agentleFS
Binbin-miaoBinbin-miao/workbuddy-expert-team/skills/karpathy-guidelines/SKILL.md

karpathy-guidelines

Skill1 starsChanged 10 days agoMITView on GitHub

Enforces Andrej Karpathy's 4 LLM coding rules: No Silent Assumptions, No Over-Engineering, No Orthogonal Changes, and Explicit Verification.

129 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use huashu-design, github-cli and 6 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

  • rogue-dev-studioSkill

    github-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

  • seikaikyoSkill

    banner-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

  • 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 9 projects that use this

  • LLl0k0laDSkill

    idea-refine

    Refine ideas through structured divergent and convergent thinking. Use "idea-refine" or "ideate" to trigger.

    Also in 4 projects that use this

  • OpenAISkill

    executing-plans

    Use when you have a written implementation plan to execute in a separate session with review checkpoints

    Also in 12 projects that use this

The file

Files
SKILL.md

/karpathy-guidelines — Karpathy 四大编码防坑铁律

源自 multica-ai/andrej-karpathy-skills,用于根治大模型编码中最常见的四大顽疾:

四大核心铁律(Four Constitutional Rules)

Rule 1: 严禁静默假设(No Silent Assumptions)

  • 在动手修改任何代码前,必须先核实对需求、数据边界与上下文的理解。
  • 凡是代码库里能查到的客观事实(Facts)自己静默查清;凡是存在多种合理解释的业务/架构分歧,必须在《开工方案卡》中向用户确认,严禁把未验证的猜测直接写进代码。

Rule 2: 严禁过度工程(No Over-Engineering)

  • 能完整解决问题且清晰易读的最简方案就是正确方案。
  • 严禁为了“未来可能的扩展性”发明无人调用的抽象层、泛型工厂、配置开关或多余封装。

Rule 3: 严禁顺手修改无关代码(No Orthogonal Changes / Surgical Diffs)

  • 外科手术式 Diff 纪律:每一行 Diff 都必须直接服务于当前请求的目标。绝对禁止在修 Bug 或做功能时顺手重构旁边的无关模块、重排未触及文件的导入顺序、或修改无关代码格式。
  • 若发现无关模块的潜在问题,在报告末尾的 ⚠️ 风险与遗留 中单独指出,绝不混入当前变更集。

Rule 4: 强制显式验证(Explicit Verification)

  • 写完代码绝不等于任务完成。必须针对改动运行对应的测试、构建、类型检查或真实命令行验证,用真实输出证明改动有效且未破坏既有功能。

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.