[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mattpocock-write-a-skill-en":3,"guides-for-mattpocock-write-a-skill":579,"similar-k17f8b769y9swjcqb91vq74zy986n2wf-en":580},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":240,"isFallback":224,"parentExtension":245,"providers":278,"relations":282,"repo":283,"tags":577,"workflow":578},1778692846401.1536,"k17f8b769y9swjcqb91vq74zy986n2wf",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.",{"claudeCode":12},"mattpocock/skills","write-a-skill","https://github.com/mattpocock/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":222,"workflow":238},1778693512400.8457,"kn76n6493f6ebs71eg5yvbvpe186ngqd","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":216,"tier":217,"useCases":218},[21,26,29,33,37,41,45,48,52,56,60,63,66,69,73,76,79,82,85,88,92,96,99,103,106,109,112,115,118,121,125,128,132,136,140,143,147,150,154,157,160,163,166,169,172,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","The description clearly states that the skill creates new agent skills and specifies the use case 'when user wants to create, write, or build a new skill', providing a precise and actionable purpose.",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","The frontmatter (name and description) is concise, self-contained, and clearly communicates the core capability and triggers within a reasonable character limit.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","The SKILL.md content is well under 500 lines and delegates deeper material to separate files like REFERENCE.md and EXAMPLES.md, adhering to progressive disclosure.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","The SKILL.md outlines the skill creation process and links to separate files for detailed documentation, adhering to progressive disclosure principles.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","This skill is about creating skills and does not involve deep exploration or code review that would necessitate forked exploration.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","The SKILL.md includes a clear template for a minimal working example and the README provides conceptual examples of skill usage, sufficient for understanding.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","The SKILL.md discusses when to split files and when to add scripts, implicitly covering limitations and recovery steps for the skill development process.",{"category":49,"check":50,"severity":39,"summary":51},"Code Execution","Tool Fallback","This skill does not appear to rely on external tools like MCP servers; it is self-contained and does not require fallbacks.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","The SKILL.md includes a 'Review Checklist' with items like 'No time-sensitive info' and 'Consistent terminology', implying a halt on unexpected or inconsistent states before proceeding.",{"category":57,"check":58,"severity":24,"summary":59},"Portability","Cross-skill coupling","The skill is standalone and focused on skill creation, without implicit reliance on other skills. It does not handle adjacent tasks that would require cross-linking.",{"category":42,"check":61,"severity":24,"summary":62},"Problem relevance","The description clearly states the problem of creating new agent skills and provides specific use cases for when the skill should be utilized.",{"category":42,"check":64,"severity":24,"summary":65},"Unique selling proposition","The skill offers a structured approach to skill creation, including best practices for documentation and resource bundling, providing value beyond basic LLM generation.",{"category":42,"check":67,"severity":24,"summary":68},"Production readiness","The skill provides a complete framework and guidance for creating new agent skills, covering requirements gathering, drafting, and review, making it ready for workflow integration.",{"category":70,"check":71,"severity":24,"summary":72},"Scope","Single responsibility principle","The skill is focused solely on the process of creating new agent skills, with no unrelated capabilities or extension into adjacent domains.",{"category":70,"check":74,"severity":24,"summary":75},"Description quality","The displayed description accurately reflects the skill's purpose of creating new agent skills with proper structure and bundled resources.",{"category":22,"check":77,"severity":39,"summary":78},"Scoped tools","This skill does not expose individual tools; it is a monolithic skill that guides the user through a process.",{"category":30,"check":80,"severity":39,"summary":81},"Configuration & parameter reference","The skill does not have configurable parameters or options that require documentation beyond the general process described.",{"category":70,"check":83,"severity":39,"summary":84},"Tool naming","This skill does not expose individual tools with names; it operates as a single unit.",{"category":70,"check":86,"severity":39,"summary":87},"Minimal I/O surface","As this skill guides a user through a process and does not expose distinct tools with input/output schemas, this check is not applicable.