[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71RS2Z5M27A5JD9TSW7BVJA":3,"skill-same:01M71RS2Z5M27A5JD9TSW7BVJA":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M71RS2Z5M27A5JD9TSW7BVJA","karpathy-guidelines",null,"Use only when the user explicitly asks to apply these guidelines (e.g. \"按 karpathy 规则写\", \"apply karpathy guidelines\", \"\u002Fkarpathy\"), or explicitly asks for a review against them. Do not activate for ordinary writing, reviewing, or refactoring tasks. When uncertain, do not activate this skill.","ThisingL\u002Fskills","ThisingL","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F104803669?v=4","01M71RREPZCNJMS303A0WEN8JW","今天机器不学习","01M71RREQHJ387D48V9TXVN42P",3,"MIT","https:\u002F\u002Fgithub.com\u002FThisingL\u002Fskills\u002Fblob\u002Fmaster\u002Fcoding\u002Fkarpathy-guidelines\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"guidelines","karpathy","karpathy guidelines","do","for","only","writing","use","when","apply","tasks","activate","review","规则","refactoring","user","2026-11-10 13:02:02",false,"---\nname: karpathy-guidelines\ndescription: Use only when the user explicitly asks to apply these guidelines (e.g. \"按 karpathy 规则写\", \"apply karpathy guidelines\", \"\u002Fkarpathy\"), or explicitly asks for a review against them. Do not activate for ordinary writing, reviewing, or refactoring tasks. When uncertain, do not activate this skill.\nlicense: MIT\n---\n\n# Karpathy Guidelines\n\nBehavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https:\u002F\u002Fx.com\u002Fkarpathy\u002Fstatus\u002F2015883857489522876) on LLM coding pitfalls.\n\n**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.\n\n## 1. Think Before Coding\n\n**Don't assume. Don't hide confusion. Surface tradeoffs.**\n\nBefore implementing:\n- State your assumptions explicitly. If uncertain, ask.\n- If multiple interpretations exist, present them - don't pick silently.\n- If a simpler approach exists, say so. Push back when warranted.\n- If something is unclear, stop. Name what's confusing. Ask.\n\n## 2. Simplicity First\n\n**Minimum code that solves the problem. Nothing speculative.**\n\n- No features beyond what was asked.\n- No abstractions for single-use code.\n- No \"flexibility\" or \"configurability\" that wasn't requested.\n- No error handling for impossible scenarios.\n- If you write 200 lines and it could be 50, rewrite it.\n\nAsk yourself: \"Would a senior engineer say this is overcomplicated?\" If yes, simplify.\n\n## 3. Surgical Changes\n\n**Touch only what you must. Clean up only your own mess.**\n\nWhen editing existing code:\n- Don't \"improve\" adjacent code, comments, or formatting.\n- Don't refactor things that aren't broken.\n- Match existing style, even if you'd do it differently.\n- If you notice unrelated dead code, mention it - don't delete it.\n\nWhen your changes create orphans:\n- Remove imports\u002Fvariables\u002Ffunctions that YOUR changes made unused.\n- Don't remove pre-existing dead code unless asked.\n\nThe test: Every changed line should trace directly to the user's request.\n\n## 4. Goal-Driven Execution\n\n**Define success criteria. Loop until verified.**\n\nTransform tasks into verifiable goals:\n- \"Add validation\" → \"Write tests for invalid inputs, then make them pass\"\n- \"Fix the bug\" → \"Write a test that reproduces it, then make it pass\"\n- \"Refactor X\" → \"Ensure tests pass before and after\"\n\nFor multi-step tasks, state a brief plan:\n```\n1. [Step] → verify: [check]\n2. [Step] → verify: [check]\n3. [Step] → verify: [check]\n```\n\nStrong success criteria let you loop independently. Weak criteria (\"make it work\") require constant clarification.\n","# Karpathy Guidelines\n\nBehavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https:\u002F\u002Fx.com\u002Fkarpathy\u002Fstatus\u002F2015883857489522876) on LLM coding pitfalls.