♻️ refactor(skills): separate thirdparty skills into thirdparty/ subdirectory

- Move all third-party skills from codex/skills/ to codex/skills/thirdparty/
- Move .sources/ to codex/skills/thirdparty/.sources/
- Delete systematic-debugging/CREATION-LOG.md (internal dev note, not skill content)
- Update sync_thirdparty_skills.sh paths and conflict detection
- Update thirdparty_skills.json source_list paths
- Update install_skills_action to collect from both own and thirdparty dirs,
  logging [thirdparty] tag for third-party installs
- Update SKILLS.md directory structure docs
- Update tests to reflect new paths

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
csh
2026-05-15 14:50:02 +08:00
co-authored by Claude Opus 4.7
parent 64950e7979
commit b3df41205d
92 changed files with 1606 additions and 27 deletions
+73
View File
@@ -0,0 +1,73 @@
---
name: karpathy-guidelines
description: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
license: MIT
---
# Karpathy Guidelines
Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.
**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
## 1. Think Before Coding
**Don't assume. Don't hide confusion. Surface tradeoffs.**
Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
## 2. Simplicity First
**Minimum code that solves the problem. Nothing speculative.**
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
If you write 200 lines and it could be 50, rewrite it.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
## 3. Surgical Changes
**Touch only what you must. Clean up only your own mess.**
When editing existing code:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it - don't delete it.
When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused.
- Don't remove pre-existing dead code unless asked.
The test: Every changed line should trace directly to the user's request.
## 4. Goal-Driven Execution
**Define success criteria. Loop until verified.**
Transform tasks into verifiable goals:
- "Add validation" → "Write tests for invalid inputs, then make them pass"
- "Fix the bug" → "Write a test that reproduces it, then make it pass"
- "Refactor X" → "Ensure tests pass before and after"
For multi-step tasks, state a brief plan:
```
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
```
Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.