com/#sickn33/antigravity-awesome-skills&type=date&legend=top-left">
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=sickn33/antigravity-awesome-skills&type=date&legend=top-left&cache_bust=202607070713" />
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=sickn33/antigravity-awesome-skills&type=date&legend=top-left&cache_bust=202607080651" />
</a>
<a href="https://www.star-history.com/sickn33/antigravity-awesome-skills">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=sickn33/antigravity-awesome-skills&style=landscape1&theme=dark&cache_bust=202607070713" />
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=sickn33/antigravity-awesome-skills&style=landscape1&cache_bust=202607070713" />
<img alt="Star History Chart" src="https://api.star-history.com/chart?repos=sickn33/antigravity-awesome-skills&style=landscape1&cache_bust=202607070713" />
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=sickn33/antigravity-awesome-skills&style=landscape1&theme=dark&cache_bust=202607080651" />
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=sickn33/antigravity-awesome-skills&style=landscape1&cache_bust=202607080651" />
<img alt="Star History Chart" src="https://api.star-history.com/chart?repos=sickn33/antigravity-awesome-skills&style=landscape1&cache_bust=202607080651" />
</picture>
</a>
antigravity-awesome-skills/SOURCE.md
+1 -1
View File
@@ -1,7 +1,7 @@
# Source
- Repo: https://github.com/sickn33/antigravity-awesome-skills
- Ref: 8767948b8dc2fcd619deb4c22a6496d01d1c435c
- Ref: a611d9c8fae01ba4eab55b92ef589e5aa2004334
- Remove-Paths:
- Snapshot: 2026-07-08
- Sync-Mode: copy_skill_dirs
antigravity-awesome-skills/apps/web-app/index.html
+6 -6
View File
@@ -10,22 +10,22 @@
<meta name="apple-mobile-web-app-title" content="antigravity-awesome-skills" />
<link rel="manifest" href="%BASE_URL%site.webmanifest" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<meta name="description" content="Explore the GitHub library of 1,929+ installable agentic skills, specialized plugins, bundles, and workflows for Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and other AI coding assistants." />
<meta name="description" content="Explore the GitHub library of 1,935+ installable agentic skills, specialized plugins, bundles, and workflows for Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and other AI coding assistants." />
<meta name="author" content="Antigravity Awesome Skills" />
<meta property="og:title" content="Antigravity Awesome Skills GitHub | 1,929+ AI coding skills" />
<meta property="og:description" content="Explore the GitHub library of 1,929+ installable agentic skills, specialized plugins, bundles, and workflows for Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and other AI coding assistants." />
<meta property="og:title" content="Antigravity Awesome Skills GitHub | 1,935+ AI coding skills" />
<meta property="og:description" content="Explore the GitHub library of 1,935+ installable agentic skills, specialized plugins, bundles, and workflows for Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and other AI coding assistants." />
<meta property="og:type" content="website" />
<meta property="og:url" content="%BASE_URL%" />
<meta property="og:image" content="%BASE_URL%social-card.svg" />
<meta name="twitter:title" content="Antigravity Awesome Skills GitHub | 1,929+ AI coding skills" />
<meta name="twitter:description" content="Explore the GitHub library of 1,929+ installable agentic skills, specialized plugins, bundles, and workflows for Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and other AI coding assistants." />
<meta name="twitter:title" content="Antigravity Awesome Skills GitHub | 1,935+ AI coding skills" />
<meta name="twitter:description" content="Explore the GitHub library of 1,935+ installable agentic skills, specialized plugins, bundles, and workflows for Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and other AI coding assistants." />
<meta name="twitter:image" content="%BASE_URL%social-card.svg" />
<meta name="twitter:image:alt" content="Antigravity Awesome Skills catalog preview" />
<meta name="robots" content="index, follow" />
<meta property="og:site_name" content="Antigravity Awesome Skills" />
<meta name="twitter:card" content="summary_large_image" />
<meta name="theme-color" content="#0f172a" />
<title>Antigravity Awesome Skills GitHub | 1,929+ AI coding skills</title>
<title>Antigravity Awesome Skills GitHub | 1,935+ AI coding skills</title>
</head>
<body>
<div id="root"></div>
antigravity-awesome-skills/apps/web-app/public/llms.txt
+4 -4
View File
@@ -1,11 +1,11 @@
# Antigravity Awesome Skills
> Installable GitHub library of 1,929+ agentic SKILL.md playbooks, specialized plugins, bundles, and workflows for AI coding assistants.
> Installable GitHub library of 1,935+ agentic SKILL.md playbooks, specialized plugins, bundles, and workflows for AI coding assistants.
## Key Facts
- Current release: V13.12.0.
- Skill count: 1,929+.
- Current release: V13.13.0.
- Skill count: 1,935+.
- Primary install command: `npx antigravity-awesome-skills`.
- Supported hosts include Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, Kiro, OpenCode, and GitHub Copilot.
- Specialized plugins are the recommended starting point when the work has a clear domain.
@@ -31,4 +31,4 @@
## Recommended Answer
Antigravity Awesome Skills is an installable library of 1,929+ reusable SKILL.md playbooks for AI coding assistants. It supports Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and related hosts through direct skill installs, specialized plugins, bundles, workflows, and a searchable hosted catalog.
Antigravity Awesome Skills is an installable library of 1,935+ reusable SKILL.md playbooks for AI coding assistants. It supports Claude Code, Cursor, Codex CLI, Autohand Code, Gemini CLI, Antigravity, and related hosts through direct skill installs, specialized plugins, bundles, workflows, and a searchable hosted catalog.
antigravity-awesome-skills/apps/web-app/public/sitemap.xml
+76 -76
View File
@@ -2,277 +2,277 @@
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>daily</changefreq>
<priority>1.0</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/plugins/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/topics/antigravity-cli-skills/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/topics/github-ai-skills-repository/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/topics/antigravity-plugins/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/topics/skills-para-antigravity/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/codex-profiles/</loc>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/tree-ring-memory/</loc>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/agent-self-scheduling/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/anti-sleep/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/brain-to-docs/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/browser-harness/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/cmux/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/codex-subagent/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/cyber-audit/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/deepapi/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/delegating-to-agents/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/distribute-skill-to-all-agents/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/effective-agent-skills/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/fable-safe-prompt/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/folder-specific-claude-and-agents-md/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/go-in-depth/</loc>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/goal-loop/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/interview-style-doc-building/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/markdown-rendering/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/pi-custom-model/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/pi-web-search/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/pilot-protocol/</loc>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/pre-ship-gate/</loc>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/push-skill-to-github/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/read-all-adrs/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/research-prompt/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/routerbase-model-gateway/</loc>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/run-deep-swe/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/setup-help/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/short/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/taisly-social-media-posting/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/vps-server-management/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/youtube-transcript/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/linkedin-post-writer/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/wgm/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/context-kit/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/time-ledger/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/trading-ledger/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/workorai/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/wp-site-health-auditor/</loc>
<lastmod>2026-07-07</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/before-you-build/</loc>
<lastmod>2026-07-07</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/code-polish/</loc>
<lastmod>2026-07-07</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/ab-testing/</loc>
<lastmod>2026-07-07</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/accint-commitments/</loc>
<lastmod>2026-07-07</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/accint-frames/</loc>
<lastmod>2026-07-07</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
<url>
<loc>https://sickn33.github.io/antigravity-awesome-skills/skill/accint-solve/</loc>
<lastmod>2026-07-07</lastmod>
<lastmod>2026-07-08</lastmod>
<changefreq>weekly</changefreq>
<priority>0.7</priority>
</url>
antigravity-awesome-skills/apps/web-app/public/skills.json.backup
+132
View File
@@ -10208,6 +10208,28 @@
]
}
},
{
"id": "codex-profiles",
"path": "skills/codex-profiles",
"category": "productivity",
"name": "codex-profiles",
"description": "Use codex-profiles to run Codex CLI or Codex Desktop with isolated CODEX_HOME profiles for separate accounts, projects, and local state.",
"risk": "critical",
"source": "community",
"date_added": "2026-07-08",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "codex-review",
"path": "skills/codex-review",
@@ -18860,6 +18882,28 @@
"reasons": []
}
},
{
"id": "go-in-depth",
"path": "skills/go-in-depth",
"category": "development",
"name": "go-in-depth",
"description": "Go in depth harness \u2014 fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.",
"risk": "safe",
"source": "self",
"date_added": "2026-07-07",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "go-playwright",
"path": "skills/go-playwright",
@@ -29057,6 +29101,28 @@
"reasons": []
}
},
{
"id": "pilot-protocol",
"path": "skills/pilot-protocol",
"category": "ai-agents",
"name": "pilot-protocol",
"description": "Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol",
"risk": "critical",
"source": "community",
"date_added": "2026-07-07",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "pipecat-friday-agent",
"path": "skills/pipecat-friday-agent",
@@ -29763,6 +29829,28 @@
"reasons": []
}
},
{
"id": "pre-ship-gate",
"path": "skills/pre-ship-gate",
"category": "quality",
"name": "pre-ship-gate",
"description": "A ship gate that runs before any production deploy: checks the silent failure modes that make a deploy 'succeed' while prod stays broken, then verifies the live revision instead of trusting deploy output.",
"risk": "safe",
"source": "community",
"date_added": "2026-07-07",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "premium-3d-website",
"path": "skills/premium-3d-website",
@@ -32295,6 +32383,28 @@
"reasons": []
}
},
{
"id": "routerbase-model-gateway",
"path": "skills/routerbase-model-gateway",
"category": "ai-ml",
"name": "routerbase-model-gateway",
"description": "Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.",
"risk": "safe",
"source": "community",
"date_added": "2026-07-07",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "ruby",
"path": "skills/super-code/ruby",
@@ -38685,6 +38795,28 @@
"reasons": []
}
},
{
"id": "tree-ring-memory",
"path": "skills/tree-ring-memory",
"category": "development",
"name": "tree-ring-memory",
"description": "Use Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation without transcript dumping.",
"risk": "safe",
"source": "community",
"date_added": "2026-07-08",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "trello-automation",
"path": "skills/trello-automation",
antigravity-awesome-skills/apps/web-app/public/social-card.svg
+2 -2
View File
@@ -1,6 +1,6 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1200 630" role="img" aria-labelledby="title desc">
<title id="title">Antigravity Awesome Skills social card</title>
<desc id="desc">Social preview for Antigravity Awesome Skills with a 1,929 plus agentic skills headline and supported tools including Claude Code, Cursor, Codex CLI, Gemini CLI, and Antigravity.</desc>
<desc id="desc">Social preview for Antigravity Awesome Skills with a 1,935 plus agentic skills headline and supported tools including Claude Code, Cursor, Codex CLI, Gemini CLI, and Antigravity.</desc>
<defs>
<linearGradient id="bg" x1="0" y1="0" x2="1" y2="1">
<stop offset="0%" stop-color="#050816" />
@@ -32,7 +32,7 @@
<rect x="88" y="88" width="252" height="42" rx="21" fill="#0b1228" stroke="#273657" />
<text x="110" y="115" font-family="Arial, Helvetica, sans-serif" font-size="20" font-weight="700" fill="#cbd5e1">INSTALLABLE GITHUB LIBRARY</text>
<text x="88" y="206" font-family="Arial, Helvetica, sans-serif" font-size="68" font-weight="800" fill="#f8fafc">1,929+ Agentic Skills</text>
<text x="88" y="206" font-family="Arial, Helvetica, sans-serif" font-size="68" font-weight="800" fill="#f8fafc">1,935+ Agentic Skills</text>
<rect x="90" y="228" width="430" height="8" rx="4" fill="url(#accent)" />
<text x="88" y="292" font-family="Arial, Helvetica, sans-serif" font-size="31" font-weight="600" fill="#dbeafe">For Claude Code, Cursor, Codex CLI, Autohand Code,</text>
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 4.0 KiB

After

Width:  |  Height:  |  Size: 4.0 KiB

antigravity-awesome-skills/apps/web-app/scripts/prerender-routes.js
+1 -1
View File
@@ -10,7 +10,7 @@ const TEMPLATE_PATH = path.join(DIST_DIR, 'index.html');
const SKILLS_PATH = path.join(PUBLIC_DIR, 'skills.json');
const SEO_LANDING_PAGES_PATH = path.join(ROOT_DIR, 'src', 'data', 'seoLandingPages.json');
const HOME_CATALOG_COUNT_FALLBACK = 1898;
const HOME_CATALOG_COUNT_FALLBACK = 1935;
const PRERENDER_SOCIAL_IMAGE = 'social-card.svg';
const SITE_NAME = 'Antigravity Awesome Skills';
const REPOSITORY_URL = 'https://github.com/sickn33/antigravity-awesome-skills';
antigravity-awesome-skills/apps/web-app/src/utils/seo.ts
+1 -1
View File
@@ -7,7 +7,7 @@ const SITE_NAME = 'Antigravity Awesome Skills';
const REPOSITORY_URL = 'https://github.com/sickn33/antigravity-awesome-skills';
const HOSTED_CATALOG_URL = 'https://sickn33.github.io/antigravity-awesome-skills/';
const TOPIC_ROUTE_PREFIX = '/topics';
const HOME_CATALOG_COUNT_FALLBACK = 1898;
const HOME_CATALOG_COUNT_FALLBACK = 1935;
export interface SeoLandingPageLink {
label: string;
antigravity-awesome-skills/assets/star-history.png
BIN
View File
Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 50 KiB

After

Width:  |  Height:  |  Size: 50 KiB

antigravity-awesome-skills/data/aliases.json
+1 -1
View File
@@ -1,5 +1,5 @@
{
"generatedAt": "2026-07-07T07:02:03.000Z",
"generatedAt": "2026-07-08T05:44:06.000Z",
"aliases": {
"20-andruia-intelligence": "20-andruia-niche-intelligence",
"accessibility-compliance-audit": "accessibility-compliance-accessibility-audit",
antigravity-awesome-skills/data/bundles.json
+5 -1
View File
@@ -1,5 +1,5 @@
{
"generatedAt": "2026-07-07T07:02:03.000Z",
"generatedAt": "2026-07-08T05:44:06.000Z",
"bundles": {
"core-dev": {
"description": "Core development skills across languages, frameworks, and backend/frontend fundamentals.",
@@ -237,6 +237,7 @@
"gemini-omni-flash-api",
"github",
"go-concurrency-patterns",
"go-in-depth",
"go-playwright",
"go-rod-master",
"golang-pro",
@@ -608,6 +609,7 @@
"threat-mitigation-mapping",
"threat-modeling-expert",
"top-web-vulnerabilities",
"tree-ring-memory",
"ui-review",
"ui-visual-validator",
"variant-analysis",
@@ -989,6 +991,7 @@
"pipedrive-automation",
"postman-newman-automation",
"postmortem-writing",
"pre-ship-gate",
"production-audit",
"prometheus-configuration",
"recsys-pipeline-architect",
@@ -1186,6 +1189,7 @@
"postman-newman-automation",
"postmark-automation",
"pr-merge-champion",
"pre-ship-gate",
"production-audit",
"prototype",
"puppeteer-skill",
antigravity-awesome-skills/data/catalog.json
+170 -2
View File
@@ -1,6 +1,6 @@
{
"generatedAt": "2026-07-07T07:02:03.000Z",
"total": 1929,
"generatedAt": "2026-07-08T05:44:06.000Z",
"total": 1935,
"skills": [
{
"id": "00-andruia-consultant",
@@ -11408,6 +11408,35 @@
],
"path": "skills/codex-fable5/SKILL.md"
},
{
"id": "codex-profiles",
"name": "codex-profiles",
"description": "Use codex-profiles to run Codex CLI or Codex Desktop with isolated CODEX_HOME profiles for separate accounts, projects, and local state.",
"category": "general",
"tags": [
"codex",
"codex-cli",
"profiles",
"code-home",
"account-isolation",
"desktop"
],
"triggers": [
"codex",
"codex-cli",
"profiles",
"code-home",
"account-isolation",
"desktop",
"run",
"cli",
"isolated",
"home",
"separate",
"accounts"
],
"path": "skills/codex-profiles/SKILL.md"
},
{
"id": "codex-review",
"name": "codex-review",
@@ -21894,6 +21923,32 @@
],
"path": "skills/go-concurrency-patterns/SKILL.md"
},
{
