csh
3d83740f88
25d895d 🐛 fix(gitea_workflow): clean up temp repos after job steps 2bc3b11 🐛 fix(gitea_workflow): clean up temporary repo dirs in workflows 98c3f30 📝 docs(agent_rules): allow plan execution on current branch 16c7230 📝 docs(prompts): define custom verify layering 8efc4dd 🐛 fix(skills): quote commit-message description bc8498f 🐛 fix(ci): install tomli for gitea tests 55cda3b 🐛 fix(tests): report missing toml parser clearly c0729c7 🐛 fix(playbook): import Optional for cli compatibility 63e24bf 📦 deps(skills): sync thirdparty skills d2f9356 🐛 fix(ci): isolate gitea workflow repos 588b81d 🐛 fix(ci): inline gitea workflow bootstrap e0b1c3a ♻️ refactor(skills): standardize first-party skill contracts 2c5050d ♻️ refactor(skills): rename repo skills source dir f049dfb 📦 deps(skills): drop duplicate first-party superpowers skills 234b335 ✨ feat(workflow): add superpowers planning and execution state tracking c1702a6 📝 docs(markdown): format tracked markdown and drop stale templates 2325409 📝 docs(markdown): clarify optional markdownlint usage 214c44e 🔧 chore(markdown): add markdownlint baseline and lint fixes a22b324 📝 docs(templates): add execution and memory-bank prompt templates 223a797 📝 docs(templates): update README for Claude Code and current features 4ac8672 📝 docs: simplify README + platform-agnostic tools + auto-create local rules 2431c9d 📝 docs: add claude_md config and use cross-platform paths d64b248 📝 docs: fix README.md inaccuracies and add Claude Code info c8d6bf2 🐛 fix(playbook): use relative paths in CLAUDE.md when not at project root 6518f0f ✨ feat(playbook): auto-create CLAUDE.md with path discovery 6ec9a45 ✨ feat(skills): add skill_link symlink support + platform-agnostic prompt 9f8b6b5 📝 docs: update README and config example for Claude Code support 79cff6c 📝 docs(skills): add Claude Code platform support 452c6f5 ✨ feat(playbook): auto-inject AGENTS.md into CLAUDE.md e1dbf3c 🐛 fix(skills): remove dual-path from commit-message skill f3a7259 🔧 chore(ci): use prepare_repo.sh in both workflows da08212 🔧 chore(ci): extract prepare_repo.sh and clean up workflows 7ade85e 🗑️ remove(tsl): drop syntax_book/, data/ source and build script f94dba0 ♻️ refactor(skills): update playbook.py and tests for thirdparty/ layout b3df412 ♻️ refactor(skills): separate thirdparty skills into thirdparty/ subdirectory 64950e7 📦 deps(skills): sync thirdparty skills a2e3cb0 ✨ feat(playbook): add no_backup deploy controls 8609d59 🐛 fix(docs): repair reference catalog source links 956da11 🐛 fix(playbook): publish hidden ci test fixes 3f67754 📦 deps(skills): sync thirdparty skills 08ca87b 📦 deps(skills): add karpathy thirdparty sync 96b705b 📝 docs(tsl): rebuild canonical syntax and routing manual 3ed5052 📦 deps(skills): sync thirdparty skills 60108dd 📦 deps(skills): sync thirdparty skills da85d4e 🐛 fix(thirdparty): prune nested project snapshots a2a697e 📦 deps(skills): sync thirdparty skills 9df610a 🐛 fix(thirdparty): exclude duplicated superpowers skills 33dd5bb 🐛 fix(thirdparty): preserve optional manifest fields 91b0ea7 🐛 fix(thirdparty): preserve manifest during snapshot update 2e26f98 🔧 chore(thirdparty): generalize skills sync pipeline 5b9c1e3 📦 deps(skills): sync superpowers 2f2d34a 📝 docs(readme): normalize subtree command spacing 62db7db 🐛 fix(ci): serialize superpowers update and sync 3463223 🐛 fix(ci): use literal superpowers sync paths 48f6de8 📦 deps(skills): sync superpowers 4b23529 🔧 chore(ci): merge superpowers update and sync workflow a56d75b 📦 deps(skills): sync superpowers 84bcefa 🔧 chore(ci): use ci[bot] commit author name 00a07e5 📦 deps(skills): sync superpowers 7b84daf 🐛 fix(templates): enforce main loop progress tracking 51373d7 🔧 chore(ci): automate superpowers sync workflow eaaa39c 🐛 fix(ci): prevent stale superpowers sync from restoring skills block 79755c6 📦 deps(skills): sync superpowers 836d878 📦 deps(skills): sync superpowers 8216c9f 📦 deps(skills): sync superpowers 9439505 🐛 fix(playbook): address reported repo issues git-subtree-dir: docs/standards/playbook git-subtree-split: 25d895d8b3f56624ccfe99ad7289e9eb49e0f316
2.5 KiB
2.5 KiB
name, description, license
| name | description | license |
|---|---|---|
| karpathy-guidelines | 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. | MIT |
Karpathy Guidelines
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations 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.