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","The MIT license is clearly provided in a LICENSE file, which is a permissive open-source license, making it usable for redistribution.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","The last commit was on 2026-05-13, which is within the last 3 months, indicating the project is actively maintained.",{"category":93,"check":97,"severity":39,"summary":98},"Dependency Management","The skill does not appear to have any third-party dependencies that would require active management or updating.",{"category":100,"check":101,"severity":39,"summary":102},"Security","Secret Management","The skill does not handle or expose any secrets, as it focuses on guiding the user through the process of creating skills.",{"category":100,"check":104,"severity":24,"summary":105},"Injection","The skill's instructions and bundled content do not appear to load or execute external, untrusted data, and no third-party data loading is present.",{"category":100,"check":107,"severity":24,"summary":108},"Transitive Supply-Chain Grenades","The skill does not load external files at runtime or use remote pipes to shell, keeping all content within the committed bundle.",{"category":100,"check":110,"severity":24,"summary":111},"Sandbox Isolation","The skill guides a user through a process and does not interact with the file system or execute commands that could escape the sandbox.",{"category":100,"check":113,"severity":24,"summary":114},"Sandbox escape primitives","No detached processes or deny-retry loops were found in the skill's logic.",{"category":100,"check":116,"severity":24,"summary":117},"Data Exfiltration","The skill does not handle or transmit any confidential data. It focuses on guiding the user's process.",{"category":100,"check":119,"severity":24,"summary":120},"Hidden Text Tricks","The bundled content is free of hidden-steering tricks, and all descriptions use clean printable ASCII.",{"category":122,"check":123,"severity":24,"summary":124},"Hooks","Opaque code execution","The skill's content is plain, readable markdown and does not involve obfuscated code, base64 payloads, or runtime script fetching.",{"category":57,"check":126,"severity":24,"summary":127},"Structural Assumption","The skill guides the user through creating a skill structure and does not make assumptions about the user's project organization outside the skill bundle.",{"category":129,"check":130,"severity":24,"summary":131},"Trust","Issues Attention","The repository has a high closure rate of open issues (117 closed vs. 27 open in 90 days), indicating good maintainer engagement.",{"category":133,"check":134,"severity":24,"summary":135},"Versioning","Release Management","The project has a meaningful semver versioning scheme indicated by the `pushedAt` date and active commits, and the installation instructions do not default to `main`.",{"category":137,"check":138,"severity":39,"summary":139},"Execution","Validation","The skill's primary function is guiding a user through a documentation-based process and does not involve executable code or structured output that requires schema validation.",{"category":100,"check":141,"severity":39,"summary":142},"Unguarded Destructive Operations","This skill does not perform any destructive operations; it is a guidance and documentation tool.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Error Handling","The skill guides the user on how to handle errors and edge cases during skill development, implying a robust error handling approach within the process it describes.",{"category":49,"check":148,"severity":39,"summary":149},"Logging","As the skill is purely instructional and does not perform actions with side effects or outbound calls, logging is not applicable.",{"category":151,"check":152,"severity":39,"summary":153},"Compliance","GDPR","The skill does not operate on personal data; it guides the user in creating skill structures.",{"category":151,"check":155,"severity":24,"summary":156},"Target market","The extension operates on general software engineering principles and skill creation, with no regional or jurisdictional logic detected; targetMarket is 'global'.",{"category":57,"check":158,"severity":24,"summary":159},"Runtime stability","The skill is written in markdown and relies on the agent's runtime environment, with no assumptions about specific OS, shells, or editors.",{"category":30,"check":161,"severity":24,"summary":162},"README","The README file exists, is comprehensive, and clearly states the extension's purpose and value proposition.",{"category":70,"check":164,"severity":39,"summary":165},"Tool surface size","This is a single monolithic skill, not a collection of tools, so tool surface size is not applicable.",{"category":22,"check":167,"severity":39,"summary":168},"Overlapping