agentleFS
Sign inStart free
Y80Y80/bmm/.agents/skills/karpathy-guidelines/SKILL.md

karpathy-guidelines

Skill344 starsChanged 6 months agoMITView on GitHub

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.

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 56 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
  1. Common:

    If multiple interpretations exist, present them - don't pick silently.

    line 19
  2. Common:

    If a simpler approach exists, say so.

    line 20
  3. Common:

    If something is unclear, stop.

    line 21
  4. Common:

    No features beyond what was asked.

    line 27
  5. Common:

    No abstractions for single-use code.

    line 28
  6. Common:

    No error handling for impossible scenarios.

    line 30
  7. Common:

    If you write 200 lines and it could be 50, rewrite it.

    line 31
  8. Common:

    Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

    line 33
  9. Common:

    When editing existing code:

    line 39
  10. Common:

    Don't "improve" adjacent code, comments, or formatting.

    line 40
  11. Common:

    Don't refactor things that aren't broken.

    line 41
  12. Common:

    If you notice unrelated dead code, mention it - don't delete it.

    line 43
  13. Common:

    When your changes create orphans:

    line 45
  14. Very specific:

    Remove imports/variables/functions that YOUR changes made unused.

    line 46
  15. Common:

    Don't remove pre-existing dead code unless asked.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 56 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Trending

Cooling: 4 new projects took it in the last 4 weeks, 0.7× the 4 weeks before.thin data

Week of Aug 30: 1 new projectWeek of Sep 6: 1 new projectWeek of Sep 13: 1 new projectWeek of Sep 20: 3 new projectsWeek of Sep 27: 1 new projectWeek of Oct 4: 3 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projects
Aug 2026Sep 2026Oct 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 10 in all, so this is a hint, not a trend.
  • Other versions118 projects use a version of this.

    Word for word · 59

    1. forrestchang/andrej-karpathy-skills★ 217k100% same
    2. multica-ai/andrej-karpathy-skills★ 214k100% same
    3. OpenBMB/PilotDeck★ 4.5k100% same
    4. didi/mpx★ 3.9k100% same
    5. x-tools-author/x-tools★ 1.1k100% same
    6. mxyhi/ok-skills★ 506100% same
    7. vtroisWhite/andrej-karpathy-skills★ 426100% same
    8. ninehills/skills★ 280100% same
    9. doggy8088/andrej-karpathy-skills★ 231100% same
    10. youdotcom-oss/agent-skills★ 98100% same

    49 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.

  • Used alongsideProjects 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.
    • XIYBHKSkill

      huashu-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

    • doug-skinnerSkill

      github-cli

      Execute GitHub CLI (gh) commands for repository management, issues, pull requests, workflows, and releases. Use when the user wants to interact with GitHub repositories, create/manage issues or PRs, trigger workflows, or perform any GitHub operations. Covers both solo developer workflows and team collaboration patterns.

      Also in 3 projects that use this

    • MicrosoftSkill

      ui-styling

      Guide for the visual style, structure, and shared building blocks used by Semantic Link Labs interactive UI tools (HTML widgets and anywidget-based widgets). Use this when adding a new interactive UI, modifying an existing one, or adding shared visual components.

      Also in 4 projects that use this

    • JetBrainsSkill

      doc-coauthoring

      Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

      Also in 7 projects that use this

    • GoogleSkill

      writing-great-skills

      Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

      Also in 5 projects that use this

    • OpenAISkill

      using-superpowers

      Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

      Also in 7 projects that use this

  • In this repository8 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.

Check your setup, free