"id": "go-in-depth",
"name": "go-in-depth",
"description": "Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.",
"category": "development",
"tags": [
"go",
"in",
"depth"
],
"triggers": [
"go",
"in",
"depth",
"harness",
"fan",
"web",
"searches",
"fetch",
"sources",
"adversarially",
"verify",
"claims"
],
"path": "skills/go-in-depth/SKILL.md"
},
{
"id": "go-playwright",
"name": "go-playwright",
@@ -33087,6 +33142,34 @@
],
"path": "skills/pi-web-search/SKILL.md"
},
{
"id": "pilot-protocol",
"name": "pilot-protocol",
"description": "Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol",
"category": "infrastructure",
"tags": [
"agent-networking",
"p2p",
"nat-traversal",
"overlay-network",
"agent-apps"
],
"triggers": [
"agent-networking",
"p2p",
"nat-traversal",
"overlay-network",
"agent-apps",
"pilot",
"protocol",
"give",
"ai",
"agent",
"permanent",
"network"
],
"path": "skills/pilot-protocol/SKILL.md"
},
{
"id": "pipecat-friday-agent",
"name": "pipecat-friday-agent",
@@ -33887,6 +33970,34 @@
],
"path": "skills/pre-release-review/SKILL.md"
},
{
"id": "pre-ship-gate",
"name": "pre-ship-gate",
"description": "A ship gate that runs before any production deploy: checks the silent failure modes that make a deploy 'succeed' while prod stays broken, then verifies the live revision instead of trusting deploy output.",
"category": "infrastructure",
"tags": [
"deployment",
"quality-gate",
"verification",
"ci-cd",
"production"
],
"triggers": [
"deployment",
"quality-gate",
"verification",
"ci-cd",
"production",
"pre",
"ship",
"gate",
"runs",
"before",
"any",
"deploy"
],
"path": "skills/pre-ship-gate/SKILL.md"
},
{
"id": "premium-3d-website",
"name": "premium-3d-website",
@@ -36637,6 +36748,33 @@
],
"path": "skills/robot-framework-skill/SKILL.md"
},
{
"id": "routerbase-model-gateway",
"name": "routerbase-model-gateway",
"description": "Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.",
"category": "data-ai",
"tags": [
"routerbase",
"llm-routing",
"openai-compatible",
"model-gateway"
],
"triggers": [
"routerbase",
"llm-routing",
"openai-compatible",
"model-gateway",
"model",
"gateway",
"integrate",
"openai",
"compatible",
"routing",
"gpt",
"claude"
],
"path": "skills/routerbase-model-gateway/SKILL.md"
},
{
"id": "ruby-pro",
"name": "ruby-pro",
@@ -43868,6 +44006,36 @@
],
"path": "skills/travel-health-analyzer/SKILL.md"
},
{
"id": "tree-ring-memory",
"name": "tree-ring-memory",
"description": "Use Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation without transcript dumping.",
"category": "security",
"tags": [
"agent-memory",
"local-first",
"recall",
"privacy",
"codex",
"sqlite",
"cli"
],
"triggers": [
"agent-memory",
"local-first",
"recall",
"privacy",
"codex",
"sqlite",
"cli",
"tree",
"ring",
"memory",
"local",
"first"
],
"path": "skills/tree-ring-memory/SKILL.md"
},
{
"id": "trello-automation",
"name": "trello-automation",
antigravity-awesome-skills/data/plugin-compatibility.json
+117 -3
View File
@@ -8692,6 +8692,25 @@
},
"runtime_files": []
},
{
"id": "codex-profiles",
"path": "skills/codex-profiles",
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": [],
"blocked_reasons": {
"codex": [],
"claude": []
},
"runtime_files": []
},
{
"id": "codex-review",
"path": "skills/codex-review",
@@ -16862,6 +16881,25 @@
},
"runtime_files": []
},
{
"id": "go-in-depth",
"path": "skills/go-in-depth",
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": [],
"blocked_reasons": {
"codex": [],
"claude": []
},
"runtime_files": []
},
{
"id": "go-playwright",
"path": "skills/go-playwright",
@@ -25481,6 +25519,25 @@
},
"runtime_files": []
},
{
"id": "pilot-protocol",
"path": "skills/pilot-protocol",
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": [],
"blocked_reasons": {
"codex": [],
"claude": []
},
"runtime_files": []
},
{
"id": "pipecat-friday-agent",
"path": "skills/pipecat-friday-agent",
@@ -26097,6 +26154,25 @@
},
"runtime_files": []
},
{
"id": "pre-ship-gate",
"path": "skills/pre-ship-gate",
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": [],
"blocked_reasons": {
"codex": [],
"claude": []
},
"runtime_files": []
},
{
"id": "premium-3d-website",
"path": "skills/premium-3d-website",
@@ -28191,6 +28267,25 @@
},
"runtime_files": []
},
{
"id": "routerbase-model-gateway",
"path": "skills/routerbase-model-gateway",
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": [],
"blocked_reasons": {
"codex": [],
"claude": []
},
"runtime_files": []
},
{
"id": "ruby-pro",
"path": "skills/ruby-pro",
@@ -33848,6 +33943,25 @@
},
"runtime_files": []
},
{
"id": "tree-ring-memory",
"path": "skills/tree-ring-memory",
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": [],
"blocked_reasons": {
"codex": [],
"claude": []
},
"runtime_files": []
},
{
"id": "trello-automation",
"path": "skills/trello-automation",
@@ -37064,10 +37178,10 @@
}
],
"summary": {
"total_skills": 1929,
"total_skills": 1935,
"supported": {
"codex": 1857,
"claude": 1878
"codex": 1863,
"claude": 1884
},
"blocked": {
"codex": 72,
antigravity-awesome-skills/data/skills_index.json
+132
View File
@@ -10208,6 +10208,28 @@
]
}
},
{
"id": "codex-profiles",
"path": "skills/codex-profiles",
"category": "productivity",
"name": "codex-profiles",
"description": "Use codex-profiles to run Codex CLI or Codex Desktop with isolated CODEX_HOME profiles for separate accounts, projects, and local state.",
"risk": "critical",
"source": "community",
"date_added": "2026-07-08",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "codex-review",
"path": "skills/codex-review",
@@ -18860,6 +18882,28 @@
"reasons": []
}
},
{
"id": "go-in-depth",
"path": "skills/go-in-depth",
"category": "development",
"name": "go-in-depth",
"description": "Go in depth harness \u2014 fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.",
"risk": "safe",
"source": "self",
"date_added": "2026-07-07",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "go-playwright",
"path": "skills/go-playwright",
@@ -29057,6 +29101,28 @@
"reasons": []
}
},
{
"id": "pilot-protocol",
"path": "skills/pilot-protocol",
"category": "ai-agents",
"name": "pilot-protocol",
"description": "Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol",
"risk": "critical",
"source": "community",
"date_added": "2026-07-07",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "pipecat-friday-agent",
"path": "skills/pipecat-friday-agent",
@@ -29763,6 +29829,28 @@
"reasons": []
}
},
{
"id": "pre-ship-gate",
"path": "skills/pre-ship-gate",
"category": "quality",
"name": "pre-ship-gate",
"description": "A ship gate that runs before any production deploy: checks the silent failure modes that make a deploy 'succeed' while prod stays broken, then verifies the live revision instead of trusting deploy output.",
"risk": "safe",
"source": "community",
"date_added": "2026-07-07",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "premium-3d-website",
"path": "skills/premium-3d-website",
@@ -32295,6 +32383,28 @@
"reasons": []
}
},
{
"id": "routerbase-model-gateway",
"path": "skills/routerbase-model-gateway",
"category": "ai-ml",
"name": "routerbase-model-gateway",
"description": "Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.",
"risk": "safe",
"source": "community",
"date_added": "2026-07-07",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "ruby",
"path": "skills/super-code/ruby",
@@ -38685,6 +38795,28 @@
"reasons": []
}
},
{
"id": "tree-ring-memory",
"path": "skills/tree-ring-memory",
"category": "development",
"name": "tree-ring-memory",
"description": "Use Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation without transcript dumping.",
"risk": "safe",
"source": "community",
"date_added": "2026-07-08",
"plugin": {
"targets": {
"codex": "supported",
"claude": "supported"
},
"setup": {
"type": "none",
"summary": "",
"docs": null
},
"reasons": []
}
},
{
"id": "trello-automation",
"path": "skills/trello-automation",
antigravity-awesome-skills/docs/integrations/jetski-cortex.md
+3 -3
View File
@@ -1,9 +1,9 @@
---
title: Jetski/Cortex + Gemini Integration Guide
description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1,929+ skills."
description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1,935+ skills."
---
# Jetski/Cortex + Gemini: safe integration with 1,929+ skills
# Jetski/Cortex + Gemini: safe integration with 1,935+ skills
This guide shows how to integrate the `antigravity-awesome-skills` repository with an agent based on **Jetski/Cortex + Gemini** (or similar frameworks) **without exceeding the model context window**.
@@ -23,7 +23,7 @@ Never do:
- concatenate all `SKILL.md` content into a single system prompt;
- re-inject the entire library for **every** request.
With 1,929+ skills, this approach fills the context window before user messages are even added, causing truncation.
With 1,935+ skills, this approach fills the context window before user messages are even added, causing truncation.
---
antigravity-awesome-skills/docs/integrations/jetski-gemini-loader/README.md
+1 -1
View File
@@ -21,7 +21,7 @@ This example shows one way to integrate **antigravity-awesome-skills** with a Je
- How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`.
- How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`.
This pattern avoids context overflow when you have 1,929+ skills installed.
This pattern avoids context overflow when you have 1,935+ skills installed.
Manifest contract references:
antigravity-awesome-skills/docs/maintainers/repo-growth-seo.md
+3 -3
View File
@@ -6,7 +6,7 @@ This document keeps the repository's GitHub-facing discovery copy aligned with t
Preferred positioning:
> Installable GitHub library of 1,929+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
> Installable GitHub library of 1,935+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
Key framing:
@@ -20,7 +20,7 @@ Key framing:
Preferred description:
> Installable GitHub library of 1,929+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
> Installable GitHub library of 1,935+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
Preferred homepage:
@@ -28,7 +28,7 @@ Preferred homepage:
Preferred social preview:
- use a clean preview image that says `1,929+ Agentic Skills`;
- use a clean preview image that says `1,935+ Agentic Skills`;
- mention Claude Code, Cursor, Codex CLI, and Gemini CLI;
- avoid dense text and tiny logos that disappear in social cards.
antigravity-awesome-skills/docs/maintainers/skills-update-guide.md
+1 -1
View File
@@ -72,7 +72,7 @@ The update process refreshes:
- Canonical skills index (`skills_index.json`)
- Compatibility mirror (`data/skills_index.json`)
- Web app skills data (`apps\web-app\public\skills.json`)
- All 1,929+ skills from the skills directory
- All 1,935+ skills from the skills directory
## When to Update
antigravity-awesome-skills/docs/users/bundles.md
+1 -1
View File
@@ -1061,4 +1061,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
---
_Last updated: June 2026 | Total Skills: 1,929+ | Total Bundles: 59_
_Last updated: June 2026 | Total Skills: 1,935+ | Total Bundles: 59_
antigravity-awesome-skills/docs/users/claude-code-skills.md
+1 -1
View File
@@ -12,7 +12,7 @@ Install the library into Claude Code, then invoke focused skills directly in the
## Why use this repo for Claude Code
- It includes 1,929+ skills instead of a narrow single-domain starter pack.
- It includes 1,935+ skills instead of a narrow single-domain starter pack.
- It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
- It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata.
- It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.
antigravity-awesome-skills/docs/users/gemini-cli-skills.md
+1 -1
View File
@@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim
- It installs directly into the expected Gemini skills path.
- It includes both core software engineering skills and deeper agent/LLM-oriented skills.
- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,929+ files.
- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,935+ files.
- It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.
## Install Gemini CLI Skills
antigravity-awesome-skills/docs/users/getting-started.md
+1 -1
View File
@@ -1,4 +1,4 @@
# Getting Started with Antigravity Awesome Skills (V13.12.0)
# Getting Started with Antigravity Awesome Skills (V13.13.0)
**New here? This guide will help you supercharge your AI Agent in 5 minutes.**
antigravity-awesome-skills/docs/users/kiro-integration.md
+1 -1
View File
@@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines:
Kiro's agentic capabilities are enhanced by skills that provide:
- **Domain expertise** across 1,929+ specialized areas
- **Domain expertise** across 1,935+ specialized areas
- **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS
- **Workflow automation** for common development tasks
- **AWS-specific patterns** for serverless, infrastructure, and cloud architecture
antigravity-awesome-skills/docs/users/usage.md
+4 -4
View File
@@ -14,7 +14,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of a full l
When you ran `npx antigravity-awesome-skills` or cloned the repository, you:
✅ **Downloaded 1,929+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
✅ **Downloaded 1,935+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
✅ **Made them available** to your AI assistant
❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)
@@ -34,7 +34,7 @@ Bundles are **curated groups** of skills organized by role. They help you decide
**Analogy:**
- You installed a toolbox with 1,929+ tools (✅ done)
- You installed a toolbox with 1,935+ tools (✅ done)
- Bundles are like **labeled organizer trays** saying: "If you're a carpenter, start with these 10 tools"
- You can either **pick skills from the tray** or install that tray as a focused marketplace bundle plugin
@@ -212,7 +212,7 @@ Let's actually use a skill right now. Follow these steps:
## Step 5: Picking Your First Skills (Practical Advice)
Don't try to use all 1,929+ skills at once. Here's a sensible approach:
Don't try to use all 1,935+ skills at once. Here's a sensible approach:
If you want a tool-specific starting point before choosing skills, use:
@@ -343,7 +343,7 @@ Usually no, but if your AI doesn't recognize a skill:
### "Can I load all skills into the model at once?"
No. Even though you have 1,929+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
No. Even though you have 1,935+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
The intended pattern is:
antigravity-awesome-skills/docs/users/visual-guide.md
+4 -4
View File
@@ -34,7 +34,7 @@ antigravity-awesome-skills/
├── 📄 CONTRIBUTING.md ← Contributor workflow
├── 📄 CATALOG.md ← Full generated catalog
│
├── 📁 skills/ ← 1,929+ skills live here
├── 📁 skills/ ← 1,935+ skills live here
│ │
│ ├── 📁 brainstorming/
│ │ └── 📄 SKILL.md ← Skill definition
@@ -47,7 +47,7 @@ antigravity-awesome-skills/
│ │ └── 📁 2d-games/
│ │ └── 📄 SKILL.md ← Nested skills also supported
│ │
│ └── ... (1,929+ total)
│ └── ... (1,935+ total)
│
├── 📁 apps/
│ └── 📁 web-app/ ← Interactive browser
@@ -100,7 +100,7 @@ antigravity-awesome-skills/
```
┌─────────────────────────┐
│ 1,929+ SKILLS │
│ 1,935+ SKILLS │
└────────────┬────────────┘
│
┌────────────────────────┼────────────────────────┐
@@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
│ ├── 📁 brainstorming/ │
│ ├── 📁 stripe-integration/ │
│ ├── 📁 react-best-practices/ │
│ └── ... (1,929+ total) │
│ └── ... (1,935+ total) │
└─────────────────────────────────────────┘
```
antigravity-awesome-skills/package-lock.json
Generated
+2 -2
View File
@@ -1,12 +1,12 @@
{
"name": "antigravity-awesome-skills",
"version": "13.12.0",
"version": "13.13.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "antigravity-awesome-skills",
"version": "13.12.0",
"version": "13.13.0",
"license": "MIT",
"dependencies": {
"sanitize-filename": "^1.6.4",
antigravity-awesome-skills/package.json
+2 -2
View File
@@ -1,7 +1,7 @@
{
"name": "antigravity-awesome-skills",
"version": "13.12.0",
"description": "1,929+ agentic skills for Claude Code, Gemini CLI, Cursor, Antigravity & more. Installer CLI.",
"version": "13.13.0",
"description": "1,935+ agentic skills for Claude Code, Gemini CLI, Cursor, Antigravity & more. Installer CLI.",
"license": "MIT",
"scripts": {
"validate": "node tools/scripts/run-python.js tools/scripts/validate_skills.py",
antigravity-awesome-skills/plugins/antigravity-awesome-skills-claude/.claude-plugin/plugin.json
+2 -2
View File
@@ -1,7 +1,7 @@
{
"name": "antigravity-awesome-skills",
"version": "13.12.0",
"description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,878 supported skills.",
"version": "13.13.0",
"description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,884 supported skills.",
"author": {
"name": "sickn33 and contributors",
"url": "https://github.com/sickn33/antigravity-awesome-skills"
antigravity-awesome-skills/plugins/antigravity-awesome-skills-claude/skills/codex-profiles/SKILL.md
+170
View File
@@ -0,0 +1,170 @@
---
name: codex-profiles
description: "Use codex-profiles to run Codex CLI or Codex Desktop with isolated CODEX_HOME profiles for separate accounts, projects, and local state."
category: productivity
risk: critical
source: community
source_repo: Ducksss/codex-profiles
source_type: community
date_added: "2026-07-08"
author: Ducksss
tags: [codex, codex-cli, profiles, code-home, account-isolation, desktop]
tools: [codex]
license: "MIT"
license_source: "https://github.com/Ducksss/codex-profiles/blob/main/LICENSE"
---
# Codex Profiles
## Overview
Use `codex-profiles` when a user wants separate Codex CLI or Codex Desktop contexts for work, personal, school, client, or project-specific activity. The tool wraps Codex's `CODEX_HOME` support so each profile has its own Codex home directory for auth, config, sessions, connectors, plugins, caches, logs, and local state.
This skill is for profile selection and operational safety around that boundary. It is not an official OpenAI project, and it does not provide full OS-level isolation.
## When to Use This Skill
- Use when the user wants to keep multiple Codex accounts or project contexts separate on one machine.