near-synonym tools","As this skill does not expose multiple tools, there are no near-synonym tools to evaluate.",{"category":30,"check":170,"severity":24,"summary":171},"Phantom features","All features advertised in the README and SKILL.md, such as structured skill creation and progressive disclosure, have corresponding implementations and guidance.",{"category":173,"check":174,"severity":24,"summary":175},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions and a quickstart setup process with agent integration.",{"category":144,"check":177,"severity":24,"summary":178},"Actionable error messages","The SKILL.md guides the user on handling potential issues during skill creation and lists review checklist items, implicitly covering actionable error reporting.",{"category":137,"check":180,"severity":39,"summary":181},"Pinned dependencies","The skill does not utilize third-party dependencies or scripts that require pinning.",{"category":70,"check":183,"severity":39,"summary":184},"Dry-run preview","This skill is instructional and does not perform any state-changing operations or outbound calls that would require a dry-run preview.",{"category":186,"check":187,"severity":39,"summary":188},"Protocol","Idempotent retry & timeouts","The skill does not make remote calls or perform state-changing operations, thus retry logic and timeouts are not applicable.",{"category":151,"check":190,"severity":39,"summary":191},"Telemetry opt-in","The skill does not emit any telemetry.",1778693512268,"This skill provides a structured process and guidance for creating new agent skills, covering requirements gathering, drafting SKILL.md, and review. It includes templates for skill structure and frontmatter, as well as advice on when to use scripts or split files.",[195,196,197,198,199],"Structured process for skill creation","Guidance on SKILL.md and frontmatter requirements","Best practices for bundling resources","Advice on splitting files and using scripts","Review checklist for skill quality",[201,202,203],"Developing skills for specific domains without general applicability.","Providing a fully automated skill generation service without user input.","Handling the execution of skills, only their creation.","3.0.0","4.4.0","To enable users to create new agent skills with proper structure, progressive disclosure, and bundled resources, ensuring clarity and usability.","The extension is fully compliant with all checks, demonstrating excellent documentation, a clear purpose, and robust practices.",100,"A comprehensive and well-documented skill for creating new agent skills.",[211,212,213,214,215],"skill-creation","agent-development","documentation","prompt-engineering","productivity","global","verified",[219,220,221],"When a user wants to create a new agent skill.","When a user needs to write or build a new skill.","When a user wants to understand the best practices for agent skill development.",{"codeQuality":223,"collectedAt":225,"documentation":226,"maintenance":229,"security":235,"testCoverage":237},{"hasLockfile":224},false,1778693497726,{"descriptionLength":227,"readmeSize":228},153,11516,{"closedIssues90d":230,"forks":231,"hasChangelog":224,"openIssues90d":232,"pushedAt":233,"stars":234},117,6767,27,1778677522000,78489,{"hasNpmPackage":224,"license":236,"smitheryVerified":224},"MIT",{"hasCi":224,"hasTests":224},{"updatedAt":239},1778693512400,{"basePath":241,"githubOwner":242,"githubRepo":243,"locale":18,"slug":13,"type":244},"skills/productivity/write-a-skill","mattpocock","skills","skill",{"_creationTime":246,"_id":247,"community":248,"display":249,"identity":253,"parentExtension":256,"providers":257,"relations":272,"tags":274,"workflow":275},1778692846401.1467,"k171mc92f05dc4v6jzgf6bng7d86mr9t",{"reviewCount":8},{"description":250,"installMethods":251,"name":252,"sourceUrl":14},"Skills for Real Engineers. Straight from my .claude directory.",{"claudeCode":252},"mattpocock-skills",{"basePath":254,"githubOwner":242,"githubRepo":243,"locale":18,"slug":243,"type":255},"","plugin",null,{"evaluate":258,"extract":267},{"promptVersionExtension":204,"promptVersionScoring":205,"score":259,"tags":260,"targetMarket":216,"tier":266},79,[261,215,262,263,264,265],"engineering","ai-tools","developer-tools","code-quality","refactoring","community",{"commitSha":268,"plugin":269},"HEAD",{"mcpCount":8,"provider":270,"skillCount":271},"classify",14,{"repoId":273},"kd70nm2vazehgqc4j28ve6cwv986mv1s",[262,264,263,261,215,265],{"evaluatedAt":276,"extractAt":277,"updatedAt":276},1778692867921,1778692846401,{"evaluate":279,"extract":281},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":280,"targetMarket":216,"tier":217},[211,212,213,214,215],{"commitSha":268},{"parentExtensionId":247,"repoId":273},{"_creationTime":284,"_id":273,"identity":285,"providers":286,"workflow":573},1778692842371.0967,{"githubOwner":242,"githubRepo":243,"sourceUrl":14},{"classify":287,"discover":568,"github":571},{"commitSha":268,"extensions":288},[289,302,311,319,327,335,346,359,373,385,403,421,429,437,449,457,465,473,481,489,499,507,515,523,531,539,547,555,563],{"basePath":254,"displayName":252,"installMethods":290,"rationale":291,"selectedPaths":292,"source":301,"sourceLanguage":18,"type":255},{"claudeCode":252},"plugin