[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-forrestchang-karpathy-guidelines-en":3,"guides-for-forrestchang-karpathy-guidelines":351,"similar-k1798nxfxtb0kgesxhkv8pt90186m36k-en":352},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":239,"isFallback":226,"parentExtension":244,"providers":301,"relations":305,"repo":306,"tags":348,"workflow":349},1778687058458.699,"k1798nxfxtb0kgesxhkv8pt90186m36k",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"forrestchang/andrej-karpathy-skills","karpathy-guidelines","https://github.com/forrestchang/andrej-karpathy-skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":237},1778687179355.7266,"kn7e311cfaqp6kjnsqk4y0dax586nyrt","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":205,"promptVersionScoring":206,"purpose":207,"rationale":208,"score":209,"summary":210,"tags":211,"targetMarket":217,"tier":218,"useCases":219},[21,26,29,33,37,41,45,48,52,56,60,63,66,69,73,76,79,82,85,88,92,96,99,103,106,109,112,115,118,121,125,128,132,136,139,142,145,148,152,155,158,161,164,167,170,174,178,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","The description clearly states the skill's purpose (reducing LLM coding mistakes) and its use cases (writing, reviewing, refactoring code), along with actionable principles. It names the artifact (LLM code) and user intent (avoid mistakes).",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and provides trigger phrases within the character limit.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","The SKILL.md file is reasonably short and delegates longer procedural details or examples to separate files, adhering to progressive disclosure.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","The SKILL.md outlines the flow and principles, with detailed explanations and examples provided in the README.md, facilitating progressive disclosure.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","This skill provides guidelines and does not engage in deep code exploration or multi-file inspection that would necessitate a forked context.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","The README.md provides clear installation instructions and usage examples, including command-line invocations for both per-project CLAUDE.md and the Claude Code plugin.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","The guidelines acknowledge tradeoffs and limitations, advising users to use judgment for trivial tasks and stating the bias towards caution over speed, implicitly handling edge cases.",{"category":49,"check":50,"severity":39,"summary":51},"Code Execution","Tool Fallback","This skill does not reference external tools like MCP servers; it functions as a set of guidelines directly processed by the LLM.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","The guidelines implicitly encourage halting and reporting on unexpected states by emphasizing explicit assumptions and surfacing confusion before implementation, promoting a cautious approach.",{"category":57,"check":58,"severity":24,"summary":59},"Portability","Cross-skill coupling","The skill is self-contained and does not implicitly rely on other skills. It provides standalone guidelines.",{"category":42,"check":61,"severity":24,"summary":62},"Problem relevance","The description clearly names the problem of common LLM coding mistakes and the specific user intent of reducing them during code development.",{"category":42,"check":64,"severity":24,"summary":65},"Unique selling proposition","The skill offers a significant behavioral steer for LLMs by implementing specific principles derived from expert observations, providing value beyond generic prompting.",{"category":42,"check":67,"severity":24,"summary":68},"Production readiness","The guidelines are complete and directly address the stated use case of improving LLM coding practices, making them ready for real-world workflows.",{"category":70,"check":71,"severity":24,"summary":72},"Scope","Single responsibility principle","The skill focuses on a single domain: providing behavioral guidelines to improve LLM coding practices.",{"category":70,"check":74,"severity":24,"summary":75},"Description quality","The displayed description accurately and concisely reflects the skill's purpose of providing behavioral guidelines to reduce LLM coding mistakes.",{"category":22,"check":77,"severity":39,"summary":78},"Scoped tools","This skill does not expose tools or commands; it operates as a set of guidelines for LLM behavior.",{"category":30,"check":80,"severity":39,"summary":81},"Configuration & parameter reference","This skill does not have configurable parameters or options that require reference.",{"category":70,"check":83,"severity":39,"summary":84},"Tool naming","This skill does not expose user-facing tools or commands.",{"category":70,"check":86,"severity":39,"summary":87},"Minimal I/O surface","This skill does not expose tools or commands with parameter schemas or response shapes.