- Use when a workflow needs a different `CODEX_HOME` without manually exporting environment variables.
- Use when diagnosing which Codex profile is active or whether profiles are logged in.
- Use when the user asks about Codex account switching without copying `auth.json`.
- Use when launching Codex Desktop from a profile, only after confirming the user accepts app/process disruption.
## How It Works
### Step 1: Confirm Scope and Installation
First check whether the user wants CLI-only profile switching or Codex Desktop profile launching. Desktop operations can quit, launch, clone, or rebuild app instances, so get explicit approval before running them.
If the tool is already installed, inspect the live command surface:
```bash
codex-profile --help
codex-profile doctor
codex-profile list
codex-profile status
```
If it is not installed, prefer package-manager installs the user can inspect and control:
```bash
npm install -g codex-profile
brew install Ducksss/tap/codex-profile
```
Do not run remote install scripts automatically. If the user asks for a source install, clone the repository and inspect its install instructions first.
### Step 2: Create or Select a Profile
Create a new isolated Codex home only when the user names the intended profile:
```bash
codex-profile init work
codex-profile path work
```
Ask the user to log in once per profile when needed:
```bash
codex-profile login work
```
Do not copy, parse, print, or migrate `auth.json` tokens between profiles.
### Step 3: Run Codex CLI With a Profile
Use the CLI profile wrapper for ordinary agent work:
```bash
codex-profile cli work
codex-profile cli work exec "run tests and summarize failures"
```
For one-off shell sessions, prefer the tool's environment or shell activation commands after checking `--help`:
```bash
codex-profile env work
codex-profile shell-init --help
```
### Step 4: Use Desktop Profile Commands Carefully
Codex Desktop launch flows can affect running app state. Before running them, state which profile, app mode, and workspace will be used, then wait for approval.
```bash
codex-profile app work ~/Dev/project
codex-profile app work --instance ~/Dev/project
```
Use `--instance` only when the user wants side-by-side Desktop profiles and accepts the additional local app clone and separate Electron user-data boundary.
## Examples
### Example 1: Read-Only Profile Audit
```bash
codex-profile list
codex-profile status
codex-profile doctor
```
Use this before changing profile state. It should not expose token contents.
### Example 2: CLI Task in a Work Profile
```bash
codex-profile cli work exec "inspect this repository and run its test suite"
```
Confirm the profile name is intentional before running long tasks.
### Example 3: Manual CODEX_HOME Equivalent
If the wrapper is unavailable, explain the underlying boundary instead of improvising token movement:
```bash
CODEX_HOME="$HOME/.codex-work" codex
CODEX_HOME="$HOME/.codex-work" codex exec "review this change"
```
## Best Practices
- Keep profile names explicit and boring, such as `work`, `personal`, `client-a`, or `school`.
- Use `status`, `list`, and `doctor` before destructive or Desktop actions.
- Treat each profile as a separate local Codex home, not as a full sandbox.
- Keep secrets inside the account/profile that owns them; do not copy auth files between profiles.
- Prefer CLI profile commands for routine work and reserve Desktop app commands for user-approved context switches.
- Verify behavior against the installed `codex-profile --help`, because command flags can change.
## Limitations
- `codex-profiles` is community-maintained and is not an official OpenAI tool.
- It isolates Codex state through separate `CODEX_HOME` directories; it does not isolate the operating-system user, shell history, SSH keys, browser cookies, GitHub CLI auth, or unrelated application state.
- Desktop profile launch behavior is macOS-focused and can change with Codex Desktop releases.
- Existing Codex sessions may still contain project context from before a profile strategy was adopted.
- The tool does not replace backups for important Codex state.
## Security & Safety Notes
- Never copy, print, parse, or migrate `auth.json` tokens as a shortcut.
- Do not run Desktop launch, app clone, rebuild, remove, or profile deletion commands without explicit user approval.
- Use `codex-profile remove` only after confirming the exact profile path and whether the user needs a backup.
- Do not assume profile isolation protects credentials outside `CODEX_HOME`.
- Avoid remote install scripts in automated agent runs; prefer inspectable package-manager or source-install steps.
## Common Pitfalls
- **Problem:** A user expects profile switching to isolate GitHub CLI, SSH, or browser state.
**Solution:** Explain that `codex-profiles` isolates Codex home state only; check and switch other tools separately.
- **Problem:** A Desktop command disrupts an active session.
**Solution:** Ask before Desktop operations and prefer CLI commands when the user only needs isolated command-line work.
- **Problem:** A profile exists but is logged out or missing connectors.
**Solution:** Run `codex-profile status` and have the user log in or configure connectors inside that profile.
## Related Skills
- `@environment-setup-guide` - Use when installing or documenting local development tools.
- `@codex-maintenance` - Use when maintaining local Codex Desktop, MCP, plugin, or cache surfaces.
- `@filesystem-context` - Use when reasoning about local files, config paths, and workspace boundaries.
antigravity-awesome-skills/plugins/antigravity-awesome-skills-claude/skills/go-in-depth/SKILL.md
+59
View File
@@ -0,0 +1,59 @@
---
name: go-in-depth
description: Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.
risk: safe
source: self
source_type: self
date_added: "2026-07-07"
---
# Go In Depth
## Overview
Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. Run the "go-in-depth" workflow.
## When to Use
When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., "what car to buy" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.
## How It Works
Phases:
- Scope: Decompose question (from args) into 5 search angles
- Search: 5 parallel WebSearch agents, one per angle
- Fetch: URL-dedup, fetch top 15 sources, extract falsifiable claims
- Verify: 3-vote adversarial verification per claim (need 2/3 refutes to kill)
- Synthesize: Merge semantic dupes, rank by confidence, cite sources
## Examples
### Example 1: Run go-in-depth workflow
```
Workflow({ name: "go-in-depth" })
```
### Example 2: Research with refined question
```
Workflow({ name: "go-in-depth", args: { query: "best hybrid cars under $30k in the US for families" } })
```
### Example 3: Deep dive into a technical concept
```
Workflow({ name: "go-in-depth", args: { query: "how does the transformer architecture handle positional encoding?" } })
```
### Example 4: Fact-checking a medical claim
```
Workflow({ name: "go-in-depth", args: { query: "efficacy of intermittent fasting for long-term weight loss in adults" } })
```
## Workflow Script
[scripts/workflow-script.js](scripts/workflow-script.js)
## Limitations
- **Slow execution**: Multi-agent searches, fetching, and 3-vote verification take significant time. Not for quick facts.
- **Context intensive**: Analyzing 15 full sources uses large context limits.
- **Synthesis risks**: May struggle if source material is weak or equally conflicting.
antigravity-awesome-skills/plugins/antigravity-awesome-skills-claude/skills/go-in-depth/scripts/workflow-script.js
+350
View File
@@ -0,0 +1,350 @@
export const meta = {
name: 'go-in-depth',
description: 'Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.',
whenToUse: 'When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., "what car to buy" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.',
phases: [{"title":"Scope","detail":"Decompose question (from args) into 5 search angles"},{"title":"Search","detail":"5 parallel WebSearch agents, one per angle"},{"title":"Fetch","detail":"URL-dedup, fetch top 15 sources, extract falsifiable claims"},{"title":"Verify","detail":"3-vote adversarial verification per claim (need 2/3 refutes to kill)"},{"title":"Synthesize","detail":"Merge semantic dupes, rank by confidence, cite sources"}],
}
// go-in-depth: Scope → pipeline(Search → URL-dedup → Fetch+Extract) → 3-vote Verify → Synthesize
// Uses a bug-hunting-style fan-out and verification pattern, adapted for web research.
// Question is passed via Workflow({name: 'go-in-depth', args: '<question>'}).
const VOTES_PER_CLAIM = 3
const REFUTATIONS_REQUIRED = 2
const MAX_FETCH = 15
const MAX_VERIFY_CLAIMS = 25
// ─── Schemas ───
const SCOPE_SCHEMA = {
type: "object", required: ["question", "angles", "summary"],
properties: {
question: { type: "string" },
summary: { type: "string" },
angles: { type: "array", minItems: 3, maxItems: 6, items: {
type: "object", required: ["label", "query"],
properties: {
label: { type: "string" },
query: { type: "string" },
rationale: { type: "string" },
},
}},
},
}
const SEARCH_SCHEMA = {
type: "object", required: ["results"],
properties: {
results: { type: "array", maxItems: 6, items: {
type: "object", required: ["url", "title", "relevance"],
properties: {
url: { type: "string" },
title: { type: "string" },
snippet: { type: "string" },
relevance: { enum: ["high", "medium", "low"] },
},
}},
},
}
const EXTRACT_SCHEMA = {
type: "object", required: ["claims", "sourceQuality"],
properties: {
sourceQuality: { enum: ["primary", "secondary", "blog", "forum", "unreliable"] },
publishDate: { type: "string" },
claims: { type: "array", maxItems: 5, items: {
type: "object", required: ["claim", "quote", "importance"],
properties: {
claim: { type: "string" },
quote: { type: "string" },
importance: { enum: ["central", "supporting", "tangential"] },
},
}},
},
}
const VERDICT_SCHEMA = {
type: "object", required: ["refuted", "evidence", "confidence"],
properties: {
refuted: { type: "boolean" },
evidence: { type: "string" },
confidence: { enum: ["high", "medium", "low"] },
counterSource: { type: "string" },
},
}
const REPORT_SCHEMA = {
type: "object", required: ["summary", "findings", "caveats"],
properties: {
summary: { type: "string" },
findings: { type: "array", items: {
type: "object", required: ["claim", "confidence", "sources", "evidence"],
properties: {
claim: { type: "string" },
confidence: { enum: ["high", "medium", "low"] },
sources: { type: "array", items: { type: "string" } },
evidence: { type: "string" },
vote: { type: "string" },
},
}},
caveats: { type: "string" },
openQuestions: { type: "array", items: { type: "string" } },
},
}
// ─── Phase 0: Scope — decompose question into search angles ───
phase("Scope")
const QUESTION = (typeof args === "string" ? args.trim() : args?.query?.trim()) || ""
if (!QUESTION) {
return { error: "No research question provided. Pass it as args: Workflow({name: 'go-in-depth', args: '<question>'})." }
}
const scope = await agent(
"Decompose this research question into complementary search angles.\n\n" +
"## Question\n" + QUESTION + "\n\n" +
"## Task\n" +
"Generate 5 distinct web search queries that together cover the question from different angles. Pick angles that suit the question's domain. Examples:\n" +
"- broad/primary · academic/technical · recent news · contrarian/skeptical · practitioner/implementation\n" +
"- For medical: anatomy · common causes · serious differentials · authoritative refs · red flags\n" +
"- For tech: state-of-art · benchmarks · limitations · industry adoption · cost/tradeoffs\n\n" +
"Make queries specific enough to surface high-signal results. Avoid redundancy.\n" +
"Return: the question (verbatim or lightly normalized), a 1-2 sentence decomposition strategy, and the angles.\n\nStructured output only.",
{ label: "scope", schema: SCOPE_SCHEMA }
)
if (!scope) {
return { error: "Scope agent returned no result — cannot decompose the research question." }
}
log("Q: " + QUESTION.slice(0, 80) + (QUESTION.length > 80 ? "…" : ""))
log("Decomposed into " + scope.angles.length + " angles: " + scope.angles.map(a => a.label).join(", "))
// ─── Dedup state — accumulates across searchers as they complete ───
const normURL = u => {
try {
const p = new URL(u)
return (p.hostname.replace(/^www\./, "") + p.pathname.replace(/\/$/, "")).toLowerCase()
} catch { return u.toLowerCase() }
}
const seen = new Map()
const dupes = []
const budgetDropped = []
const relRank = { high: 0, medium: 1, low: 2 }
let fetchSlots = MAX_FETCH
// ─── Prompts ───
const SEARCH_PROMPT = (angle) =>
"## Web Searcher: " + angle.label + "\n\n" +
"Research question: \"" + QUESTION + "\"\n\n" +
"Your angle: **" + angle.label + "** — " + (angle.rationale || "") + "\n" +
"Search query: `" + angle.query + "`\n\n" +
"## Task\nUse WebSearch with the query above (or a refined version). Return the top 4-6 most relevant results.\n" +
"Rank by relevance to the ORIGINAL question, not just the search query. Skip obvious SEO spam/content farms.\n" +
"Include a short snippet capturing why each result is relevant.\n\nStructured output only."
const FETCH_PROMPT = (source, angle) =>
"## Source Extractor\n\n" +
"Research question: \"" + QUESTION + "\"\n\n" +
"Fetch and extract key claims from this source:\n" +
"**URL:** " + source.url + "\n**Title:** " + source.title + "\n**Found via:** " + angle + " search\n\n" +
"## Task\n1. Use WebFetch to retrieve the page content.\n" +
"2. Assess source quality: primary research/institution? secondary reporting? blog/opinion? forum? unreliable?\n" +
"3. Extract 2-5 FALSIFIABLE claims that bear on the research question. Each claim must:\n" +
" - be a concrete, checkable statement (not vague generalities)\n" +
" - include a direct quote from the source as support\n" +
" - be rated central/supporting/tangential to the research question\n" +
"4. Note publish date if available.\n\n" +
"If the fetch fails or the page is irrelevant/paywalled, return claims: [] and sourceQuality: \"unreliable\".\n\nStructured output only."
const VERIFY_PROMPT = (claim, v) =>
"## Adversarial Claim Verifier (voter " + (v + 1) + "/" + VOTES_PER_CLAIM + ")\n\n" +
"Be SKEPTICAL. Try to REFUTE this claim. ≥" + REFUTATIONS_REQUIRED + "/" + VOTES_PER_CLAIM + " refutations kill it.\n\n" +
"## Research question\n" + QUESTION + "\n\n" +
"## Claim under review\n\"" + claim.claim + "\"\n\n" +
"**Source:** " + claim.sourceUrl + " (" + claim.sourceQuality + ")\n" +
"**Supporting quote:** \"" + claim.quote + "\"\n\n" +
"## Checklist\n" +
"1. Is the claim actually supported by the quote, or is it an overreach/misread?\n" +
"2. WebSearch for contradicting evidence — does any credible source dispute or heavily qualify this?\n" +
"3. Is the source quality sufficient for the claim's strength? (extraordinary claims need primary sources)\n" +
"4. Is the claim outdated? (check dates — old claims about fast-moving fields are suspect)\n" +
"5. Is this a marketing claim / press release / cherry-picked benchmark / forum speculation?\n\n" +
"**refuted=true** if: unsupported by quote / contradicted / low-quality source for strong claim / outdated / marketing fluff.\n" +
"**refuted=false** ONLY if: claim is well-supported, current, and source quality matches claim strength.\n" +
"Default to refuted=true if uncertain.\n\nStructured output only. Evidence MUST be specific."
