karpathy-guidelines
Skill0 starsChanged 26 days agoUnlicenseView on GitHub
Behavioral guidelines for planning, writing, and reviewing code. Load at session start when doing any code work. Highest priority: Goal-Driven Execution — transform tasks into verifiable goals with success criteria and loop until verified. Also covers: Think Before Coding (surface assumptions, push back when warranted), Simplicity First (minimum code, no speculation), and Surgical Changes (touch only what you must).
126 other projects use a version of this, 112 of them edited.
Adopted by
Most recently taken up by
- Markssuave/Markssuave-Agent-skillsedited, first seen Nov 8, 2026
- mujtbabbas/andrej-karpathy-skillsedited, first seen Nov 8, 2026
- afawfawffaf/my-skillsedited, first seen Nov 8, 2026
- hamzzaqureshi/gravidexedited, first seen Nov 8, 2026
- lemonAlpha23/claude_code_toolboxedited, first seen Nov 8, 2026
- mel0nyrame/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use huashu-design, github-cli and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
XIYBHKSkillhuashu-design
花叔Design(Huashu-Design)——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索+设计方向顾问+专家评审的一体化设计能力。HTML是工具不是媒介,根据任务embody不同专家(UX设计师/动画师/幻灯片设计师/原型师),避免web design tropes。触发词:做原型、设计Demo、交互原型、HTML演示、动画Demo、设计变体、hi-fi设计、UI mockup、prototype、设计探索、做个HTML页面、做个可视化、app原型、iOS原型、移动应用mockup、导出MP4、导出GIF、60fps视频、设计风格、设计方向、设计哲学、配色方案、视觉风格、推荐风格、选个风格、做个好看的、评审、好不好看、review this design。**主干能力**:Junior Designer工作流(先给假设+reasoning+placeholder再迭代)、反AI slop清单、React+Babel最佳实践、Tweaks变体切换、Speaker Notes演示、Starter Components(幻灯片外壳/变体画布/动画引擎/设备边框)、App原型专属守则(默认从Wikimedia/Met/Unsplash取真图、每台iPhone包AppPhone状态管理器可交互、交付前跑Playwright点击测试)、Playwright验证、HTML动画→MP4/GIF视频导出(25fps基础 + 60fps插帧 + palette优化GIF + 6首场景化BGM + 自动fade)。**需求模糊时的Fallback**:设计方向顾问模式——从5流派×20种设计哲学(Pentagram信息建筑/Field.io运动诗学/Kenya Hara东方极简/Sagmeister实验先锋等)推荐3个差异化方向,展示24个预制showcase(8场景×3风格),并行生成3个视觉Demo让用户选。**交付后可选**:专家级5维度评审(哲学一致性/视觉层级/细节执行/功能性/创新性各打10分+修复清单)。
Also in 3 projects that use this
rogue-dev-studioSkillgithub-cli
GitHub CLI authentication and workflow configuration. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `github-cli` work when listed in TEAM.yaml or explicitly requested.
Also in 3 projects that use this
seikaikyoSkillbanner-design
Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.
Also in 4 projects that use this
OpenAISkillusing-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Also in 9 projects that use this
GoogleSkillponytail
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
Also in 9 projects that use this
LLl0k0laDSkillidea-refine
Refine ideas through structured divergent and convergent thinking. Use "idea-refine" or "ideate" to trigger.
Also in 4 projects that use this
Other versions126 projects use a version of this.
Word for word · 0
None found.
Edited · 112
- forrestchang/andrej-karpathy-skills★ 217k86% same
- multica-ai/andrej-karpathy-skills★ 214k86% same
- ghostfolio/ghostfolio★ 9.7k86% same
- OpenBMB/PilotDeck★ 5k86% same
- didi/mpx★ 4k86% same
- hzm0321/real-time-fund★ 1.8k86% same
- x-tools-author/x-tools★ 1.1k86% same
- mxyhi/ok-skills★ 51186% same
- vtroisWhite/andrej-karpathy-skills★ 42686% same
- Y80/bmm★ 34486% same
102 more not listed
Wrote their own version · 14
- coco-research/coco★ 797same name
- tev6/andrej-karpathy-skills-zhCN★ 17same name
- Sspacegray/andrej-karpathy-skills-codex★ 8same name
- richling98/karpathy-codex-skills★ 4same name
- hahuyhungdev/ai-coding-config★ 3same name
- Hotakus/hotakus-useful-skills★ 2same name
- mel0nyrame/skills★ 2same name
- thlaure/Signalist★ 2same name
- ahmadrishi/agentic-mahoraga★ 1same name
- audriusstat/execution-discipline★ 0same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 14 are common, 0 are distinctive, and 1 is very specific to this project.
14
Common
Most of the 122 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 36
If multiple interpretations exist, present them - don't pick silently.
- Common: line 37
If a simpler approach exists, say so.
- Common: line 38
If something is unclear, stop.
- Common: line 44
No features beyond what was asked.
- Common: line 45
No abstractions for single-use code.
- Common: line 47
No error handling for impossible scenarios.
- Common: line 48
If you write 200 lines and it could be 50, rewrite it.
- Common: line 50
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
- Common: line 56
When editing existing code:
- Common: line 57
Don't "improve" adjacent code, comments, or formatting.
- Common: line 58
Don't refactor things that aren't broken.
- Common: line 60
If you notice unrelated dead code, mention it - don't delete it.
- Common: line 62
When your changes create orphans:
- Very specific: line 63
Remove imports/variables/functions that YOUR changes made unused.
- Common: line 64
Don't remove pre-existing dead code unless asked.
“Common” is measured: kept by at least 6 in 10 of the 122 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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. Goal-Driven Execution (highest priority)
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.
2. 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.
3. 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.
4. 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.
These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