\n\n**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.\n\n## 1. Think Before Coding\n\n**Don't assume. Don't hide confusion. Surface tradeoffs.**\n\nBefore implementing:\n- State your assumptions explicitly. If uncertain, ask.\n- If multiple interpretations exist, present them - don't pick silently.\n- If a simpler approach exists, say so. Push back when warranted.\n- If something is unclear, stop. Name what's confusing. Ask.\n\n## 2. Simplicity First\n\n**Minimum code that solves the problem. Nothing speculative.**\n\n- No features beyond what was asked.\n- No abstractions for single-use code.\n- No \"flexibility\" or \"configurability\" that wasn't requested.\n- No error handling for impossible scenarios.\n- If you write 200 lines and it could be 50, rewrite it.\n\nAsk yourself: \"Would a senior engineer say this is overcomplicated?\" If yes, simplify.\n\n## 3. Surgical Changes\n\n**Touch only what you must. Clean up only your own mess.**\n\nWhen editing existing code:\n- Don't \"improve\" adjacent code, comments, or formatting.\n- Don't refactor things that aren't broken.\n- Match existing style, even if you'd do it differently.\n- If you notice unrelated dead code, mention it - don't delete it.\n\nWhen your changes create orphans:\n- Remove imports\u002Fvariables\u002Ffunctions that YOUR changes made unused.\n- Don't remove pre-existing dead code unless asked.\n\nThe test: Every changed line should trace directly to the user's request.\n\n## 4. Goal-Driven Execution\n\n**Define success criteria. Loop until verified.**\n\nTransform tasks into verifiable goals:\n- \"Add validation\" → \"Write tests for invalid inputs, then make them pass\"\n- \"Fix the bug\" → \"Write a test that reproduces it, then make it pass\"\n- \"Refactor X\" → \"Ensure tests pass before and after\"\n\nFor multi-step tasks, state a brief plan:\n```\n1. [Step] → verify: [check]\n2. [Step] → verify: [check]\n3. [Step] → verify: [check]\n```\n\nStrong success criteria let you loop independently. Weak criteria (\"make it work\") require constant clarification.\n",{"name":5,"license":15,"description":7},"master","144a1a346c5cea3571f30099f1d52fbfb2f521ea","coding\u002Fkarpathy-guidelines",0,"https:\u002F\u002Fgithub.com\u002FThisingL\u002Fskills","https:\u002F\u002Fgithub.com\u002FThisingL","thisingl.github.io","数学，计算机科学，现代人工智能","2026-11-01 20:40:33",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add ThisingL\u002Fskills --skill karpathy-guidelines",{"tool":55,"command":56},"bunx","bunx skills add ThisingL\u002Fskills --skill karpathy-guidelines",{"tool":58,"command":59},"pnpm","pnpm dlx skills add ThisingL\u002Fskills --skill karpathy-guidelines","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FThisingL\u002Fskills\u002Fblob\u002Fmaster\u002Fcoding\u002Fkarpathy-guidelines\u002FSKILL.md",true,[63],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"README.md","REFERENCE","参考文档",6042,"https:\u002F\u002Fgithub.com\u002FThisingL\u002Fskills\u002Fblob\u002Fmaster\u002Fcoding\u002Fkarpathy-guidelines\u002FREADME.md",[70],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":35},"01M71RS5CRSHRRK40CC0FE5G23","focus-session","Use when a user wants a focused study session (开始专注学习、随机学习提醒), controls this project's study timer, requests the current session's timeline, or wants to recall and check what they just learned. Not for general tutoring, long-term study planning, or automatic review after every task.","https:\u002F\u002Fgithub.com\u002FThisingL\u002Fskills\u002Fblob\u002Fmaster\u002Flearning\u002Ffocus-session\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FThisingL\u002Fskills\u002Fblob\u002Fmaster\u002Flearning\u002Ffocus-session\u002FSKILL.md",[],[78,79,80,34,27,81,26,82,83,84,85,86,87,88,89,90,23,91,92,93],"focus session","session","focus","timeline","timer","controls","automatic","general","long","recall","study","just","project","planning","learned","requests"]