// ─── Pipeline: search → dedup → fetch+extract (no barrier) ───
const searchResults = await pipeline(
scope.angles,
angle => agent(SEARCH_PROMPT(angle), {
label: "search:" + angle.label, phase: "Search", schema: SEARCH_SCHEMA
}).then(r => {
if (!r) return null
log(angle.label + ": " + r.results.length + " results")
return { angle: angle.label, results: r.results }
}),
searchResult => {
const sorted = [...searchResult.results].sort((a, b) => relRank[a.relevance] - relRank[b.relevance])
const novel = sorted.filter(r => {
const key = normURL(r.url)
if (seen.has(key)) {
dupes.push({ ...r, angle: searchResult.angle, dupOf: seen.get(key) })
return false
}
if (fetchSlots <= 0) {
budgetDropped.push({ ...r, angle: searchResult.angle })
return false
}
seen.set(key, { angle: searchResult.angle, title: r.title })
fetchSlots--
return true
})
if (novel.length < searchResult.results.length) {
log(searchResult.angle + ": " + novel.length + " novel (" + (searchResult.results.length - novel.length) + " filtered)")
}
return parallel(
novel.map(source => () => {
let host = "unknown"
try { host = new URL(source.url).hostname.replace(/^www\./, "") } catch {}
return agent(FETCH_PROMPT(source, searchResult.angle), {
label: "fetch:" + host,
phase: "Fetch",
schema: EXTRACT_SCHEMA,
}).then(ext => {
// User-skip → null; drop it (filtered by searchResults.flat().filter(Boolean))
// rather than throwing into .catch() and mislabeling it "unreliable".
if (!ext) return null
return {
url: source.url, title: source.title, angle: searchResult.angle,
sourceQuality: ext.sourceQuality, publishDate: ext.publishDate,
claims: ext.claims.map(c => ({ ...c, sourceUrl: source.url, sourceQuality: ext.sourceQuality })),
}
}).catch(e => {
log("fetch failed: " + source.url + " — " + (e.message || e))
return { url: source.url, title: source.title, angle: searchResult.angle, sourceQuality: "unreliable", claims: [] }
})
})
)
}
)
const allSources = searchResults.flat().filter(Boolean)
const allClaims = allSources.flatMap(s => s.claims)
const impRank = { central: 0, supporting: 1, tangential: 2 }
const qualRank = { primary: 0, secondary: 1, blog: 2, forum: 3, unreliable: 4 }
const rankedClaims = [...allClaims]
.sort((a, b) => (impRank[a.importance] - impRank[b.importance]) || (qualRank[a.sourceQuality] - qualRank[b.sourceQuality]))
.slice(0, MAX_VERIFY_CLAIMS)
log("Fetched " + allSources.length + " sources → " + allClaims.length + " claims → verifying top " + rankedClaims.length)
if (rankedClaims.length === 0) {
return {
question: QUESTION,
summary: "No claims extracted. " + allSources.length + " sources fetched, all empty/failed. " + dupes.length + " URL dupes, " + budgetDropped.length + " budget-dropped.",
findings: [], refuted: [], sources: allSources.map(s => ({ url: s.url, quality: s.sourceQuality })),
stats: { angles: scope.angles.length, sources: allSources.length, claims: 0, dupes: dupes.length },
}
}
// ─── Verify: 3-vote adversarial ───
// Barrier here is intentional — claim pool must be fully assembled before ranking/verification.
phase("Verify")
const voted = (await parallel(
rankedClaims.map(claim => () =>
parallel(
Array.from({ length: VOTES_PER_CLAIM }, (_, v) => () =>
agent(VERIFY_PROMPT(claim, v), {
label: "v" + v + ":" + claim.claim.slice(0, 40),
phase: "Verify",
schema: VERDICT_SCHEMA,
})
)
).then(verdicts => {
// A vote can be null (user-skip or agent error) — treat as abstain.
const valid = verdicts.filter(Boolean)
const refuted = valid.filter(v => v.refuted).length
// Survive only if the claim was actually adjudicated: a quorum of
// valid votes AND fewer than REFUTATIONS_REQUIRED refuting. Too many
// abstentions = unverified, which must NOT pass into the report
// (otherwise all-abstain → refuted=0 → false survive).
const abstained = VOTES_PER_CLAIM - valid.length
const survives = valid.length >= REFUTATIONS_REQUIRED && refuted < REFUTATIONS_REQUIRED
log("\"" + claim.claim.slice(0, 50) + "…\": " + (valid.length - refuted) + "-" + refuted + (abstained > 0 ? " (" + abstained + " abstain)" : "") + " " + (survives ? "✓" : "✗"))
return { ...claim, verdicts: valid, refutedVotes: refuted, survives }
})
)
)).filter(Boolean)
const confirmed = voted.filter(c => c.survives)
const killed = voted.filter(c => !c.survives)
log("Verify done: " + voted.length + " claims → " + confirmed.length + " confirmed, " + killed.length + " killed")
if (confirmed.length === 0) {
return {
question: QUESTION,
summary: "All " + voted.length + " claims refuted by adversarial verification. Research inconclusive — sources may be low-quality or claims overstated.",
findings: [],
refuted: killed.map(c => ({ claim: c.claim, vote: (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes, source: c.sourceUrl })),
sources: allSources.map(s => ({ url: s.url, quality: s.sourceQuality, claimCount: s.claims.length })),
stats: { angles: scope.angles.length, sources: allSources.length, claims: allClaims.length, verified: voted.length, confirmed: 0, killed: killed.length },
}
}
// ─── Synthesize ───
phase("Synthesize")
const confRank = { high: 0, medium: 1, low: 2 }
const block = confirmed.map((c, i) => {
const best = c.verdicts.filter(v => !v.refuted).sort((a, b) => confRank[a.confidence] - confRank[b.confidence])[0]
return "### [" + i + "] " + c.claim + "\n" +
"Vote: " + (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes + " · Source: " + c.sourceUrl + " (" + c.sourceQuality + ")\n" +
"Quote: \"" + c.quote + "\"\nVerifier evidence (" + best.confidence + "): " + best.evidence + "\n"
}).join("\n")
const killedBlock = killed.length > 0
? "\n## Refuted claims (for transparency)\n" +
killed.map(c => "- \"" + c.claim + "\" (" + c.sourceUrl + ", vote " + (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes + ")").join("\n")
: ""
const report = await agent(
"## Synthesis: research report\n\n" +
"**Question:** " + QUESTION + "\n\n" +
confirmed.length + " claims survived " + VOTES_PER_CLAIM + "-vote adversarial verification. Merge semantic duplicates and synthesize.\n\n" +
"## Confirmed claims\n" + block + "\n" + killedBlock + "\n\n" +
"## Instructions\n" +
"1. Identify claims that say the same thing — merge them, combine their sources.\n" +
"2. Group related claims into coherent findings. Each finding should directly address the research question.\n" +
"3. Assign confidence per finding: high (multiple primary sources, unanimous votes), medium (secondary sources or split votes), low (single source or blog-quality).\n" +
"4. Write a 3-5 sentence executive summary answering the research question.\n" +
"5. Note caveats: what's uncertain, what sources were weak, what time-sensitivity applies.\n" +
"6. List 2-4 open questions that emerged but weren't answered.\n\nStructured output only.",
{ label: "synthesize", schema: REPORT_SCHEMA }
)
if (!report) {
// Synthesis skipped/errored — salvage the verified claims raw rather
// than throwing on report.findings and discarding the whole run.
return {
question: QUESTION,
summary: "Synthesis step was skipped or failed — returning " + confirmed.length + " verified claims unmerged.",
findings: [],
confirmed: confirmed.map(c => ({ claim: c.claim, source: c.sourceUrl, quote: c.quote, vote: (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes })),
refuted: killed.map(c => ({ claim: c.claim, vote: (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes, source: c.sourceUrl })),
sources: allSources.map(s => ({ url: s.url, quality: s.sourceQuality, claimCount: s.claims.length })),
stats: { angles: scope.angles.length, sources: allSources.length, claims: allClaims.length, verified: voted.length, confirmed: confirmed.length, killed: killed.length, afterSynthesis: 0 },
}
}
return {
question: QUESTION,
...report,
refuted: killed.map(c => ({ claim: c.claim, vote: (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes, source: c.sourceUrl })),
sources: allSources.map(s => ({ url: s.url, quality: s.sourceQuality, angle: s.angle, claimCount: s.claims.length })),
stats: {
angles: scope.angles.length,
sourcesFetched: allSources.length,
claimsExtracted: allClaims.length,
claimsVerified: voted.length,
confirmed: confirmed.length,
killed: killed.length,
afterSynthesis: report.findings.length,
urlDupes: dupes.length,
budgetDropped: budgetDropped.length,
agentCalls: 1 + scope.angles.length + allSources.length + (voted.length * VOTES_PER_CLAIM) + 1,
},
}
antigravity-awesome-skills/plugins/antigravity-awesome-skills-claude/skills/pilot-protocol/SKILL.md
+145
View File
@@ -0,0 +1,145 @@
---
name: pilot-protocol
description: "Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol"
category: ai-agents
risk: critical
source: community
source_repo: pilot-protocol/pilotprotocol
source_type: official
date_added: "2026-07-07"
author: pilot-protocol
tags: [agent-networking, p2p, nat-traversal, overlay-network, agent-apps]
tools: [claude, cursor, gemini, codex]
license: "AGPL-3.0"
license_source: "https://github.com/pilot-protocol/pilotprotocol/blob/main/LICENSE"
---
# Pilot Protocol
## Overview
Pilot Protocol is an open-source overlay network that gives AI agents first-class
network citizenship: a permanent virtual address, encrypted UDP tunnels, NAT
traversal, and an explicit per-peer trust model. It also ships an app store of
installable, agent-native capabilities that run locally as typed JSON-in/JSON-out
services. Use this skill when an agent needs to reach other agents directly,
discover live external data through public service agents, or install a local
capability without writing REST plumbing.
If this skill adapts material from an external GitHub repository, it declares:
- `source_repo: pilot-protocol/pilotprotocol`
- `source_type: official`
## When to Use This Skill
- Use when an agent needs a stable address that survives restarts, IP changes,
or moving across clouds (no more re-registering webhooks).
- Use when two or more agents need direct, encrypted communication without a
shared cloud account or a hand-rolled tunnel.
- Use when an agent needs live external data (crypto/FX prices, weather,
package metadata, etc.) via structured JSON instead of scraping HTML.
- Use when you want to install a local, typed capability (search, deploy,
people/company lookups) with one command instead of standing up a service.
## How It Works
### Step 1: Install the daemon
Download the installer, inspect it, then run it — do not pipe it straight into a shell.
```bash
curl -fsSL https://pilotprotocol.network/install.sh -o /tmp/pilot-install.sh
less /tmp/pilot-install.sh # review before executing
sh /tmp/pilot-install.sh
```
### Step 2: Start the node and confirm it registered
```bash
pilotctl daemon start
pilotctl info
```
### Step 3: Query a service agent (no handshake needed)
Service agents in the public directory auto-approve incoming messages.
```bash
pilotctl send-message list-agents --data '/data {"search":"weather"}' --wait
jq -r '.data' "$(ls -1t ~/.pilot/inbox/*.json | head -1)"
```
### Step 4: Handshake a peer agent for direct messaging
Peer nodes (as opposed to service agents) require mutual approval before a
tunnel works.
```bash
pilotctl handshake <hostname|node_id|address> "<reason>"
pilotctl trust
pilotctl send-message <peer> --data '<message>'
```
### Step 5: Install and call an agent app
```bash
pilotctl appstore catalogue
pilotctl appstore install <app-id>
pilotctl appstore call <app-id> <app>.help '{}'
```
## Examples
### Example 1: Ask a live-data service agent
```bash
pilotctl send-message list-agents --data '/data {"search":"bitcoin"}' --wait
jq -r '.data' "$(ls -1t ~/.pilot/inbox/*.json | head -1)"
```
### Example 2: Install and call a local capability app
```bash
pilotctl appstore install io.pilot.cosift
pilotctl appstore call io.pilot.cosift cosift.answer '{"q":"What is HNSW?"}'
```
## Best Practices
- ✅ Use `--wait` on `send-message` so the reply is guaranteed to be in the
inbox before you read it.
- ✅ Query `list-agents` before guessing a hostname — the catalogue changes.
- ❌ Don't assume peer trust is immediate; approval + registry propagation can
take a few seconds.
- ❌ Don't set `--auto-answer` on your own node — it's a service-agent-only flag.
## Limitations
- This skill does not replace reading `pilotctl --help` or the project docs
for less common commands.
- Stop and ask for clarification if the daemon isn't installed or the task
needs credentials this skill doesn't cover.
## Security & Safety Notes
- The install script fetches an installer from `pilotprotocol.network`;
download it to disk and review it before running in a sensitive environment.
- `~/.pilot/identity.json` is a private keypair — never copy it between hosts.
- Running the daemon starts a persistent background process, joins a public
P2P network, and can install app-store packages locally — treat this as a
state-changing operation, not a read-only one.
## Common Pitfalls
- **Problem:** A `send-message` to a peer silently fails right after a handshake.
**Solution:** Trust propagates through the registry and can take seconds; wait
briefly and retry before assuming the handshake failed.
- **Problem:** Large replies arrive truncated in the inbox JSON.
**Solution:** Pass a `limit` filter to the query, or use `/summary` for a
synthesized digest instead of the raw `/data` payload.
## Related Skills
- `@network-101` - General networking background before diving into overlay
networks specifically.
antigravity-awesome-skills/plugins/antigravity-awesome-skills-claude/skills/pre-ship-gate/SKILL.md
+129
View File
@@ -0,0 +1,129 @@
---
name: pre-ship-gate
description: "A ship gate that runs before any production deploy: checks the silent failure modes that make a deploy 'succeed' while prod stays broken, then verifies the live revision instead of trusting deploy output."
category: quality
risk: safe
source: community
source_repo: Sharrmavishal/operating-kit
source_type: community
date_added: "2026-07-07"
author: Sharrmavishal
tags: [deployment, quality-gate, verification, ci-cd, production]
tools: [claude, cursor, gemini]
license: MIT
license_source: "https://github.com/Sharrmavishal/operating-kit/blob/main/LICENSE"
---
# Pre-Ship Gate
## Overview
Most bad deploys do not fail loudly. The pipeline goes green, the CLI prints "deployed", and the old or broken version is still what users hit. This skill is the gate you run right before a production deploy and right after, so an agent stops trusting deploy output and starts confirming what is actually live. It exists because "the deploy command exited 0" and "the new version is serving traffic" are two different facts, and agents routinely confuse them.
## When to Use This Skill
- Use before running any command that pushes to a production or staging environment.
- Use when an agent is about to report "shipped", "deployed", or "live".
- Use when a deploy reported success but users still see the old behavior.
- Use when a release involves database migrations, feature flags, or a staged rollout.
## How It Works
The gate has three phases. Do not skip to phase 3.
### Phase 1: Pre-flight (before the deploy runs)
Walk the silent failure catalog. These are the modes that let a deploy "succeed" while production stays broken. For each one, confirm it or flag it. Do not assume.
- **Migrations**: Are schema migrations part of this release, and will they run against the target before the new code serves traffic? A deploy that ships code expecting a column that does not exist yet fails silently for users, not for the pipeline.
- **Feature flags**: Is the flag that gates this change actually enabled in the target environment, not just in dev? Shipped code behind an off flag looks like a no-op deploy.
- **Build cache / stale assets**: Could a cached build or CDN layer serve the previous bundle after deploy? Confirm the artifact hash or asset fingerprint changed.
- **Release pointer**: Does the deploy update the symlink, active revision, or traffic pointer, or does it only upload the new build? Uploading is not releasing.
- **Staged rollout / canary**: If traffic is staged, is it stuck at 0 percent or waiting on a manual promote? A canary that never promotes is not a deploy.
- **Env and secrets**: Are the env vars and secrets the new code needs present in the target, not just locally? Missing config surfaces as runtime errors, not deploy errors.
### Phase 2: Run the deploy
The human or the deploy tooling runs the actual command. This skill does not execute the production deploy itself. It gates it.
### Phase 3: Verify live (before saying "shipped")
Confirm the running system, not the deploy log.
- Fetch the live version or revision identifier from the running service and compare it to the one you intended to ship.
- Hit a health or status endpoint and confirm it returns the expected version, not just HTTP 200.
- Tail production logs for the first errors after cutover.
- Only after the live revision matches the intended revision may you report "shipped". If it does not match, report the mismatch, not success.
## Examples
### Example 1: Verifying the live revision instead of trusting the deploy log
```bash
# You intended to ship this commit
INTENDED="$(git rev-parse --short HEAD)"
# Ask the running service what it is actually serving
LIVE="$(curl -fsS https://your-service.example.com/health | jq -r '.revision')"
if [ "$INTENDED" = "$LIVE" ]; then
echo "Live revision $LIVE matches intended $INTENDED: verified shipped."
else
echo "MISMATCH: intended $INTENDED but live is $LIVE. Do not report shipped."
fi
```
### Example 2: Pre-flight verdict format an agent can emit
```markdown
PRE-SHIP GATE, verdict: HOLD
- Migrations: 1 pending (add_users_status_col): NOT yet applied to prod. BLOCK.
- Feature flags: new_checkout flag is OFF in prod. Enabling required post-deploy.
- Build assets: new bundle hash confirmed (a1b2c3 != previous 9f8e7d). OK.
- Release pointer: deploy updates active symlink. OK.
- Rollout: canary at 10%, manual promote required. NOTE.
- Env/secrets: STRIPE_KEY present in prod. OK.
Reason for HOLD: run migration add_users_status_col before cutover, or the
new code will 500 on /orders.
```
## Best Practices
- ✅ Treat "the command exited 0" and "the new version is live" as separate facts, and verify the second one.
- ✅ Emit an explicit verdict (SHIP / HOLD) with the failing item named, not a vague "looks good".
- ✅ Compare a live revision identifier against the intended one after every deploy.
- ✅ Name the specific silent failure mode you are worried about, so a human can override with context.
- ❌ Do not report "shipped" from deploy output alone.
- ❌ Do not skip the pre-flight because the pipeline is green.
- ❌ Do not treat a passing health check as proof the right version is live. Check the version field.
## Limitations
- This skill does not run the production deploy for you. It gates and verifies around it.
- It cannot know your environment's exact health or version endpoint. Wire in the real one before relying on the verification phase.
- The silent failure catalog is common cases, not exhaustive. Systems with unusual release mechanics need their own additions.
- It does not replace environment-specific testing, load testing, or expert review.
- Stop and ask for clarification if the target environment, the intended revision, or the verification endpoint is unknown.
## Common Pitfalls
- **Problem:** Health check returns 200 but users still see the old version.
**Solution:** The check is hitting a cached edge or the old pod. Verify the revision field in the response, not just the status code.
- **Problem:** Migration runs after the new code is already serving traffic.
**Solution:** Sequence migrations before cutover, or gate the code path behind a flag until the migration lands.
- **Problem:** Deploy "succeeds" but the canary is stuck at 0 percent.
**Solution:** Confirm the traffic pointer or promotion step, not just the upload step.
## Security & Safety Notes
- This skill is defensive and read-oriented. Its own commands are verification calls (fetching a version endpoint, tailing logs, comparing revisions). It does not itself mutate production.