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","The license is MIT, a permissive open-source license, and is clearly stated in both SKILL.md and README.md.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","The last commit was on April 20, 2026, which is within the last 90 days.",{"category":93,"check":97,"severity":39,"summary":98},"Dependency Management","The skill does not use any third-party dependencies.",{"category":100,"check":101,"severity":39,"summary":102},"Security","Secret Management","This skill does not handle or expose any secrets.",{"category":100,"check":104,"severity":24,"summary":105},"Injection","The skill provides guidelines and does not load or execute any external data as instructions, nor does it fetch remote content.",{"category":100,"check":107,"severity":24,"summary":108},"Transitive Supply-Chain Grenades","The skill does not load external files at runtime or fetch remote content; all guidelines are bundled.",{"category":100,"check":110,"severity":24,"summary":111},"Sandbox Isolation","This skill is purely informational and does not interact with the file system or execute code, thus posing no sandbox escape risk.",{"category":100,"check":113,"severity":24,"summary":114},"Sandbox escape primitives","As a purely informational skill, it does not contain any scripts or instructions that could facilitate sandbox escape.",{"category":100,"check":116,"severity":24,"summary":117},"Data Exfiltration","The skill does not perform any outbound calls or read confidential data.",{"category":100,"check":119,"severity":24,"summary":120},"Hidden Text Tricks","Bundled content is free of hidden-steering tricks, and descriptions use clean printable ASCII.",{"category":122,"check":123,"severity":24,"summary":124},"Hooks","Opaque code execution","The skill consists of plain-text markdown and does not involve obfuscated code, base64 payloads, or runtime script fetching.",{"category":57,"check":126,"severity":39,"summary":127},"Structural Assumption","The skill makes no assumptions about the user's project structure as it provides guidelines, not code that operates on project files.",{"category":129,"check":130,"severity":24,"summary":131},"Trust","Issues Attention","There are 0 open and 0 closed issues in the last 90 days, indicating no active issues requiring attention, which is a positive signal for a stable skill.",{"category":133,"check":134,"severity":24,"summary":135},"Versioning","Release Management","The `SKILL.md` frontmatter declares a `name` and `license`, and installation instructions reference `main` implicitly, but the code is recent and the project is popular, suggesting stability. The lack of explicit versioning is not a critical issue here.",{"category":49,"check":137,"severity":39,"summary":138},"Validation","This skill does not execute code or process structured input/output that requires schema validation.",{"category":100,"check":140,"severity":24,"summary":141},"Unguarded Destructive Operations","The skill is purely informational and does not contain any destructive operations.",{"category":49,"check":143,"severity":39,"summary":144},"Error Handling","This skill is informational and does not have error paths related to code execution.",{"category":49,"check":146,"severity":39,"summary":147},"Logging","This skill is read-only and informational, so local audit logging is not applicable.",{"category":149,"check":150,"severity":39,"summary":151},"Compliance","GDPR","The skill does not operate on personal data.",{"category":149,"check":153,"severity":24,"summary":154},"Target market","The skill provides general coding guidelines applicable globally, with no regional or jurisdictional restrictions.",{"category":57,"check":156,"severity":24,"summary":157},"Runtime stability","The skill is a markdown file providing guidelines, making it inherently stable and portable across different LLM environments.",{"category":30,"check":159,"severity":24,"summary":160},"README","The README.md clearly states the extension's purpose, providing installation instructions and detailed explanations of the guidelines.",{"category":70,"check":162,"severity":39,"summary":163},"Tool surface size","This is a single-tool extension (a set of guidelines) and does not expose multiple distinct tools or