📝 docs(tsl): clarify syntax constraints and enhance test infrastructure
- Add TSF file naming constraint to syntax/02_core_model.md - Clarify semicolon rules: syntax facts vs style preferences - Separate control flow end semicolon rules (syntax allows both) - Add function body semicolon requirements to syntax/05_functions_and_calls.md - Move style preferences to code_style.md (control flow end semicolons) - Remove cross-references from syntax docs to maintain independence - Enhance Gitea workflow emoji for better CI output readability - Fix CI test path from tests/ to test/ - Organize agent test results under test/agent/result/ directory - Add complete Chinese translation of test cases (test_cases_zh.md) - Clean up .gitignore to use unified test/agent/result/ directory - Remove obsolete agent test artifacts (REPORTS_LOCATION.md, old results) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Claude Opus 4.6
+30
-61
@@ -1,21 +1,22 @@
|
||||
# Skills Overview
|
||||
|
||||
本目录放置 Playbook 可安装的 AI agent skills。
|
||||
本目录包含 Playbook 提供的 AI agent skills，分为两类：
|
||||
|
||||
- 一方 skill 位于 `skills/<name>/SKILL.md`，由本仓库维护。
|
||||
- 第三方 skill 位于 `skills/thirdparty/<name>/SKILL.md`，由同步流程生成或更新。
|
||||
- 第三方来源登记见 `skills/thirdparty/thirdparty-skills.yml` 与
|
||||
`.gitea/ci/thirdparty_skills.json`。
|
||||
- **一方 skills**：本仓库维护（`skills/<name>/`）
|
||||
- **第三方 skills**：同步自外部来源（`skills/thirdparty/<name>/`）
|
||||
|
||||
安装与使用详见 [SKILLS.md](../SKILLS.md)。
|
||||
|
||||
## 一方 Skills
|
||||
|
||||
| Skill | 作用 | 典型场景 |
|
||||
| --- | --- | --- |
|
||||
| `bulk-refactor-workflow` | 大规模重构工作流：符号重命名、API 迁移、安全机械变更 | 跨多文件重命名、API 替换、批量代码转换 |
|
||||
| `commit-message` | 根据 staged diff 生成符合仓库规范的提交信息，并判断是否应拆分提交 | 写 commit message、检查 staged 改动是否适合一个提交 |
|
||||
| `gitea-fix-ci` | 基于 Gitea Actions run/job/log 诊断失败 CI，先形成修复计划再改代码 | Gitea PR checks 失败、远端 CI 红但本地需要定位 |
|
||||
| `style-cleanup` | 使用仓库既有 formatter/linter 做格式和 lint 收尾，不改变语义 | 格式化、lint cleanup、代码改完后的风格整理 |
|
||||
|
||||
## 已同步第三方 Skills
|
||||
## 第三方 Skills
|
||||
|
||||
### Superpowers Workflow Suite
|
||||
|
||||
@@ -38,63 +39,31 @@
|
||||
| `receiving-code-review` | 处理别人给出的 review 意见，判断采纳、反驳或澄清 |
|
||||
| `writing-skills` | 创建、修改或验证 skill 的写作规范 |
|
||||
|
||||
### Other Synced Third-party Skills
|
||||
|
||||
| Skill | 来源 | 作用 |
|
||||
| --- | --- | --- |
|
||||
| `ui-ux-pro-max` | `ui-ux-pro-max-skill` | UI/UX 设计知识库，包含风格、配色、字体、组件和栈相关建议 |
|
||||
| `karpathy-guidelines` | `andrej-karpathy-skills` | 写代码、审查、重构时降低 LLM 常见错误：保持简单、聚焦、可验证 |
|
||||
|
||||
## 已登记待同步 Third-party Skills
|
||||
|
||||
这些来源已登记，后续同步后会落到 `skills/thirdparty/`。
|
||||
|
||||
### brooks-lint Suite
|
||||
|
||||
`brooks-lint` 是一个套件来源，不是单个 skill。同步时会包含多个下游 skill
|
||||
以及共享资料目录：
|
||||
Code review 和质量审查工具集，包含共享参考资料目录 `_shared`。
|
||||
|
||||
| 下游项 | 隶属 | 作用 |
|
||||
| --- | --- | --- |
|
||||