- The example commands use `curl -fsS` against a status endpoint and are illustrative. Replace the placeholder host and version field with your own before use.
- The actual production deploy is performed by your existing tooling and is out of this skill's scope. Keep human confirmation on the deploy step.
- No credentials or tokens are embedded. Do not paste secrets into health-check URLs.
## Related Skills
- `@codebase-audit-pre-push`: clean and audit the code before it ever reaches a deploy.
- `@dos-verify-done-claims`: verify a "done" claim against git ground truth after the fact.
antigravity-awesome-skills/plugins/antigravity-awesome-skills-claude/skills/routerbase-model-gateway/SKILL.md
+175
View File
@@ -0,0 +1,175 @@
---
name: routerbase-model-gateway
description: "Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests."
category: ai-ml
risk: safe
source: community
source_repo: zenlee123/routerbase-agent-skills
source_type: community
date_added: "2026-07-07"
author: zenlee123
tags: [routerbase, llm-routing, openai-compatible, model-gateway]
tools: [claude, cursor, gemini, codex, antigravity]
license: "MIT-0"
license_source: "https://github.com/zenlee123/routerbase-agent-skills/blob/main/LICENSE"
---
# RouterBase Model Gateway
## Overview
Use [routerbase](https://routerbase.com/) when an application needs one OpenAI-compatible API surface for model routing across GPT, Claude, Gemini, image, video, audio, and embedding workloads. This skill helps agents migrate existing OpenAI SDK calls, document model-selection tradeoffs, and produce safe implementation snippets without exposing credentials.
RouterBase model availability, pricing, and provider capabilities can change, so treat examples as starting points and verify current catalog data before production recommendations.
## When to Use This Skill
- Use when migrating an OpenAI-compatible client to RouterBase by changing the base URL and model ID.
- Use when selecting primary and fallback models for chat, reasoning, vision, media generation, audio, or embeddings.
- Use when debugging RouterBase request setup, headers, environment variables, streaming, tool calls, JSON mode, or multimodal payloads.
- Use when documenting an internal model-routing plan that balances cost, latency, quality, and provider redundancy.
## How It Works
### Step 1: Classify the Workload
Identify the modality and hard constraints before choosing a model:
- Modality: chat, vision, image, video, audio, embeddings, or mixed.
- Quality target: draft, production, high-stakes review, or automated background task.
- Runtime constraints: latency budget, context length, streaming, JSON mode, tool calling, and retry tolerance.
- Business constraints: price ceiling, provider preference, regional requirements, and fallback rules.
### Step 2: Configure the OpenAI-Compatible Client
Keep the RouterBase API key server-side in an environment variable such as `ROUTERBASE_API_KEY`. Do not put keys in browser, mobile, or public repository code.
```python
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ROUTERBASE_API_KEY"],
base_url="https://routerbase.com/v1",
)
response = client.chat.completions.create(
model="google/gemini-2.5-flash",
messages=[{"role": "user", "content": "Write one sentence about model routing."}],
)
print(response.choices[0].message.content)
```
```js
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.ROUTERBASE_API_KEY,
baseURL: "https://routerbase.com/v1",
});
const response = await client.chat.completions.create({
model: "google/gemini-2.5-flash",
messages: [{ role: "user", content: "Write one sentence about model routing." }],
});
console.log(response.choices[0].message.content);
```
### Step 3: Validate Model IDs and Capabilities
When credentials and network access are available, check the live catalog before locking in a model ID or price-sensitive recommendation.
```bash
curl "https://routerbase.com/api/v1/models?task=chat" \
-H "Authorization: Bearer $ROUTERBASE_API_KEY"
```
Confirm feature assumptions with a small request fixture:
- Streaming works when `stream: true` is set.
- Tool calling accepts the exact schema used by the app.
- JSON mode returns parseable output and still passes application validation.
- Vision or media payloads use the expected OpenAI-compatible content shape.
### Step 4: Design Fallbacks Conservatively
Use explicit application-level fallbacks unless the user's RouterBase account already has a smart-routing policy configured.
```js
const modelPlan = [
"anthropic/claude-sonnet-4-6",
"google/gemini-2.5-flash",
];
for (const model of modelPlan) {
try {
return await client.chat.completions.create({ model, messages });
} catch (error) {
if (!isRetryableRouterBaseError(error)) throw error;
}
}
```
Treat transient network errors, timeouts, rate limits, and server errors as candidates for retry. Do not blindly retry authentication failures, invalid model IDs, validation errors, or policy refusals.
## Examples
### Migration Checklist
When converting an existing OpenAI SDK integration:
1. Change the base URL to `https://routerbase.com/v1`.
2. Read `ROUTERBASE_API_KEY` from server-side environment configuration.
3. Replace the model name with a RouterBase model ID that matches the task.
4. Preserve standard OpenAI request fields unless RouterBase documentation says otherwise.
5. Run one minimal smoke test before shipping.
### Routing Plan Format
Use this table when recommending a model strategy:
| Use case | Primary model | Fallback model | Reason | Validation |
| --- | --- | --- | --- | --- |
| Support chat | Provider/model ID | Provider/model ID | Low latency and acceptable quality | Streaming smoke test |
| Deep analysis | Provider/model ID | Provider/model ID | Strong reasoning, higher cost acceptable | Eval prompt plus human review |
## Best Practices
- Do keep RouterBase keys in server-side environment variables or secret managers.
- Do verify current model availability and pricing before production decisions.
- Do document primary and fallback model assumptions in the code or runbook.
- Do validate structured outputs with application schemas.
- Do not paste, log, commit, or screenshot real API keys.
- Do not hard-code model pricing or provider availability as permanent facts.
- Do not expose RouterBase keys in client-side JavaScript, mobile apps, or public repos.
## Limitations
- This skill does not replace RouterBase account configuration, live model catalog checks, or production observability.
- Some model features are provider-specific and must be tested with the exact selected model.
- High-stakes outputs still require human review and domain-specific evaluation.
## Security & Safety Notes
- Treat RouterBase credentials as production secrets.
- Mask tokens in logs and support tickets.
- Ask for explicit user approval before running live API calls that consume credits.
- Use placeholders such as environment variables in examples; never invent or include realistic secret strings.
## Common Pitfalls
- **Problem:** The code works with one provider but fails after switching models.
**Solution:** Re-test tool calling, JSON mode, streaming, and multimodal payloads for each selected model.
- **Problem:** Fallback logic retries non-retryable errors.
**Solution:** Retry only transient failures and fail fast on authentication, validation, and invalid model errors.
- **Problem:** A model recommendation becomes stale.
**Solution:** Re-check the RouterBase catalog and pricing page before finalizing the plan.
## Related Skills
- `@api-analyzer` - Use when the task is only to validate one API request shape.
- `@langfuse` - Use when the task needs production LLM observability, tracing, and evaluation.
antigravity-awesome-skills/plugins/antigravity-awesome-skills-claude/skills/tree-ring-memory/SKILL.md
+218
View File
@@ -0,0 +1,218 @@
---
name: tree-ring-memory
description: "Use Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation without transcript dumping."
category: development
risk: safe
source: community
source_repo: TerminallyLazy/Tree-Ring-Memory
source_type: community
date_added: "2026-07-08"
author: TerminallyLazy
tags: [agent-memory, local-first, recall, privacy, codex, sqlite, cli]
tools: [claude, codex, cursor, gemini, antigravity, opencode]
license: "Apache-2.0"
license_source: "https://github.com/TerminallyLazy/Tree-Ring-Memory/blob/main/LICENSE"
---
# Tree Ring Memory
## Overview
Tree Ring Memory is a framework-agnostic, local-first memory lifecycle layer for
AI agents. Use this skill when an agent should recall, preserve, audit, or
forget durable project memory without treating raw conversation transcripts as
memory.
The public runtime is a Rust CLI/TUI with local SQLite/FTS storage, scoped
recall, evidence records, audit, deterministic consolidation, maintenance,
DOX/Revolve source adapters, framework discovery, redaction, and explicit
forgetting.
## When to Use This Skill
- Use before resuming a project where prior decisions, warnings, preferences,
or failed approaches may matter.
- Use before changing architecture, storage, security, privacy, release, or
agent-memory behavior.
- Use when the user asks to remember, recall, audit, redact, forget, or
consolidate agent memory.
- Use after tests, reviews, incidents, or production behavior validate a lesson
future agents should preserve.
- Use when a project contains `.tree-ring/SKILL.md`, `.tree-ring/CLI.md`, or
other Tree Ring bridge files.
## How It Works
### Step 1: Discover Local Guidance
Check whether the current project already has Tree Ring guidance:
```bash
test -f .tree-ring/SKILL.md && sed -n '1,220p' .tree-ring/SKILL.md
test -f .tree-ring/CLI.md && sed -n '1,220p' .tree-ring/CLI.md
```
Treat project-local `.tree-ring` files as more authoritative than generic
examples in this skill. If the CLI is installed, inspect the current command
surface before assuming flags:
```bash
tree-ring --help
tree-ring recall --help
tree-ring remember --help
tree-ring evidence --help
tree-ring audit --help
tree-ring forget --help
```
If Tree Ring is not installed, do not run remote installer commands
automatically. Point the user to the project repository or install docs and ask
whether they want installation help.
## Step 2: Recall Before Risky Work
Use narrow, project-scoped recall first:
```bash
tree-ring recall "release behavior" --scope project
tree-ring recall "sqlite migration" --scope project
tree-ring recall "user preference" --scope global
```
Use recalled memory as context, not authority. Verify it against current source
files, tests, docs, issues, pull requests, logs, and runtime state before making
changes.
## Step 3: Write Only Durable Memory
Write concise memory only when it is likely to help future agents:
```bash
tree-ring remember "Run project-scoped recall before release changes." --event-type lesson --scope project
```
Prefer specific event types when supported locally:
- `decision`
- `lesson`
- `warning`
- `correction`
- `user_preference`
- `tool_result`
- `summary`
- `hypothesis`
Store the durable lesson, decision, warning, or follow-up. Do not store the
full conversation.
## Step 4: Record Evidence for Evaluated Outcomes
Use evidence records for test runs, incidents, reviewed changes, or other
evaluated outcomes:
```bash
tree-ring evidence \
--outcome observed \
--summary "Installer smoke test passed in an isolated HOME." \
--evidence-ref "ci/install-smoke/2026-07-08"
```
Outcome guidance:
- `promoted`: durable truth backed by strong evidence
- `rejected`: failed or rolled-back approach worth keeping visible
- `deferred`: unresolved idea or future option
- `observed`: normal evaluated result
Do not promote weak, stale, or unreviewed claims to durable truth.
## Step 5: Use Source Adapters Carefully
When a repo has structured source records, run dry runs first:
```bash
tree-ring dox sync --source-root . --dry-run
tree-ring revolve sync --source-root revolve --dry-run
tree-ring integrations scan --source-root .
```
Only write adapter summaries when they are concise, source-linked, useful, and
privacy-safe. Imported memory does not replace the underlying `AGENTS.md`,
Revolve record, test, pull request, issue, or documentation.
## Ring Selection
Use the smallest durable ring that fits:
- `cambium`: active or recent task context
- `outer`: recent decisions and task lessons
- `inner`: older compressed project knowledge
- `heartwood`: durable high-confidence truths
- `scar`: failures, regressions, rejected approaches, warnings
- `seed`: unresolved ideas, hypotheses, follow-ups
Prefer `outer` or `seed` unless the user confirms durability or the evidence is
strong.
## Best Practices
- Recall before risky or repeat work.
- Keep project memory project-scoped unless it is a durable cross-project user
preference.
- Attach source references such as file paths, issue ids, PR ids, evaluation
runs, or docs paths.
- Re-check current source files and runtime state before acting on recalled
memory.
- Ask at closeout what future agents should remember, avoid, or revisit.
- Use redaction, deletion, or supersession when memory is wrong, stale,
sensitive, or replaced by a newer decision.
## Security & Safety Notes
- Never use Tree Ring Memory as a hidden recorder.
- Do not store secrets, credentials, tokens, private keys, recovery codes, raw
chain-of-thought, or temporary scratchpad content.
- Do not store sensitive personal data unless the user explicitly asks and the
retention boundary is safe.
- Do not store copyrighted source text beyond short allowed excerpts.
- Do not run installer, network, destructive, or mutation commands without
explicit user approval and a clear target environment.
- Treat all examples as commands to adapt after checking local `--help`, not as
guaranteed command surfaces.
## Limitations
- Tree Ring Memory is not a replacement for source control, issue trackers,
documentation, tests, logs, or live runtime verification.
- Recalled memory can be stale or wrong. Always verify important claims against
the current project before using them to make changes.
- The CLI surface can change across releases. Prefer local `.tree-ring`
guidance and `tree-ring --help` over copied command examples.
- It should not be used for secret storage, comprehensive transcript archives,
compliance retention, or unreviewed collection of sensitive personal data.
- Cross-agent interoperability depends on each tool's ability to call the local
CLI or read project-local guidance files.
## Common Pitfalls
- **Problem:** Recalled memory conflicts with current source.
**Solution:** Treat source files, tests, docs, and runtime evidence as
authoritative; supersede or forget stale memory.
- **Problem:** Memory starts becoming transcript storage.
**Solution:** Store only durable decisions, warnings, preferences, outcomes,
and follow-ups.
- **Problem:** A lesson is useful but contains sensitive detail.
**Solution:** Store a redacted summary or do not store it.
## Related Skills
- `@agent-memory-systems` - Use for broad agent-memory architecture choices.
- `@agent-memory` - Use for the listed hybrid memory MCP system.
- `@planning-with-files` - Use when simple persistent files are enough.
## Additional Resources
- Tree Ring Memory repository: <https://github.com/TerminallyLazy/Tree-Ring-Memory>
- Codex plugin wrapper: <https://github.com/TerminallyLazy/tree-ring-memory-codex-plugin>
antigravity-awesome-skills/plugins/antigravity-awesome-skills/.codex-plugin/plugin.json
+2 -2
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-awesome-skills",
"version": "13.12.0",
"version": "13.13.0",
"description": "Plugin-safe Codex plugin for the Antigravity Awesome Skills library.",
"author": {
"name": "sickn33 and contributors",
@@ -19,7 +19,7 @@
"skills": "./skills/",
"interface": {
"displayName": "Antigravity Awesome Skills",
"shortDescription": "1,857 plugin-safe skills for coding, security, product, and ops workflows.",
"shortDescription": "1,863 plugin-safe skills for coding, security, product, and ops workflows.",
"longDescription": "Install a plugin-safe Codex distribution of Antigravity Awesome Skills. Skills that still need hardening or target-specific setup remain available in the repo but are excluded from this plugin.",
"developerName": "sickn33 and contributors",
"category": "Productivity",
antigravity-awesome-skills/plugins/antigravity-awesome-skills/skills/codex-profiles/SKILL.md
+170
View File
@@ -0,0 +1,170 @@
---
name: codex-profiles
description: "Use codex-profiles to run Codex CLI or Codex Desktop with isolated CODEX_HOME profiles for separate accounts, projects, and local state."
category: productivity
risk: critical
source: community
source_repo: Ducksss/codex-profiles
source_type: community
date_added: "2026-07-08"
author: Ducksss
tags: [codex, codex-cli, profiles, code-home, account-isolation, desktop]
tools: [codex]
license: "MIT"
license_source: "https://github.com/Ducksss/codex-profiles/blob/main/LICENSE"
---
# Codex Profiles
## Overview
Use `codex-profiles` when a user wants separate Codex CLI or Codex Desktop contexts for work, personal, school, client, or project-specific activity. The tool wraps Codex's `CODEX_HOME` support so each profile has its own Codex home directory for auth, config, sessions, connectors, plugins, caches, logs, and local state.
This skill is for profile selection and operational safety around that boundary. It is not an official OpenAI project, and it does not provide full OS-level isolation.
## When to Use This Skill
- Use when the user wants to keep multiple Codex accounts or project contexts separate on one machine.
- Use when a workflow needs a different `CODEX_HOME` without manually exporting environment variables.
- Use when diagnosing which Codex profile is active or whether profiles are logged in.
- Use when the user asks about Codex account switching without copying `auth.json`.
- Use when launching Codex Desktop from a profile, only after confirming the user accepts app/process disruption.
## How It Works
### Step 1: Confirm Scope and Installation
First check whether the user wants CLI-only profile switching or Codex Desktop profile launching. Desktop operations can quit, launch, clone, or rebuild app instances, so get explicit approval before running them.
If the tool is already installed, inspect the live command surface:
```bash
codex-profile --help
codex-profile doctor
codex-profile list
codex-profile status
```
If it is not installed, prefer package-manager installs the user can inspect and control:
```bash
npm install -g codex-profile
brew install Ducksss/tap/codex-profile
```
Do not run remote install scripts automatically. If the user asks for a source install, clone the repository and inspect its install instructions first.
### Step 2: Create or Select a Profile
Create a new isolated Codex home only when the user names the intended profile:
```bash
codex-profile init work
codex-profile path work
```
Ask the user to log in once per profile when needed:
```bash
codex-profile login work
```
Do not copy, parse, print, or migrate `auth.json` tokens between profiles.