manifest at .claude-plugin/plugin.json",[293,296,298],{"path":294,"priority":295},".claude-plugin/plugin.json","mandatory",{"path":297,"priority":295},"README.md",{"path":299,"priority":300},"LICENSE","high","rule",{"basePath":303,"description":304,"displayName":305,"installMethods":306,"rationale":307,"selectedPaths":308,"source":301,"sourceLanguage":18,"type":244},"skills/deprecated/design-an-interface","Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions \"design it twice\".","design-an-interface",{"claudeCode":12},"SKILL.md frontmatter at skills/deprecated/design-an-interface/SKILL.md",[309],{"path":310,"priority":295},"SKILL.md",{"basePath":312,"description":313,"displayName":314,"installMethods":315,"rationale":316,"selectedPaths":317,"source":301,"sourceLanguage":18,"type":244},"skills/deprecated/qa","Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions \"QA session\".","qa",{"claudeCode":12},"SKILL.md frontmatter at skills/deprecated/qa/SKILL.md",[318],{"path":310,"priority":295},{"basePath":320,"description":321,"displayName":322,"installMethods":323,"rationale":324,"selectedPaths":325,"source":301,"sourceLanguage":18,"type":244},"skills/deprecated/request-refactor-plan","Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.","request-refactor-plan",{"claudeCode":12},"SKILL.md frontmatter at skills/deprecated/request-refactor-plan/SKILL.md",[326],{"path":310,"priority":295},{"basePath":328,"description":329,"displayName":330,"installMethods":331,"rationale":332,"selectedPaths":333,"source":301,"sourceLanguage":18,"type":244},"skills/deprecated/ubiquitous-language","Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions \"domain model\" or \"DDD\".","ubiquitous-language",{"claudeCode":12},"SKILL.md frontmatter at skills/deprecated/ubiquitous-language/SKILL.md",[334],{"path":310,"priority":295},{"basePath":336,"description":337,"displayName":338,"installMethods":339,"rationale":340,"selectedPaths":341,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/diagnose","Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says \"diagnose this\" / \"debug this\", reports a bug, says something is broken/throwing/failing, or describes a performance regression.","diagnose",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/diagnose/SKILL.md",[342,343],{"path":310,"priority":295},{"path":344,"priority":345},"scripts/hitl-loop.template.sh","low",{"basePath":347,"description":348,"displayName":349,"installMethods":350,"rationale":351,"selectedPaths":352,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/grill-with-docs","Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.","grill-with-docs",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/grill-with-docs/SKILL.md",[353,354,357],{"path":310,"priority":295},{"path":355,"priority":356},"ADR-FORMAT.md","medium",{"path":358,"priority":356},"CONTEXT-FORMAT.md",{"basePath":360,"description":361,"displayName":362,"installMethods":363,"rationale":364,"selectedPaths":365,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/improve-codebase-architecture","Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.","improve-codebase-architecture",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/improve-codebase-architecture/SKILL.md",[366,367,369,371],{"path":310,"priority":295},{"path":368,"priority":356},"DEEPENING.md",{"path":370,"priority":356},"INTERFACE-DESIGN.md",{"path":372,"priority":356},"LANGUAGE.md",{"basePath":374,"description":375,"displayName":376,"installMethods":377,"rationale":378,"selectedPaths":379,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/prototype","Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says \"prototype this\", \"let me play with it\", \"try a few designs\".","prototype",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/prototype/SKILL.md",[380,381,383],{"path":310,"priority":295},{"path":382,"priority":356},"LOGIC.md",{"path":384,"priority":356},"UI.md",{"basePath":386,"description":387,"displayName":388,"installMethods":389,"rationale":390,"selectedPaths":391,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/setup-matt-pocock-skills","Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.","setup-matt-pocock-skills",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/setup-matt-pocock-skills/SKILL.md",[392,393,395,397,399,401],{"path":310,"priority":295},{"path":394,"priority":356},"domain.md",{"path":396,"priority":356},"issue-tracker-github.md",{"path":398,"priority":356},"issue-tracker-gitlab.md",{"path":400,"priority":356},"issue-tracker-local.md",{"path":402,"priority":356},"triage-labels.md",{"basePath":404,"description":405,"displayName":406,"installMethods":407,"rationale":408,"selectedPaths":409,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/tdd","Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions \"red-green-refactor\", wants integration tests, or asks for test-first development.","tdd",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/tdd/SKILL.md",[410,411,413,415,417,419],{"path":310,"priority":295},{"path":412,"priority":356},"deep-modules.md",{"path":414,"priority":356},"interface-design.md",{"path":416,"priority":356},"mocking.md",{"path":418,"priority":356},"refactoring.md",{"path":420,"priority":356},"tests.md",{"basePath":422,"description":423,"displayName":424,"installMethods":425,"rationale":426,"selectedPaths":427,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/to-issues","Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.","to-issues",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/to-issues/SKILL.md",[428],{"path":310,"priority":295},{"basePath":430,"description":431,"displayName":432,"installMethods":433,"rationale":434,"selectedPaths":435,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/to-prd","Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.","to-prd",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/to-prd/SKILL.md",[436],{"path":310,"priority":295},{"basePath":438,"description":439,"displayName":440,"installMethods":441,"rationale":442,"selectedPaths":443,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/triage","Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.","triage",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/triage/SKILL.md",[444,445,447],{"path":310,"priority":295},{"path":446,"priority":356},"AGENT-BRIEF.md",{"path":448,"priority":356},"OUT-OF-SCOPE.md",{"basePath":450,"description":451,"displayName":452,"installMethods":453,"rationale":454,"selectedPaths":455,"source":301,"sourceLanguage":18,"type":244},"skills/engineering/zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","zoom-out",{"claudeCode":12},"SKILL.md frontmatter at skills/engineering/zoom-out/SKILL.md",[456],{"path":310,"priority":295},{"basePath":458,"description":459,"displayName":460,"installMethods":461,"rationale":462,"selectedPaths":463,"source":301,"sourceLanguage":18,"type":244},"skills/in-progress/review","Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".","review",{"claudeCode":12},"SKILL.md frontmatter at skills/in-progress/review/SKILL.md",[464],{"path":310,"priority":295},{"basePath":466,"description":467,"displayName":468,"installMethods":469,"rationale":470,"selectedPaths":471,"source":301,"sourceLanguage":18,"type":244},"skills/in-progress/writing-beats","Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.","writing-beats",{"claudeCode":12},"SKILL.md frontmatter at skills/in-progress/writing-beats/SKILL.md",[472],{"path":310,"priority":295},{"basePath":474,"description":475,"displayName":476,"installMethods":477,"rationale":478,"selectedPaths":479,"source":301,"sourceLanguage":18,"type":244},"skills/in-progress/writing-fragments","Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions \"fragments\", \"ideate\", or \"raw material\" for writing.","writing-fragments",{"claudeCode":12},"SKILL.md frontmatter at skills/in-progress/writing-fragments/SKILL.md",[480],{"path":310,"priority":295},{"basePath":482,"description":483,"displayName":484,"installMethods":485,"rationale":486,"selectedPaths":487,"source":301,"sourceLanguage":18,"type":244},"skills/in-progress/writing-shape","Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.","writing-shape",{"claudeCode":12},"SKILL.md frontmatter at skills/in-progress/writing-shape/SKILL.md",[488],{"path":310,"priority":295},{"basePath":490,"description":491,"displayName":492,"installMethods":493,"rationale":494,"selectedPaths":495,"source":301,"sourceLanguage":18,"type":244},"skills/misc/git-guardrails-claude-code","Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.","git-guardrails-claude-code",{"claudeCode":12},"SKILL.md frontmatter at skills/misc/git-guardrails-claude-code/SKILL.md",[496,497],{"path":310,"priority":295},{"path":498,"priority":345},"scripts/block-dangerous-git.sh",{"basePath":500,"description":501,"displayName":502,"installMethods":503,"rationale":504,"selectedPaths":505,"source":301,"sourceLanguage":18,"type":244},"skills/misc/migrate-to-shoehorn","Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.","migrate-to-shoehorn",{"claudeCode":12},"SKILL.md frontmatter at skills/misc/migrate-to-shoehorn/SKILL.md",[506],{"path":310,"priority":295},{"basePath":508,"description":509,"displayName":510,"installMethods":511,"rationale":512,"selectedPaths":513,"source":301,"sourceLanguage":18,"type":244},"skills/misc/scaffold-exercises","Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.","scaffold-exercises",{"claudeCode":12},"SKILL.md frontmatter at