| `brooks-review` | `brooks-lint` | 常规 PR / diff code review |
|
||||
| `brooks-audit` | `brooks-lint` | architecture audit、系统性结构问题审查 |
|
||||
| `brooks-debt` | `brooks-lint` | technical debt review |
|
||||
| `brooks-health` | `brooks-lint` | 项目健康度检查 |
|
||||
| `brooks-sweep` | `brooks-lint` | 扫描式问题发现 |
|
||||
| `brooks-test` | `brooks-lint` | 测试质量审查 |
|
||||
| `_shared` | `brooks-lint` | brooks 系列 skill 共享参考资料，不是独立使用的 skill |
|
||||
|
||||
### outfitter-dev/agents Source
|
||||
|
||||
`outfitter-dev/agents` 是一个较大的 agents 仓库。当前只登记并同步其中和
|
||||
代码库侦察相关的下游项：
|
||||
|
||||
| 下游项 | 隶属 | 作用 |
|
||||
| --- | --- | --- |
|
||||
| `codebase-recon` | `outfitter-dev/agents` | 通过 git 历史和代码结构做 risk scan、热点分析、重构前侦察 |
|
||||
| `pathfinding` | `outfitter-dev/agents` | 需求澄清和 confidence calibration；同时补齐 `codebase-recon` 引用的 `confidence.md` |
|
||||
|
||||
### Single-skill Sources
|
||||
|
||||
| Skill | 来源 | 作用 |
|
||||
| --- | --- | --- |
|
||||
| `codebase-migrate` | `awesome-codex-skills` | 大代码库迁移、多文件 refactor、分批变更与 CI 验证工作流 |
|
||||
| `uncle-bob-craft` | `antigravity-awesome-skills` | Clean Architecture、SOLID、设计模式误用和代码工匠实践审查 |
|
||||
|
||||
#### `uncle-bob-craft` 定位
|
||||
|
||||
`uncle-bob-craft` 是原则型补强 skill，不替代现有 `brooks-*` 或
|
||||
`codebase-*` 主流程。它适合在问题明确聚焦 Clean Architecture、SOLID、
|
||||
职责拆分、依赖方向、设计模式是否滥用、代码工匠实践时使用。
|
||||
|
||||
| 对比项 | 分工 |
|
||||
| Skill | 作用 |
|
||||
| --- | --- |
|
||||
| `codebase-recon` | 负责重构前侦察、热点分析和影响面判断；`uncle-bob-craft` 不负责代码库级侦察 |
|
||||
| `brooks-audit` | 负责架构边界、模块职责和长期维护性审查；`uncle-bob-craft` 只作为 Clean Architecture / SOLID 视角补强 |
|
||||
| `codebase-migrate` | 负责大规模迁移、多文件 refactor 和 CI 验证节奏；`uncle-bob-craft` 不负责迁移编排 |
|
||||
| `brooks-review` | 负责 PR / diff 级代码审查；`uncle-bob-craft` 仅在审查重点是 SOLID、职责拆分或设计模式误用时配合使用 |
|
||||
| `brooks-test` | 负责测试质量、断言边界和测试脆弱性审查；`uncle-bob-craft` 不负责测试质量专项审查 |
|
||||
| `brooks-review` | 常规 PR / diff code review |
|
||||
| `brooks-audit` | architecture audit、系统性结构问题审查 |
|
||||
| `brooks-debt` | technical debt review |
|
||||
| `brooks-health` | 项目健康度检查 |
|
||||
| `brooks-sweep` | 扫描式问题发现 |
|
||||
| `brooks-test` | 测试质量审查 |
|
||||
|
||||
推荐触发方式：有明确 Clean Architecture、SOLID、Uncle Bob、职责拆分、
|
||||
依赖方向或设计模式误用问题时使用；普通 PR 审查仍优先 `brooks-review`，
|
||||
架构级审查仍优先 `brooks-audit`。
|
||||
### 代码库侦察与迁移
|
||||
|
||||
| Skill | 作用 |
|
||||
| --- | --- |
|
||||
| `codebase-recon` | 通过 git 历史和代码结构做 risk scan、热点分析、重构前侦察 |
|
||||
| `pathfinding` | 需求澄清和 confidence calibration |
|
||||
| `codebase-migrate` | 大代码库迁移、多文件 refactor、分批变更与 CI 验证工作流 |
|
||||
|
||||
### 其他
|
||||
|
||||
| Skill | 作用 |
|
||||
| --- | --- |
|
||||
| `ui-ux-pro-max` | UI/UX 设计知识库，包含风格、配色、字体、组件和栈相关建议 |
|
||||
| `karpathy-guidelines` | 写代码、审查、重构时降低 LLM 常见错误：保持简单、聚焦、可验证 |
|
||||
| `uncle-bob-craft` | Clean Architecture、SOLID、设计模式误用和代码工匠实践审查 |
|
||||
|
||||
Reference in New Issue
Block a user