commands.",{"category":22,"check":165,"severity":39,"summary":166},"Overlapping near-synonym tools","This skill does not expose tools, so there are no overlapping near-synonym tools.",{"category":30,"check":168,"severity":24,"summary":169},"Phantom features","All features promised in the README and SKILL.md (guidelines for LLM coding mistakes) are directly implemented in the provided text.",{"category":171,"check":172,"severity":24,"summary":173},"Install","Installation instruction","The README.md provides clear, copy-pasteable installation instructions for both the Claude Code plugin and per-project CLAUDE.md.",{"category":175,"check":176,"severity":39,"summary":177},"Errors","Actionable error messages","This skill does not execute code and therefore has no error paths visible to the user.",{"category":179,"check":180,"severity":39,"summary":181},"Execution","Pinned dependencies","The skill has no third-party dependencies to pin.",{"category":70,"check":183,"severity":39,"summary":184},"Dry-run preview","This skill is purely informational and does not perform state-changing operations or send data outward.",{"category":186,"check":187,"severity":39,"summary":188},"Protocol","Idempotent retry & timeouts","This skill is purely informational and does not perform remote calls or state-changing operations.",{"category":149,"check":190,"severity":39,"summary":191},"Telemetry opt-in","This skill does not emit telemetry.",1778687179079,"This skill provides a set of behavioral guidelines derived from Andrej Karpathy's observations to help LLMs reduce common coding mistakes. It focuses on principles like thinking before coding, simplicity, surgical changes, and goal-driven execution.",[195,196,197,198,199],"Provides explicit principles for LLM code generation","Encourages stating assumptions and surfacing tradeoffs","Promotes simple, focused code without speculation","Ensures changes are surgical and limited to the task scope","Defines success criteria for verifiable execution",[201,202,203,204],"Automatically fixing all LLM coding mistakes","Replacing human oversight in the coding process","Providing project-specific coding standards","Performing code execution or validation itself","3.0.0","4.4.0","To improve the quality and reduce the common mistakes made by LLMs when writing, reviewing, or refactoring code.","The skill is exceptionally well-documented and robust, with a clear purpose and comprehensive usage instructions. The only minor point is the lack of explicit versioning in the frontmatter, which is mitigated by recent commits and project popularity.",99,"High-quality skill providing expert coding guidelines to improve LLM outputs.",[212,213,214,215,216],"llm","coding","guidelines","best-practices","developer-tools","global","verified",[220,221,222,223],"When writing new code to ensure adherence to best practices","During code reviews to identify potential LLM-induced mistakes","When refactoring code to maintain focus and avoid unnecessary changes","To guide LLM interactions for more predictable and high-quality code output",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"security":235,"testCoverage":236},{"hasLockfile":226},false,1778687155274,{"descriptionLength":229,"readmeSize":230},219,6198,{"closedIssues90d":8,"forks":232,"hasChangelog":226,"openIssues90d":8,"pushedAt":233,"stars":234},13000,1776679504000,128093,{"hasNpmPackage":226,"smitheryVerified":226},{"hasCi":226,"hasTests":226},{"updatedAt":238},1778687179355,{"basePath":240,"githubOwner":241,"githubRepo":242,"locale":18,"slug":13,"type":243},"skills/karpathy-guidelines","forrestchang","andrej-karpathy-skills","skill",{"_creationTime":245,"_id":246,"community":247,"display":248,"identity":251,"parentExtension":254,"providers":287,"relations":296,"tags":297,"workflow":298},1778687058458.6987,"k1739sx217s32es9e9p803xn1h86m6zv",{"reviewCount":8},{"description":249,"installMethods":250,"name":242,"sourceUrl":14},"Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls",{"claudeCode":242},{"basePath":252,"githubOwner":241,"githubRepo":242,"locale":18,"slug":242,"type":253},"","plugin",{"_creationTime":255,"_id":256,"community":257,"display":258,"identity":262,"providers":264,"relations":280,"tags":282,"workflow":283},1778687058458.6985,"k174fg5qph3f55akvm05r7ys2d86mxkh",{"reviewCount":8},{"description":259,"installMethods":260,"name":261,"sourceUrl":14},"Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations",{"claudeCode":12},"Karpathy-Inspired Claude Code