### Step 3: Run Codex CLI With a Profile
Use the CLI profile wrapper for ordinary agent work:
```bash
codex-profile cli work
codex-profile cli work exec "run tests and summarize failures"
```
For one-off shell sessions, prefer the tool's environment or shell activation commands after checking `--help`:
```bash
codex-profile env work
codex-profile shell-init --help
```
### Step 4: Use Desktop Profile Commands Carefully
Codex Desktop launch flows can affect running app state. Before running them, state which profile, app mode, and workspace will be used, then wait for approval.
```bash
codex-profile app work ~/Dev/project
codex-profile app work --instance ~/Dev/project
```
Use `--instance` only when the user wants side-by-side Desktop profiles and accepts the additional local app clone and separate Electron user-data boundary.
## Examples
### Example 1: Read-Only Profile Audit
```bash
codex-profile list
codex-profile status
codex-profile doctor
```
Use this before changing profile state. It should not expose token contents.
### Example 2: CLI Task in a Work Profile
```bash
codex-profile cli work exec "inspect this repository and run its test suite"
```
Confirm the profile name is intentional before running long tasks.
### Example 3: Manual CODEX_HOME Equivalent
If the wrapper is unavailable, explain the underlying boundary instead of improvising token movement:
```bash
CODEX_HOME="$HOME/.codex-work" codex
CODEX_HOME="$HOME/.codex-work" codex exec "review this change"
```
## Best Practices
- Keep profile names explicit and boring, such as `work`, `personal`, `client-a`, or `school`.
- Use `status`, `list`, and `doctor` before destructive or Desktop actions.
- Treat each profile as a separate local Codex home, not as a full sandbox.
- Keep secrets inside the account/profile that owns them; do not copy auth files between profiles.
- Prefer CLI profile commands for routine work and reserve Desktop app commands for user-approved context switches.
- Verify behavior against the installed `codex-profile --help`, because command flags can change.
## Limitations
- `codex-profiles` is community-maintained and is not an official OpenAI tool.
- It isolates Codex state through separate `CODEX_HOME` directories; it does not isolate the operating-system user, shell history, SSH keys, browser cookies, GitHub CLI auth, or unrelated application state.
- Desktop profile launch behavior is macOS-focused and can change with Codex Desktop releases.
- Existing Codex sessions may still contain project context from before a profile strategy was adopted.
- The tool does not replace backups for important Codex state.
## Security & Safety Notes
- Never copy, print, parse, or migrate `auth.json` tokens as a shortcut.
- Do not run Desktop launch, app clone, rebuild, remove, or profile deletion commands without explicit user approval.
- Use `codex-profile remove` only after confirming the exact profile path and whether the user needs a backup.
- Do not assume profile isolation protects credentials outside `CODEX_HOME`.
- Avoid remote install scripts in automated agent runs; prefer inspectable package-manager or source-install steps.
## Common Pitfalls
- **Problem:** A user expects profile switching to isolate GitHub CLI, SSH, or browser state.
**Solution:** Explain that `codex-profiles` isolates Codex home state only; check and switch other tools separately.
- **Problem:** A Desktop command disrupts an active session.
**Solution:** Ask before Desktop operations and prefer CLI commands when the user only needs isolated command-line work.
- **Problem:** A profile exists but is logged out or missing connectors.
**Solution:** Run `codex-profile status` and have the user log in or configure connectors inside that profile.
## Related Skills
- `@environment-setup-guide` - Use when installing or documenting local development tools.
- `@codex-maintenance` - Use when maintaining local Codex Desktop, MCP, plugin, or cache surfaces.
- `@filesystem-context` - Use when reasoning about local files, config paths, and workspace boundaries.
antigravity-awesome-skills/plugins/antigravity-awesome-skills/skills/go-in-depth/SKILL.md
+59
View File
@@ -0,0 +1,59 @@
---
name: go-in-depth
description: Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.
risk: safe
source: self
source_type: self
date_added: "2026-07-07"
---
# Go In Depth
## Overview
Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. Run the "go-in-depth" workflow.
## When to Use
When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., "what car to buy" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.
## How It Works
Phases:
- Scope: Decompose question (from args) into 5 search angles
- Search: 5 parallel WebSearch agents, one per angle
- Fetch: URL-dedup, fetch top 15 sources, extract falsifiable claims
- Verify: 3-vote adversarial verification per claim (need 2/3 refutes to kill)
- Synthesize: Merge semantic dupes, rank by confidence, cite sources
## Examples
### Example 1: Run go-in-depth workflow
```
Workflow({ name: "go-in-depth" })
```
### Example 2: Research with refined question
```
Workflow({ name: "go-in-depth", args: { query: "best hybrid cars under $30k in the US for families" } })
```
### Example 3: Deep dive into a technical concept
```
Workflow({ name: "go-in-depth", args: { query: "how does the transformer architecture handle positional encoding?" } })
```
### Example 4: Fact-checking a medical claim
```
Workflow({ name: "go-in-depth", args: { query: "efficacy of intermittent fasting for long-term weight loss in adults" } })
```
## Workflow Script
[scripts/workflow-script.js](scripts/workflow-script.js)
## Limitations
- **Slow execution**: Multi-agent searches, fetching, and 3-vote verification take significant time. Not for quick facts.
- **Context intensive**: Analyzing 15 full sources uses large context limits.
- **Synthesis risks**: May struggle if source material is weak or equally conflicting.
antigravity-awesome-skills/plugins/antigravity-awesome-skills/skills/go-in-depth/scripts/workflow-script.js
+350
View File
@@ -0,0 +1,350 @@
export const meta = {
name: 'go-in-depth',
description: 'Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.',
whenToUse: 'When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., "what car to buy" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.',
phases: [{"title":"Scope","detail":"Decompose question (from args) into 5 search angles"},{"title":"Search","detail":"5 parallel WebSearch agents, one per angle"},{"title":"Fetch","detail":"URL-dedup, fetch top 15 sources, extract falsifiable claims"},{"title":"Verify","detail":"3-vote adversarial verification per claim (need 2/3 refutes to kill)"},{"title":"Synthesize","detail":"Merge semantic dupes, rank by confidence, cite sources"}],
}
// go-in-depth: Scope → pipeline(Search → URL-dedup → Fetch+Extract) → 3-vote Verify → Synthesize
// Uses a bug-hunting-style fan-out and verification pattern, adapted for web research.
// Question is passed via Workflow({name: 'go-in-depth', args: '<question>'}).
const VOTES_PER_CLAIM = 3
const REFUTATIONS_REQUIRED = 2
const MAX_FETCH = 15
const MAX_VERIFY_CLAIMS = 25
// ─── Schemas ───
const SCOPE_SCHEMA = {
type: "object", required: ["question", "angles", "summary"],
properties: {
question: { type: "string" },
summary: { type: "string" },
angles: { type: "array", minItems: 3, maxItems: 6, items: {
type: "object", required: ["label", "query"],
properties: {
label: { type: "string" },
query: { type: "string" },
rationale: { type: "string" },
},
}},
},
}
const SEARCH_SCHEMA = {
type: "object", required: ["results"],
properties: {
results: { type: "array", maxItems: 6, items: {
type: "object", required: ["url", "title", "relevance"],
properties: {
url: { type: "string" },
title: { type: "string" },
snippet: { type: "string" },
relevance: { enum: ["high", "medium", "low"] },
},
}},
},
}
const EXTRACT_SCHEMA = {
type: "object", required: ["claims", "sourceQuality"],
properties: {
sourceQuality: { enum: ["primary", "secondary", "blog", "forum", "unreliable"] },
publishDate: { type: "string" },
claims: { type: "array", maxItems: 5, items: {
type: "object", required: ["claim", "quote", "importance"],
properties: {
claim: { type: "string" },
quote: { type: "string" },
importance: { enum: ["central", "supporting", "tangential"] },
},
}},
},
}
const VERDICT_SCHEMA = {
type: "object", required: ["refuted", "evidence", "confidence"],
properties: {
refuted: { type: "boolean" },
evidence: { type: "string" },
confidence: { enum: ["high", "medium", "low"] },
counterSource: { type: "string" },
},
}
const REPORT_SCHEMA = {
type: "object", required: ["summary", "findings", "caveats"],
properties: {
summary: { type: "string" },
findings: { type: "array", items: {
type: "object", required: ["claim", "confidence", "sources", "evidence"],
properties: {
claim: { type: "string" },
confidence: { enum: ["high", "medium", "low"] },
sources: { type: "array", items: { type: "string" } },
evidence: { type: "string" },
vote: { type: "string" },
},
}},
caveats: { type: "string" },
openQuestions: { type: "array", items: { type: "string" } },
},
}
// ─── Phase 0: Scope — decompose question into search angles ───
phase("Scope")
const QUESTION = (typeof args === "string" ? args.trim() : args?.query?.trim()) || ""
if (!QUESTION) {
return { error: "No research question provided. Pass it as args: Workflow({name: 'go-in-depth', args: '<question>'})." }
}
const scope = await agent(
"Decompose this research question into complementary search angles.\n\n" +
"## Question\n" + QUESTION + "\n\n" +
"## Task\n" +
"Generate 5 distinct web search queries that together cover the question from different angles. Pick angles that suit the question's domain. Examples:\n" +
"- broad/primary · academic/technical · recent news · contrarian/skeptical · practitioner/implementation\n" +
"- For medical: anatomy · common causes · serious differentials · authoritative refs · red flags\n" +
"- For tech: state-of-art · benchmarks · limitations · industry adoption · cost/tradeoffs\n\n" +
"Make queries specific enough to surface high-signal results. Avoid redundancy.\n" +
"Return: the question (verbatim or lightly normalized), a 1-2 sentence decomposition strategy, and the angles.\n\nStructured output only.",
{ label: "scope", schema: SCOPE_SCHEMA }
)
if (!scope) {
return { error: "Scope agent returned no result — cannot decompose the research question." }
}
log("Q: " + QUESTION.slice(0, 80) + (QUESTION.length > 80 ? "…" : ""))
log("Decomposed into " + scope.angles.length + " angles: " + scope.angles.map(a => a.label).join(", "))
// ─── Dedup state — accumulates across searchers as they complete ───
const normURL = u => {
try {
const p = new URL(u)
return (p.hostname.replace(/^www\./, "") + p.pathname.replace(/\/$/, "")).toLowerCase()
} catch { return u.toLowerCase() }
}
const seen = new Map()
const dupes = []
const budgetDropped = []
const relRank = { high: 0, medium: 1, low: 2 }
let fetchSlots = MAX_FETCH
// ─── Prompts ───
const SEARCH_PROMPT = (angle) =>
"## Web Searcher: " + angle.label + "\n\n" +
"Research question: \"" + QUESTION + "\"\n\n" +
"Your angle: **" + angle.label + "** — " + (angle.rationale || "") + "\n" +
"Search query: `" + angle.query + "`\n\n" +
"## Task\nUse WebSearch with the query above (or a refined version). Return the top 4-6 most relevant results.\n" +
"Rank by relevance to the ORIGINAL question, not just the search query. Skip obvious SEO spam/content farms.\n" +
"Include a short snippet capturing why each result is relevant.\n\nStructured output only."
const FETCH_PROMPT = (source, angle) =>
"## Source Extractor\n\n" +
"Research question: \"" + QUESTION + "\"\n\n" +
"Fetch and extract key claims from this source:\n" +
"**URL:** " + source.url + "\n**Title:** " + source.title + "\n**Found via:** " + angle + " search\n\n" +
"## Task\n1. Use WebFetch to retrieve the page content.\n" +
"2. Assess source quality: primary research/institution? secondary reporting? blog/opinion? forum? unreliable?\n" +
"3. Extract 2-5 FALSIFIABLE claims that bear on the research question. Each claim must:\n" +
" - be a concrete, checkable statement (not vague generalities)\n" +
" - include a direct quote from the source as support\n" +
" - be rated central/supporting/tangential to the research question\n" +
"4. Note publish date if available.\n\n" +
"If the fetch fails or the page is irrelevant/paywalled, return claims: [] and sourceQuality: \"unreliable\".\n\nStructured output only."
const VERIFY_PROMPT = (claim, v) =>
"## Adversarial Claim Verifier (voter " + (v + 1) + "/" + VOTES_PER_CLAIM + ")\n\n" +
"Be SKEPTICAL. Try to REFUTE this claim. ≥" + REFUTATIONS_REQUIRED + "/" + VOTES_PER_CLAIM + " refutations kill it.\n\n" +
"## Research question\n" + QUESTION + "\n\n" +
"## Claim under review\n\"" + claim.claim + "\"\n\n" +
"**Source:** " + claim.sourceUrl + " (" + claim.sourceQuality + ")\n" +
"**Supporting quote:** \"" + claim.quote + "\"\n\n" +
"## Checklist\n" +
"1. Is the claim actually supported by the quote, or is it an overreach/misread?\n" +
"2. WebSearch for contradicting evidence — does any credible source dispute or heavily qualify this?\n" +
"3. Is the source quality sufficient for the claim's strength? (extraordinary claims need primary sources)\n" +
"4. Is the claim outdated? (check dates — old claims about fast-moving fields are suspect)\n" +
"5. Is this a marketing claim / press release / cherry-picked benchmark / forum speculation?\n\n" +
"**refuted=true** if: unsupported by quote / contradicted / low-quality source for strong claim / outdated / marketing fluff.\n" +
"**refuted=false** ONLY if: claim is well-supported, current, and source quality matches claim strength.\n" +
"Default to refuted=true if uncertain.\n\nStructured output only. Evidence MUST be specific."
// ─── Pipeline: search → dedup → fetch+extract (no barrier) ───
const searchResults = await pipeline(
scope.angles,
angle => agent(SEARCH_PROMPT(angle), {
label: "search:" + angle.label, phase: "Search", schema: SEARCH_SCHEMA
}).then(r => {
if (!r) return null
log(angle.label + ": " + r.results.length + " results")
return { angle: angle.label, results: r.results }
}),
searchResult => {
const sorted = [...searchResult.results].sort((a, b) => relRank[a.relevance] - relRank[b.relevance])
const novel = sorted.filter(r => {
const key = normURL(r.url)
if (seen.has(key)) {
dupes.push({ ...r, angle: searchResult.angle, dupOf: seen.get(key) })
return false
}
if (fetchSlots <= 0) {
budgetDropped.push({ ...r, angle: searchResult.angle })
return false
}
seen.set(key, { angle: searchResult.angle, title: r.title })
fetchSlots--
return true
})
if (novel.length < searchResult.results.length) {
log(searchResult.angle + ": " + novel.length + " novel (" + (searchResult.results.length - novel.length) + " filtered)")
}
return parallel(
novel.map(source => () => {
let host = "unknown"
try { host = new URL(source.url).hostname.replace(/^www\./, "") } catch {}
return agent(FETCH_PROMPT(source, searchResult.angle), {
label: "fetch:" + host,
phase: "Fetch",
schema: EXTRACT_SCHEMA,
}).then(ext => {
// User-skip → null; drop it (filtered by searchResults.flat().filter(Boolean))
// rather than throwing into .catch() and mislabeling it "unreliable".
if (!ext) return null
return {
url: source.url, title: source.title, angle: searchResult.angle,
sourceQuality: ext.sourceQuality, publishDate: ext.publishDate,
claims: ext.claims.map(c => ({ ...c, sourceUrl: source.url, sourceQuality: ext.sourceQuality })),
}
}).catch(e => {
log("fetch failed: " + source.url + " — " + (e.message || e))
return { url: source.url, title: source.title, angle: searchResult.angle, sourceQuality: "unreliable", claims: [] }
})
})
)
}
)
const allSources = searchResults.flat().filter(Boolean)
const allClaims = allSources.flatMap(s => s.claims)
const impRank = { central: 0, supporting: 1, tangential: 2 }
const qualRank = { primary: 0, secondary: 1, blog: 2, forum: 3, unreliable: 4 }
const rankedClaims = [...allClaims]
.sort((a, b) => (impRank[a.importance] - impRank[b.importance]) || (qualRank[a.sourceQuality] - qualRank[b.sourceQuality]))
.slice(0, MAX_VERIFY_CLAIMS)
log("Fetched " + allSources.length + " sources → " + allClaims.length + " claims → verifying top " + rankedClaims.length)
if (rankedClaims.length === 0) {
return {
question: QUESTION,
summary: "No claims extracted. " + allSources.length + " sources fetched, all empty/failed. " + dupes.length + " URL dupes, " + budgetDropped.length + " budget-dropped.",
findings: [], refuted: [], sources: allSources.map(s => ({ url: s.url, quality: s.sourceQuality })),
stats: { angles: scope.angles.length, sources: allSources.length, claims: 0, dupes: dupes.length },
}
}
// ─── Verify: 3-vote adversarial ───
// Barrier here is intentional — claim pool must be fully assembled before ranking/verification.
phase("Verify")
const voted = (await parallel(
rankedClaims.map(claim => () =>
parallel(
Array.from({ length: VOTES_PER_CLAIM }, (_, v) => () =>
agent(VERIFY_PROMPT(claim, v), {
label: "v" + v + ":" + claim.claim.slice(0, 40),
phase: "Verify",
schema: VERDICT_SCHEMA,
})
)
).then(verdicts => {
// A vote can be null (user-skip or agent error) — treat as abstain.
const valid = verdicts.filter(Boolean)
const refuted = valid.filter(v => v.refuted).length
// Survive only if the claim was actually adjudicated: a quorum of
// valid votes AND fewer than REFUTATIONS_REQUIRED refuting. Too many
// abstentions = unverified, which must NOT pass into the report
// (otherwise all-abstain → refuted=0 → false survive).
const abstained = VOTES_PER_CLAIM - valid.length
const survives = valid.length >= REFUTATIONS_REQUIRED && refuted < REFUTATIONS_REQUIRED
log("\"" + claim.claim.slice(0, 50) + "…\": " + (valid.length - refuted) + "-" + refuted + (abstained > 0 ? " (" + abstained + " abstain)" : "") + " " + (survives ? "✓" : "✗"))
return { ...claim, verdicts: valid, refutedVotes: refuted, survives }
})
)
)).filter(Boolean)
const confirmed = voted.filter(c => c.survives)
const killed = voted.filter(c => !c.survives)
log("Verify done: " + voted.length + " claims → " + confirmed.length + " confirmed, " + killed.length + " killed")
if (confirmed.length === 0) {
return {
question: QUESTION,
summary: "All " + voted.length + " claims refuted by adversarial verification. Research inconclusive — sources may be low-quality or claims overstated.",
findings: [],
refuted: killed.map(c => ({ claim: c.claim, vote: (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes, source: c.sourceUrl })),
sources: allSources.map(s => ({ url: s.url, quality: s.sourceQuality, claimCount: s.claims.length })),
stats: { angles: scope.angles.length, sources: allSources.length, claims: allClaims.length, verified: voted.length, confirmed: 0, killed: killed.length },
}
}
// ─── Synthesize ───
phase("Synthesize")
const confRank = { high: 0, medium: 1, low: 2 }
const block = confirmed.map((c, i) => {
const best = c.verdicts.filter(v => !v.refuted).sort((a, b) => confRank[a.confidence] - confRank[b.confidence])[0]
return "### [" + i + "] " + c.claim + "\n" +
"Vote: " + (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes + " · Source: " + c.sourceUrl + " (" + c.sourceQuality + ")\n" +
"Quote: \"" + c.quote + "\"\nVerifier evidence (" + best.confidence + "): " + best.evidence + "\n"
}).join("\n")
const killedBlock = killed.length > 0
? "\n## Refuted claims (for transparency)\n" +
killed.map(c => "- \"" + c.claim + "\" (" + c.sourceUrl + ", vote " + (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes + ")").join("\n")
: ""
const report = await agent(
"## Synthesis: research report\n\n" +
"**Question:** " + QUESTION + "\n\n" +
confirmed.length + " claims survived " + VOTES_PER_CLAIM + "-vote adversarial verification. Merge semantic duplicates and synthesize.\n\n" +
"## Confirmed claims\n" + block + "\n" + killedBlock + "\n\n" +
"## Instructions\n" +
"1. Identify claims that say the same thing — merge them, combine their sources.\n" +
"2. Group related claims into coherent findings. Each finding should directly address the research question.\n" +
"3. Assign confidence per finding: high (multiple primary sources, unanimous votes), medium (secondary sources or split votes), low (single source or blog-quality).\n" +
"4. Write a 3-5 sentence executive summary answering the research question.\n" +
"5. Note caveats: what's uncertain, what sources were weak, what time-sensitivity applies.\n" +
"6. List 2-4 open questions that emerged but weren't answered.\n\nStructured output only.",
{ label: "synthesize", schema: REPORT_SCHEMA }
)
if (!report) {
// Synthesis skipped/errored — salvage the verified claims raw rather
// than throwing on report.findings and discarding the whole run.
return {
question: QUESTION,
summary: "Synthesis step was skipped or failed — returning " + confirmed.length + " verified claims unmerged.",
findings: [],
confirmed: confirmed.map(c => ({ claim: c.claim, source: c.sourceUrl, quote: c.quote, vote: (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes })),
refuted: killed.map(c => ({ claim: c.claim, vote: (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes, source: c.sourceUrl })),
sources: allSources.map(s => ({ url: s.url, quality: s.sourceQuality, claimCount: s.claims.length })),
stats: { angles: scope.angles.length, sources: allSources.length, claims: allClaims.length, verified: voted.length, confirmed: confirmed.length, killed: killed.length, afterSynthesis: 0 },
}
}
return {
question: QUESTION,
...report,
refuted: killed.map(c => ({ claim: c.claim, vote: (c.verdicts.length - c.refutedVotes) + "-" + c.refutedVotes, source: c.sourceUrl })),
sources: allSources.map(s => ({ url: s.url, quality: s.sourceQuality, angle: s.angle, claimCount: s.claims.length })),
stats: {
angles: scope.angles.length,
sourcesFetched: allSources.length,
claimsExtracted: allClaims.length,
claimsVerified: voted.length,
confirmed: confirmed.length,
killed: killed.length,
afterSynthesis: report.findings.length,
urlDupes: dupes.length,
budgetDropped: budgetDropped.length,
agentCalls: 1 + scope.angles.length + allSources.length + (voted.length * VOTES_PER_CLAIM) + 1,
},
}
antigravity-awesome-skills/plugins/antigravity-awesome-skills/skills/pilot-protocol/SKILL.md
+145
View File
@@ -0,0 +1,145 @@
---
name: pilot-protocol
description: "Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol"
category: ai-agents
risk: critical
source: community
source_repo: pilot-protocol/pilotprotocol
source_type: official
date_added: "2026-07-07"
author: pilot-protocol
tags: [agent-networking, p2p, nat-traversal, overlay-network, agent-apps]
tools: [claude, cursor, gemini, codex]
license: "AGPL-3.0"
license_source: "https://github.com/pilot-protocol/pilotprotocol/blob/main/LICENSE"
---
# Pilot Protocol
## Overview
Pilot Protocol is an open-source overlay network that gives AI agents first-class
network citizenship: a permanent virtual address, encrypted UDP tunnels, NAT
traversal, and an explicit per-peer trust model. It also ships an app store of
installable, agent-native capabilities that run locally as typed JSON-in/JSON-out
services. Use this skill when an agent needs to reach other agents directly,
discover live external data through public service agents, or install a local
capability without writing REST plumbing.
If this skill adapts material from an external GitHub repository, it declares:
- `source_repo: pilot-protocol/pilotprotocol`
- `source_type: official`
## When to Use This Skill
- Use when an agent needs a stable address that survives restarts, IP changes,
or moving across clouds (no more re-registering webhooks).
- Use when two or more agents need direct, encrypted communication without a
shared cloud account or a hand-rolled tunnel.
- Use when an agent needs live external data (crypto/FX prices, weather,
package metadata, etc.) via structured JSON instead of scraping HTML.
- Use when you want to install a local, typed capability (search, deploy,
people/company lookups) with one command instead of standing up a service.
## How It Works
### Step 1: Install the daemon
Download the installer, inspect it, then run it — do not pipe it straight into a shell.
```bash
curl -fsSL https://pilotprotocol.network/install.sh -o /tmp/pilot-install.sh
less /tmp/pilot-install.sh # review before executing
sh /tmp/pilot-install.sh
```
### Step 2: Start the node and confirm it registered
```bash
pilotctl daemon start
pilotctl info
```
### Step 3: Query a service agent (no handshake needed)
Service agents in the public directory auto-approve incoming messages.
```bash
pilotctl send-message list-agents --data '/data {"search":"weather"}' --wait
jq -r '.data' "$(ls -1t ~/.pilot/inbox/*.json | head -1)"
```
### Step 4: Handshake a peer agent for direct messaging
Peer nodes (as opposed to service agents) require mutual approval before a
tunnel works.
```bash
pilotctl handshake <hostname|node_id|address> "<reason>"
pilotctl trust
pilotctl send-message <peer> --data '<message>'
```
### Step 5: Install and call an agent app
```bash
pilotctl appstore catalogue
pilotctl appstore install <app-id>
pilotctl appstore call <app-id> <app>.help '{}'
```
## Examples
### Example 1: Ask a live-data service agent
```bash
pilotctl send-message list-agents --data '/data {"search":"bitcoin"}' --wait
jq -r '.data' "$(ls -1t ~/.pilot/inbox/*.json | head -1)"
```
### Example 2: Install and call a local capability app
```bash
pilotctl appstore install io.pilot.cosift
pilotctl appstore call io.pilot.cosift cosift.answer '{"q":"What is HNSW?"}'
```
## Best Practices
- ✅ Use `--wait` on `send-message` so the reply is guaranteed to be in the
inbox before you read it.
- ✅ Query `list-agents` before guessing a hostname — the catalogue changes.
- ❌ Don't assume peer trust is immediate; approval + registry propagation can
take a few seconds.
- ❌ Don't set `--auto-answer` on your own node — it's a service-agent-only flag.
## Limitations
- This skill does not replace reading `pilotctl --help` or the project docs
for less common commands.
- Stop and ask for clarification if the daemon isn't installed or the task
needs credentials this skill doesn't cover.
## Security & Safety Notes
- The install script fetches an installer from `pilotprotocol.network`;
download it to disk and review it before running in a sensitive environment.
- `~/.pilot/identity.json` is a private keypair — never copy it between hosts.
- Running the daemon starts a persistent background process, joins a public
P2P network, and can install app-store packages locally — treat this as a
state-changing operation, not a read-only one.
## Common Pitfalls
- **Problem:** A `send-message` to a peer silently fails right after a handshake.
**Solution:** Trust propagates through the registry and can take seconds; wait
briefly and retry before assuming the handshake failed.
- **Problem:** Large replies arrive truncated in the inbox JSON.
**Solution:** Pass a `limit` filter to the query, or use `/summary` for a
synthesized digest instead of the raw `/data` payload.
## Related Skills
- `@network-101` - General networking background before diving into overlay
networks specifically.
antigravity-awesome-skills/plugins/antigravity-awesome-skills/skills/pre-ship-gate/SKILL.md
+129
View File
@@ -0,0 +1,129 @@
---
name: pre-ship-gate
description: "A ship gate that runs before any production deploy: checks the silent failure modes that make a deploy 'succeed' while prod stays broken, then verifies the live revision instead of trusting deploy output."
category: quality
risk: safe
source: community
source_repo: Sharrmavishal/operating-kit
source_type: community
date_added: "2026-07-07"
author: Sharrmavishal
tags: [deployment, quality-gate, verification, ci-cd, production]
tools: [claude, cursor, gemini]
license: MIT
license_source: "https://github.com/Sharrmavishal/operating-kit/blob/main/LICENSE"
---
# Pre-Ship Gate
## Overview
Most bad deploys do not fail loudly. The pipeline goes green, the CLI prints "deployed", and the old or broken version is still what users hit. This skill is the gate you run right before a production deploy and right after, so an agent stops trusting deploy output and starts confirming what is actually live. It exists because "the deploy command exited 0" and "the new version is serving traffic" are two different facts, and agents routinely confuse them.
## When to Use This Skill
- Use before running any command that pushes to a production or staging environment.
- Use when an agent is about to report "shipped", "deployed", or "live".
- Use when a deploy reported success but users still see the old behavior.
- Use when a release involves database migrations, feature flags, or a staged rollout.
## How It Works
The gate has three phases. Do not skip to phase 3.
### Phase 1: Pre-flight (before the deploy runs)
Walk the silent failure catalog. These are the modes that let a deploy "succeed" while production stays broken. For each one, confirm it or flag it. Do not assume.
- **Migrations**: Are schema migrations part of this release, and will they run against the target before the new code serves traffic? A deploy that ships code expecting a column that does not exist yet fails silently for users, not for the pipeline.
- **Feature flags**: Is the flag that gates this change actually enabled in the target environment, not just in dev? Shipped code behind an off flag looks like a no-op deploy.
- **Build cache / stale assets**: Could a cached build or CDN layer serve the previous bundle after deploy? Confirm the artifact hash or asset fingerprint changed.
- **Release pointer**: Does the deploy update the symlink, active revision, or traffic pointer, or does it only upload the new build? Uploading is not releasing.
- **Staged rollout / canary**: If traffic is staged, is it stuck at 0 percent or waiting on a manual promote? A canary that never promotes is not a deploy.
- **Env and secrets**: Are the env vars and secrets the new code needs present in the target, not just locally? Missing config surfaces as runtime errors, not deploy errors.
### Phase 2: Run the deploy
The human or the deploy tooling runs the actual command. This skill does not execute the production deploy itself. It gates it.
### Phase 3: Verify live (before saying "shipped")
Confirm the running system, not the deploy log.
- Fetch the live version or revision identifier from the running service and compare it to the one you intended to ship.
- Hit a health or status endpoint and confirm it returns the expected version, not just HTTP 200.
- Tail production logs for the first errors after cutover.
- Only after the live revision matches the intended revision may you report "shipped". If it does not match, report the mismatch, not success.
## Examples
### Example 1: Verifying the live revision instead of trusting the deploy log
```bash
# You intended to ship this commit
INTENDED="$(git rev-parse --short HEAD)"
# Ask the running service what it is actually serving
LIVE="$(curl -fsS https://your-service.example.com/health | jq -r '.revision')"
if [ "$INTENDED" = "$LIVE" ]; then
echo "Live revision $LIVE matches intended $INTENDED: verified shipped."
else
echo "MISMATCH: intended $INTENDED but live is $LIVE. Do not report shipped."
fi
```
### Example 2: Pre-flight verdict format an agent can emit
```markdown
PRE-SHIP GATE, verdict: HOLD
- Migrations: 1 pending (add_users_status_col): NOT yet applied to prod. BLOCK.
- Feature flags: new_checkout flag is OFF in prod. Enabling required post-deploy.
- Build assets: new bundle hash confirmed (a1b2c3 != previous 9f8e7d). OK.
- Release pointer: deploy updates active symlink. OK.
- Rollout: canary at 10%, manual promote required. NOTE.
- Env/secrets: STRIPE_KEY present in prod. OK.
Reason for HOLD: run migration add_users_status_col before cutover, or the
new code will 500 on /orders.
```
## Best Practices
- ✅ Treat "the command exited 0" and "the new version is live" as separate facts, and verify the second one.
- ✅ Emit an explicit verdict (SHIP / HOLD) with the failing item named, not a vague "looks good".
- ✅ Compare a live revision identifier against the intended one after every deploy.
- ✅ Name the specific silent failure mode you are worried about, so a human can override with context.
- ❌ Do not report "shipped" from deploy output alone.
- ❌ Do not skip the pre-flight because the pipeline is green.
- ❌ Do not treat a passing health check as proof the right version is live. Check the version field.
## Limitations
- This skill does not run the production deploy for you. It gates and verifies around it.
- It cannot know your environment's exact health or version endpoint. Wire in the real one before relying on the verification phase.
- The silent failure catalog is common cases, not exhaustive. Systems with unusual release mechanics need their own additions.
- It does not replace environment-specific testing, load testing, or expert review.
- Stop and ask for clarification if the target environment, the intended revision, or the verification endpoint is unknown.
## Common Pitfalls
- **Problem:** Health check returns 200 but users still see the old version.
**Solution:** The check is hitting a cached edge or the old pod. Verify the revision field in the response, not just the status code.
- **Problem:** Migration runs after the new code is already serving traffic.
**Solution:** Sequence migrations before cutover, or gate the code path behind a flag until the migration lands.
- **Problem:** Deploy "succeeds" but the canary is stuck at 0 percent.
**Solution:** Confirm the traffic pointer or promotion step, not just the upload step.
## Security & Safety Notes
- This skill is defensive and read-oriented. Its own commands are verification calls (fetching a version endpoint, tailing logs, comparing revisions). It does not itself mutate production.
- The example commands use `curl -fsS` against a status endpoint and are illustrative. Replace the placeholder host and version field with your own before use.
- The actual production deploy is performed by your existing tooling and is out of this skill's scope. Keep human confirmation on the deploy step.
- No credentials or tokens are embedded. Do not paste secrets into health-check URLs.
## Related Skills
- `@codebase-audit-pre-push`: clean and audit the code before it ever reaches a deploy.
- `@dos-verify-done-claims`: verify a "done" claim against git ground truth after the fact.
antigravity-awesome-skills/plugins/antigravity-awesome-skills/skills/routerbase-model-gateway/SKILL.md
+175
View File
@@ -0,0 +1,175 @@
---
name: routerbase-model-gateway
description: "Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests."
category: ai-ml
risk: safe
source: community
source_repo: zenlee123/routerbase-agent-skills
source_type: community
date_added: "2026-07-07"
author: zenlee123
tags: [routerbase, llm-routing, openai-compatible, model-gateway]
tools: [claude, cursor, gemini, codex, antigravity]
license: "MIT-0"
license_source: "https://github.com/zenlee123/routerbase-agent-skills/blob/main/LICENSE"
---
# RouterBase Model Gateway
## Overview
Use [routerbase](https://routerbase.com/) when an application needs one OpenAI-compatible API surface for model routing across GPT, Claude, Gemini, image, video, audio, and embedding workloads. This skill helps agents migrate existing OpenAI SDK calls, document model-selection tradeoffs, and produce safe implementation snippets without exposing credentials.