Guidelines",{"basePath":252,"githubOwner":241,"githubRepo":242,"locale":18,"slug":242,"type":263},"marketplace",{"evaluate":265,"extract":272},{"promptVersionExtension":266,"promptVersionScoring":206,"score":267,"tags":268,"targetMarket":217,"tier":218},"3.1.0",98,[212,269,215,270,271],"coding-guidelines","claude-code","prompt-engineering",{"commitSha":273,"license":274,"marketplace":275,"plugin":278},"HEAD","MIT",{"name":276,"pluginCount":277},"karpathy-skills",1,{"mcpCount":8,"provider":279,"skillCount":8},"classify",{"repoId":281},"kd7awe12sdp9xgt83qhzh8se5186mz5x",[215,270,269,212,271],{"evaluatedAt":284,"extractAt":285,"updatedAt":286},1778687113381,1778687058458,1778687230040,{"evaluate":288,"extract":294},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":289,"targetMarket":217,"tier":218},[214,212,290,291,292,293],"coding-practices","refactoring","documentation","karpathy",{"commitSha":273,"license":274,"plugin":295},{"mcpCount":8,"provider":279,"skillCount":277},{"parentExtensionId":256,"repoId":281},[290,292,214,293,212,291],{"evaluatedAt":299,"extractAt":285,"updatedAt":300},1778687139483,1778687230225,{"evaluate":302,"extract":304},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":303,"targetMarket":217,"tier":218},[212,213,214,215,216],{"commitSha":273},{"parentExtensionId":246,"repoId":281},{"_creationTime":307,"_id":281,"identity":308,"providers":309,"workflow":344},1778687054482.7363,{"githubOwner":241,"githubRepo":242,"sourceUrl":14},{"classify":310,"discover":338,"github":341},{"commitSha":273,"extensions":311},[312,322,332],{"basePath":252,"description":259,"displayName":276,"installMethods":313,"rationale":314,"selectedPaths":315,"source":321,"sourceLanguage":18,"type":263},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[316,319],{"path":317,"priority":318},".claude-plugin/marketplace.json","mandatory",{"path":320,"priority":318},"README.md","rule",{"basePath":252,"description":249,"displayName":242,"installMethods":323,"license":274,"rationale":324,"selectedPaths":325,"source":321,"sourceLanguage":18,"type":253},{"claudeCode":242},"plugin manifest at .claude-plugin/plugin.json",[326,328,329],{"path":327,"priority":318},".claude-plugin/plugin.json",{"path":320,"priority":318},{"path":330,"priority":331},"skills/karpathy-guidelines/SKILL.md","medium",{"basePath":240,"description":10,"displayName":13,"installMethods":333,"rationale":334,"selectedPaths":335,"source":321,"sourceLanguage":18,"type":243},{"claudeCode":12},"SKILL.md frontmatter at skills/karpathy-guidelines/SKILL.md",[336],{"path":337,"priority":318},"SKILL.md",{"sources":339},[340],"manual",{"closedIssues90d":8,"description":342,"forks":232,"openIssues90d":8,"pushedAt":233,"readmeSize":230,"stars":234,"topics":343},"A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.",[],{"classifiedAt":345,"discoverAt":346,"extractAt":347,"githubAt":347,"updatedAt":345},1778687058299,1778687054482,1778687056438,[215,213,216,214,212],{"evaluatedAt":238,"extractAt":285,"updatedAt":350},1778687229859,[],[353,379,408,435,463,491],{"_creationTime":354,"_id":355,"community":356,"display":357,"identity":363,"providers":367,"relations":373,"tags":375,"workflow":376},1778696691708.28,"k17463tm33jcn3fnx5vvmmfmh586mxhb",{"reviewCount":8},{"description":358,"installMethods":359,"name":361,"sourceUrl":362},"Agent skill for coder - invoke with $agent-coder",{"claudeCode":360},"ruvnet/ruflo","agent-coder","https://github.com/ruvnet/ruflo",{"basePath":364,"githubOwner":365,"githubRepo":366,"locale":18,"slug":361,"type":243},".agents/skills/agent-coder","ruvnet","ruflo",{"evaluate":368,"extract":372},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":369,"targetMarket":217,"tier":218},[213,370,291,371,215],"development","optimization",{"commitSha":273},{"repoId":374},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[215,213,370,371,291],{"evaluatedAt":377,"extractAt":378,"updatedAt":377},1778697523416,1778696691708,{"_creationTime":380,"_id":381,"community":382,"display":383,"identity":389,"providers":393,"relations":401,"tags":403,"workflow":404},1778694510092.8093,"k1739tdkkxjmmx9m9gk67e8s5986me1q",{"reviewCount":8},{"description":384,"installMethods":385,"name":387,"sourceUrl":388},"Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.",{"claudeCode":386},"neondatabase/agent-skills","neon-postgres","https://github.com/neondatabase/agent-skills",{"basePath":390,"githubOwner":391,"githubRepo":392,"locale":18,"slug":387,"type":243},"skills/neon-postgres","neondatabase","agent-skills",{"evaluate":394,"extract":400},{"promptVersionExtension":205,"promptVersionScoring":206,"score":395,"tags":396,"targetMarket":217,"tier":218},100,[397,398,399,292,215],"postgres","neon","database",{"commitSha":273},{"repoId":402},"kd7fnpnf2z4z7frgbq47jwrzzh86nx09",[215,399,292,398,397],{"evaluatedAt":405,"extractAt":406,"updatedAt":407},1778694576976,1778694510092,1778694671737,{"_creationTime":409,"_id":410,"community":411,"display":412,"identity":418,"providers":422,"relations":429,"tags":431,"workflow":432},1778691705439.1682,"k17d64c6cje0qa1sp2r2wn4pzx86mv9p",{"reviewCount":8},{"description":413,"installMethods":414,"name":416,"sourceUrl":417},"Design SDKs that developers love to use—APIs that feel native, error messages that guide, and experiences that reduce friction. This skill covers creating SDKs that drive adoption through exceptional developer experience rather than aggressive marketing.