RouterBase model availability, pricing, and provider capabilities can change, so treat examples as starting points and verify current catalog data before production recommendations.
## When to Use This Skill
- Use when migrating an OpenAI-compatible client to RouterBase by changing the base URL and model ID.
- Use when selecting primary and fallback models for chat, reasoning, vision, media generation, audio, or embeddings.
- Use when debugging RouterBase request setup, headers, environment variables, streaming, tool calls, JSON mode, or multimodal payloads.
- Use when documenting an internal model-routing plan that balances cost, latency, quality, and provider redundancy.
## How It Works
### Step 1: Classify the Workload
Identify the modality and hard constraints before choosing a model:
- Modality: chat, vision, image, video, audio, embeddings, or mixed.
- Quality target: draft, production, high-stakes review, or automated background task.
- Runtime constraints: latency budget, context length, streaming, JSON mode, tool calling, and retry tolerance.
- Business constraints: price ceiling, provider preference, regional requirements, and fallback rules.
### Step 2: Configure the OpenAI-Compatible Client
Keep the RouterBase API key server-side in an environment variable such as `ROUTERBASE_API_KEY`. Do not put keys in browser, mobile, or public repository code.
```python
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ROUTERBASE_API_KEY"],
base_url="https://routerbase.com/v1",
)
response = client.chat.completions.create(
model="google/gemini-2.5-flash",
messages=[{"role": "user", "content": "Write one sentence about model routing."}],
)
print(response.choices[0].message.content)
```
```js
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.ROUTERBASE_API_KEY,
baseURL: "https://routerbase.com/v1",
});
const response = await client.chat.completions.create({
model: "google/gemini-2.5-flash",
messages: [{ role: "user", content: "Write one sentence about model routing." }],
});
console.log(response.choices[0].message.content);
```
### Step 3: Validate Model IDs and Capabilities
When credentials and network access are available, check the live catalog before locking in a model ID or price-sensitive recommendation.
```bash
curl "https://routerbase.com/api/v1/models?task=chat" \
-H "Authorization: Bearer $ROUTERBASE_API_KEY"
```
Confirm feature assumptions with a small request fixture:
- Streaming works when `stream: true` is set.
- Tool calling accepts the exact schema used by the app.
- JSON mode returns parseable output and still passes application validation.
- Vision or media payloads use the expected OpenAI-compatible content shape.
### Step 4: Design Fallbacks Conservatively
Use explicit application-level fallbacks unless the user's RouterBase account already has a smart-routing policy configured.
```js
const modelPlan = [
"anthropic/claude-sonnet-4-6",
"google/gemini-2.5-flash",
];
for (const model of modelPlan) {
try {
return await client.chat.completions.create({ model, messages });
} catch (error) {
if (!isRetryableRouterBaseError(error)) throw error;
}
}
```
Treat transient network errors, timeouts, rate limits, and server errors as candidates for retry. Do not blindly retry authentication failures, invalid model IDs, validation errors, or policy refusals.
## Examples
### Migration Checklist
When converting an existing OpenAI SDK integration:
1. Change the base URL to `https://routerbase.com/v1`.
2. Read `ROUTERBASE_API_KEY` from server-side environment configuration.
3. Replace the model name with a RouterBase model ID that matches the task.
4. Preserve standard OpenAI request fields unless RouterBase documentation says otherwise.
5. Run one minimal smoke test before shipping.
### Routing Plan Format
Use this table when recommending a model strategy:
| Use case | Primary model | Fallback model | Reason | Validation |
| --- | --- | --- | --- | --- |
| Support chat | Provider/model ID | Provider/model ID | Low latency and acceptable quality | Streaming smoke test |
| Deep analysis | Provider/model ID | Provider/model ID | Strong reasoning, higher cost acceptable | Eval prompt plus human review |
## Best Practices
- Do keep RouterBase keys in server-side environment variables or secret managers.
- Do verify current model availability and pricing before production decisions.
- Do document primary and fallback model assumptions in the code or runbook.
- Do validate structured outputs with application schemas.
- Do not paste, log, commit, or screenshot real API keys.
- Do not hard-code model pricing or provider availability as permanent facts.
- Do not expose RouterBase keys in client-side JavaScript, mobile apps, or public repos.
## Limitations
- This skill does not replace RouterBase account configuration, live model catalog checks, or production observability.
- Some model features are provider-specific and must be tested with the exact selected model.
- High-stakes outputs still require human review and domain-specific evaluation.
## Security & Safety Notes
- Treat RouterBase credentials as production secrets.
- Mask tokens in logs and support tickets.
- Ask for explicit user approval before running live API calls that consume credits.
- Use placeholders such as environment variables in examples; never invent or include realistic secret strings.
## Common Pitfalls
- **Problem:** The code works with one provider but fails after switching models.
**Solution:** Re-test tool calling, JSON mode, streaming, and multimodal payloads for each selected model.
- **Problem:** Fallback logic retries non-retryable errors.
**Solution:** Retry only transient failures and fail fast on authentication, validation, and invalid model errors.
- **Problem:** A model recommendation becomes stale.
**Solution:** Re-check the RouterBase catalog and pricing page before finalizing the plan.
## Related Skills
- `@api-analyzer` - Use when the task is only to validate one API request shape.
- `@langfuse` - Use when the task needs production LLM observability, tracing, and evaluation.
antigravity-awesome-skills/plugins/antigravity-awesome-skills/skills/tree-ring-memory/SKILL.md
+218
View File
@@ -0,0 +1,218 @@
---
name: tree-ring-memory
description: "Use Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation without transcript dumping."
category: development
risk: safe
source: community
source_repo: TerminallyLazy/Tree-Ring-Memory
source_type: community
date_added: "2026-07-08"
author: TerminallyLazy
tags: [agent-memory, local-first, recall, privacy, codex, sqlite, cli]
tools: [claude, codex, cursor, gemini, antigravity, opencode]
license: "Apache-2.0"
license_source: "https://github.com/TerminallyLazy/Tree-Ring-Memory/blob/main/LICENSE"
---
# Tree Ring Memory
## Overview
Tree Ring Memory is a framework-agnostic, local-first memory lifecycle layer for
AI agents. Use this skill when an agent should recall, preserve, audit, or
forget durable project memory without treating raw conversation transcripts as
memory.
The public runtime is a Rust CLI/TUI with local SQLite/FTS storage, scoped
recall, evidence records, audit, deterministic consolidation, maintenance,
DOX/Revolve source adapters, framework discovery, redaction, and explicit
forgetting.
## When to Use This Skill
- Use before resuming a project where prior decisions, warnings, preferences,
or failed approaches may matter.
- Use before changing architecture, storage, security, privacy, release, or
agent-memory behavior.
- Use when the user asks to remember, recall, audit, redact, forget, or
consolidate agent memory.
- Use after tests, reviews, incidents, or production behavior validate a lesson
future agents should preserve.
- Use when a project contains `.tree-ring/SKILL.md`, `.tree-ring/CLI.md`, or
other Tree Ring bridge files.
## How It Works
### Step 1: Discover Local Guidance
Check whether the current project already has Tree Ring guidance:
```bash
test -f .tree-ring/SKILL.md && sed -n '1,220p' .tree-ring/SKILL.md
test -f .tree-ring/CLI.md && sed -n '1,220p' .tree-ring/CLI.md
```
Treat project-local `.tree-ring` files as more authoritative than generic
examples in this skill. If the CLI is installed, inspect the current command
surface before assuming flags:
```bash
tree-ring --help
tree-ring recall --help
tree-ring remember --help
tree-ring evidence --help
tree-ring audit --help
tree-ring forget --help
```
If Tree Ring is not installed, do not run remote installer commands
automatically. Point the user to the project repository or install docs and ask
whether they want installation help.
## Step 2: Recall Before Risky Work
Use narrow, project-scoped recall first:
```bash
tree-ring recall "release behavior" --scope project
tree-ring recall "sqlite migration" --scope project
tree-ring recall "user preference" --scope global
```
Use recalled memory as context, not authority. Verify it against current source
files, tests, docs, issues, pull requests, logs, and runtime state before making
changes.
## Step 3: Write Only Durable Memory
Write concise memory only when it is likely to help future agents:
```bash
tree-ring remember "Run project-scoped recall before release changes." --event-type lesson --scope project
```
Prefer specific event types when supported locally:
- `decision`
- `lesson`
- `warning`
- `correction`
- `user_preference`
- `tool_result`
- `summary`
- `hypothesis`
Store the durable lesson, decision, warning, or follow-up. Do not store the
full conversation.
## Step 4: Record Evidence for Evaluated Outcomes
Use evidence records for test runs, incidents, reviewed changes, or other
evaluated outcomes:
```bash
tree-ring evidence \
--outcome observed \
--summary "Installer smoke test passed in an isolated HOME." \
--evidence-ref "ci/install-smoke/2026-07-08"
```
Outcome guidance:
- `promoted`: durable truth backed by strong evidence
- `rejected`: failed or rolled-back approach worth keeping visible
- `deferred`: unresolved idea or future option
- `observed`: normal evaluated result
Do not promote weak, stale, or unreviewed claims to durable truth.
## Step 5: Use Source Adapters Carefully
When a repo has structured source records, run dry runs first:
```bash
tree-ring dox sync --source-root . --dry-run
tree-ring revolve sync --source-root revolve --dry-run
tree-ring integrations scan --source-root .
```
Only write adapter summaries when they are concise, source-linked, useful, and
privacy-safe. Imported memory does not replace the underlying `AGENTS.md`,
Revolve record, test, pull request, issue, or documentation.
## Ring Selection
Use the smallest durable ring that fits:
- `cambium`: active or recent task context
- `outer`: recent decisions and task lessons
- `inner`: older compressed project knowledge
- `heartwood`: durable high-confidence truths
- `scar`: failures, regressions, rejected approaches, warnings
- `seed`: unresolved ideas, hypotheses, follow-ups
Prefer `outer` or `seed` unless the user confirms durability or the evidence is
strong.
## Best Practices
- Recall before risky or repeat work.
- Keep project memory project-scoped unless it is a durable cross-project user
preference.
- Attach source references such as file paths, issue ids, PR ids, evaluation
runs, or docs paths.
- Re-check current source files and runtime state before acting on recalled
memory.
- Ask at closeout what future agents should remember, avoid, or revisit.
- Use redaction, deletion, or supersession when memory is wrong, stale,
sensitive, or replaced by a newer decision.
## Security & Safety Notes
- Never use Tree Ring Memory as a hidden recorder.
- Do not store secrets, credentials, tokens, private keys, recovery codes, raw
chain-of-thought, or temporary scratchpad content.
- Do not store sensitive personal data unless the user explicitly asks and the
retention boundary is safe.
- Do not store copyrighted source text beyond short allowed excerpts.
- Do not run installer, network, destructive, or mutation commands without
explicit user approval and a clear target environment.
- Treat all examples as commands to adapt after checking local `--help`, not as
guaranteed command surfaces.
## Limitations
- Tree Ring Memory is not a replacement for source control, issue trackers,
documentation, tests, logs, or live runtime verification.
- Recalled memory can be stale or wrong. Always verify important claims against
the current project before using them to make changes.
- The CLI surface can change across releases. Prefer local `.tree-ring`
guidance and `tree-ring --help` over copied command examples.
- It should not be used for secret storage, comprehensive transcript archives,
compliance retention, or unreviewed collection of sensitive personal data.
- Cross-agent interoperability depends on each tool's ability to call the local
CLI or read project-local guidance files.
## Common Pitfalls
- **Problem:** Recalled memory conflicts with current source.
**Solution:** Treat source files, tests, docs, and runtime evidence as
authoritative; supersede or forget stale memory.
- **Problem:** Memory starts becoming transcript storage.
**Solution:** Store only durable decisions, warnings, preferences, outcomes,
and follow-ups.
- **Problem:** A lesson is useful but contains sensitive detail.
**Solution:** Store a redacted summary or do not store it.
## Related Skills
- `@agent-memory-systems` - Use for broad agent-memory architecture choices.
- `@agent-memory` - Use for the listed hybrid memory MCP system.
- `@planning-with-files` - Use when simple persistent files are enough.
## Additional Resources
- Tree Ring Memory repository: <https://github.com/TerminallyLazy/Tree-Ring-Memory>
- Codex plugin wrapper: <https://github.com/TerminallyLazy/tree-ring-memory-codex-plugin>
antigravity-awesome-skills/plugins/antigravity-bundle-aas-accessibility-inclusive-ux/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-accessibility-inclusive-ux",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Accessibility & Inclusive UX\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-accessibility-inclusive-ux/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-accessibility-inclusive-ux",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Accessibility & Inclusive UX\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-agent-mcp-builder/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-agent-mcp-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Agent & MCP Builder\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-agent-mcp-builder/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-agent-mcp-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Agent & MCP Builder\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-ai-product-evaluation-ops/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-ai-product-evaluation-ops",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS AI Product & Evaluation Ops\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-ai-product-evaluation-ops/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-ai-product-evaluation-ops",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS AI Product & Evaluation Ops\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-api-platform-builder/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-api-platform-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS API Platform Builder\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-api-platform-builder/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-api-platform-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS API Platform Builder\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-automation-builder/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-automation-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Automation Builder\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-automation-builder/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-automation-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Automation Builder\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-data-analytics/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-data-analytics",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Data Analytics\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-data-analytics/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-data-analytics",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Data Analytics\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-data-engineering-platform/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-data-engineering-platform",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Data Engineering Platform\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-data-engineering-platform/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-data-engineering-platform",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Data Engineering Platform\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-devops-cloud/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-devops-cloud",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS DevOps & Cloud\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-devops-cloud/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-devops-cloud",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS DevOps & Cloud\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-documents-presentations/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-documents-presentations",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Documents & Presentations\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-documents-presentations/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-documents-presentations",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Documents & Presentations\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-localization-international-growth/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-localization-international-growth",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Localization & International Growth\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-localization-international-growth/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-localization-international-growth",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Localization & International Growth\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-marketing-seo-growth/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-marketing-seo-growth",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Marketing, SEO & Growth\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-marketing-seo-growth/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-marketing-seo-growth",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Marketing, SEO & Growth\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-mobile-app-builder/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-mobile-app-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Mobile App Builder\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-mobile-app-builder/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-mobile-app-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Mobile App Builder\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-observability-ir/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-observability-ir",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Observability IR\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-observability-ir/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-observability-ir",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Observability IR\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-oss-maintainer/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-oss-maintainer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS OSS Maintainer\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-oss-maintainer/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-oss-maintainer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS OSS Maintainer\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-privacy-compliance-engineering/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-privacy-compliance-engineering",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Privacy & Compliance Engineering\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-privacy-compliance-engineering/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-privacy-compliance-engineering",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Privacy & Compliance Engineering\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-product-design-studio/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-product-design-studio",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Product Design Studio\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-product-design-studio/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-product-design-studio",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Product Design Studio\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-python-api-builder/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-python-api-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Python API Builder\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-python-api-builder/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-python-api-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Python API Builder\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-qa-test-automation/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-qa-test-automation",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS QA & Test Automation\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-qa-test-automation/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-qa-test-automation",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS QA & Test Automation\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-saas-launch-revenue/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-saas-launch-revenue",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS SaaS Launch & Revenue\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-saas-launch-revenue/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-saas-launch-revenue",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS SaaS Launch & Revenue\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-secure-app-builder/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-secure-app-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Secure App Builder\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-secure-app-builder/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-secure-app-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Secure App Builder\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-security-engineer/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-security-engineer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Security Engineer\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-security-engineer/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-security-engineer",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Security Engineer\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-web-app-builder/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-aas-web-app-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"AAS Web App Builder\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-aas-web-app-builder/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-aas-web-app-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"AAS Web App Builder\" workflow plugin from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-agent-architect/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-agent-architect",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"Agent Architect\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-agent-architect/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-agent-architect",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Agent Architect\" editorial skill bundle from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-apple-platform-design/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-apple-platform-design",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"Apple Platform Design\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-apple-platform-design/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-apple-platform-design",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Apple Platform Design\" editorial skill bundle from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-architecture-design/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-architecture-design",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"Architecture & Design\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-architecture-design/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-architecture-design",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Architecture & Design\" editorial skill bundle from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-automation-builder/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "antigravity-bundle-automation-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Editorial \"Automation Builder\" bundle for Claude Code from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",
antigravity-awesome-skills/plugins/antigravity-bundle-automation-builder/.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agyb-automation-builder",
"version": "13.12.0",
"version": "13.13.0",
"description": "Install the \"Automation Builder\" editorial skill bundle from Antigravity Awesome Skills.",
"author": {
"name": "sickn33 and contributors",

Some files were not shown because too many files have changed in this diff Show More