\n\nTrigger phrases: \"SDK design\", \"developer experience\", \"API design\", \"SDK DX\", \"error messages\", \"type safety\", \"IDE integration\", \"SDK versioning\", \"migration guides\", \"client library design\", \"making SDKs feel native\", \"SDK best practices\"\n",{"claudeCode":415},"jonathimer/devmarketing-skills","sdk-dx","https://github.com/jonathimer/devmarketing-skills",{"basePath":419,"githubOwner":420,"githubRepo":421,"locale":18,"slug":416,"type":243},"skills/sdk-dx","jonathimer","devmarketing-skills",{"evaluate":423,"extract":428},{"promptVersionExtension":205,"promptVersionScoring":206,"score":395,"tags":424,"targetMarket":217,"tier":218},[425,426,427,292,215],"sdk","developer-experience","api-design",{"commitSha":273},{"repoId":430},"kd74f65yh7zvhb9s83jpzx33cd86nd64",[427,215,426,292,425],{"evaluatedAt":433,"extractAt":434,"updatedAt":433},1778692521720,1778691705439,{"_creationTime":436,"_id":437,"community":438,"display":439,"identity":445,"providers":449,"relations":457,"tags":459,"workflow":460},1778687399826.03,"k17aw44qv21pmpr9yh96rknat986n6md",{"reviewCount":8},{"description":440,"installMethods":441,"name":443,"sourceUrl":444},"Get best practices for C# async programming",{"claudeCode":442},"github/awesome-copilot","csharp-async","https://github.com/github/awesome-copilot",{"basePath":446,"githubOwner":447,"githubRepo":448,"locale":18,"slug":443,"type":243},"skills/csharp-async","github","awesome-copilot",{"evaluate":450,"extract":456},{"promptVersionExtension":205,"promptVersionScoring":206,"score":395,"tags":451,"targetMarket":217,"tier":218},[452,453,454,215,455],"csharp","async","programming","developer-tooling",{"commitSha":273},{"repoId":458},"kd7dsmv976w8rtkqnjjfdtfgks86nnmw",[453,215,452,455,454],{"evaluatedAt":461,"extractAt":462,"updatedAt":461},1778689742883,1778687399826,{"_creationTime":464,"_id":465,"community":466,"display":467,"identity":473,"providers":477,"relations":485,"tags":487,"workflow":488},1778687029453.9026,"k1730ev9b9mj0r91y1b46f4nhs86ngc2",{"reviewCount":8},{"description":468,"installMethods":469,"name":471,"sourceUrl":472},"Best practices for using `expect` and `package:matcher`.\nFocuses on readable assertions, proper matcher selection, and avoiding\ncommon pitfalls.",{"claudeCode":470},"flutter/skills","dart-matcher-best-practices","https://github.com/flutter/skills",{"basePath":474,"githubOwner":475,"githubRepo":476,"locale":18,"slug":471,"type":243},"tool/dart_skills_lint/.agents/skills/dart-matcher-best-practices","flutter","skills",{"evaluate":478,"extract":484},{"promptVersionExtension":205,"promptVersionScoring":206,"score":395,"tags":479,"targetMarket":217,"tier":218},[480,481,482,483,215],"dart","testing","matcher","assertions",{"commitSha":273},{"repoId":486},"kd7100bqmd3gmqn2rdf4t72qqn86nfdd",[483,215,480,482,481],{"evaluatedAt":489,"extractAt":490,"updatedAt":489},1778687418456,1778687029453,{"_creationTime":492,"_id":493,"community":494,"display":495,"identity":501,"providers":506,"relations":513,"tags":515,"workflow":516},1778683190010.2546,"k1769whm3ctfxq1z708j6w3cp986n35n",{"reviewCount":8},{"description":496,"installMethods":497,"name":499,"sourceUrl":500},"Go concurrency patterns for production services: context cancellation, errgroup, worker pools, bounded parallelism, fan-in/fan-out, and common race/deadlock pitfalls",{"claudeCode":498},"bobmatnyc/claude-mpm-skills","golang-concurrency-patterns","https://github.com/bobmatnyc/claude-mpm-skills",{"basePath":502,"githubOwner":503,"githubRepo":504,"locale":18,"slug":505,"type":243},"toolchains/golang/concurrency","bobmatnyc","claude-mpm-skills","concurrency",{"evaluate":507,"extract":512},{"promptVersionExtension":205,"promptVersionScoring":206,"score":395,"tags":508,"targetMarket":217,"tier":218},[509,505,510,511,215],"golang","patterns","production",{"commitSha":273},{"repoId":514},"kd72g55e5qeqs90bk1bvkt8wbx86nkn3",[215,505,509,510,511],{"evaluatedAt":517,"extractAt":518,"updatedAt":517},1778683530961,1778683190010]