skills/misc/scaffold-exercises/SKILL.md",[514],{"path":310,"priority":295},{"basePath":516,"description":517,"displayName":518,"installMethods":519,"rationale":520,"selectedPaths":521,"source":301,"sourceLanguage":18,"type":244},"skills/misc/setup-pre-commit","Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.","setup-pre-commit",{"claudeCode":12},"SKILL.md frontmatter at skills/misc/setup-pre-commit/SKILL.md",[522],{"path":310,"priority":295},{"basePath":524,"description":525,"displayName":526,"installMethods":527,"rationale":528,"selectedPaths":529,"source":301,"sourceLanguage":18,"type":244},"skills/personal/edit-article","Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.","edit-article",{"claudeCode":12},"SKILL.md frontmatter at skills/personal/edit-article/SKILL.md",[530],{"path":310,"priority":295},{"basePath":532,"description":533,"displayName":534,"installMethods":535,"rationale":536,"selectedPaths":537,"source":301,"sourceLanguage":18,"type":244},"skills/personal/obsidian-vault","Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.","obsidian-vault",{"claudeCode":12},"SKILL.md frontmatter at skills/personal/obsidian-vault/SKILL.md",[538],{"path":310,"priority":295},{"basePath":540,"description":541,"displayName":542,"installMethods":543,"rationale":544,"selectedPaths":545,"source":301,"sourceLanguage":18,"type":244},"skills/productivity/caveman","Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes /caveman.\n","caveman",{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/caveman/SKILL.md",[546],{"path":310,"priority":295},{"basePath":548,"description":549,"displayName":550,"installMethods":551,"rationale":552,"selectedPaths":553,"source":301,"sourceLanguage":18,"type":244},"skills/productivity/grill-me","Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions \"grill me\".","grill-me",{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/grill-me/SKILL.md",[554],{"path":310,"priority":295},{"basePath":556,"description":557,"displayName":558,"installMethods":559,"rationale":560,"selectedPaths":561,"source":301,"sourceLanguage":18,"type":244},"skills/productivity/handoff","Compact the current conversation into a handoff document for another agent to pick up.","handoff",{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/handoff/SKILL.md",[562],{"path":310,"priority":295},{"basePath":241,"description":10,"displayName":13,"installMethods":564,"rationale":565,"selectedPaths":566,"source":301,"sourceLanguage":18,"type":244},{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/write-a-skill/SKILL.md",[567],{"path":310,"priority":295},{"sources":569},[570],"manual",{"closedIssues90d":230,"description":250,"forks":231,"license":236,"openIssues90d":232,"pushedAt":233,"readmeSize":228,"stars":234,"topics":572},[],{"classifiedAt":574,"discoverAt":575,"extractAt":576,"githubAt":576,"updatedAt":574},1778692846116,1778692842371,1778692844195,[212,213,215,214,211],{"evaluatedAt":239,"extractAt":277,"updatedAt":239},[],[581,609,637,657,679,698],{"_creationTime":582,"_id":583,"community":584,"display":585,"identity":591,"providers":595,"relations":602,"tags":605,"workflow":606},1778694480889.9487,"k17eg219cke0p45yfhh8n2t37986mgm4",{"reviewCount":8},{"description":586,"installMethods":587,"name":589,"sourceUrl":590},"Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration",{"claudeCode":588},"NeoLabHQ/context-engineering-kit","create-command","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":592,"githubOwner":593,"githubRepo":594,"locale":18,"slug":589,"type":244},"plugins/customaize-agent/skills/create-command","NeoLabHQ","context-engineering-kit",{"evaluate":596,"extract":601},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":597,"targetMarket":216,"tier":217},[598,212,214,599,600],"command-creation","mcp","claude-code",{"commitSha":268},{"parentExtensionId":603,"repoId":604},"k173g0c46wghgz5j9gn02wfydn86mkh8","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[212,600,598,599,214],{"evaluatedAt":607,"extractAt":608,"updatedAt":607},1778694773368,1778694480890,{"_creationTime":610,"_id":611,"community":612,"display":613,"identity":619,"providers":624,"relations":631,"tags":633,"workflow":634},1778697652123.898,"k1771s1snb8n9ktrpx9nm64pfh86ncfq",{"reviewCount":8},{"description":614,"installMethods":615,"name":617,"sourceUrl":618},"Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.",{"claudeCode":616},"steipete/clawdis","Skill Creator","https://github.com/steipete/clawdis",{"basePath":620,"githubOwner":621,"githubRepo":622,"locale":18,"slug":623,"type":244},"skills/skill-creator","steipete","clawdis","skill-creator",{"evaluate":625,"extract":630},{"promptVersionExtension":204,"promptVersionScoring":205,"score":626,"tags":627,"targetMarket":216,"tier":217},99,[212,211,628,213,629],"cli","python",{"commitSha":268,"license":236},{"repoId":632},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[212,628,213,629,211],{"evaluatedAt":635,"extractAt":636,"updatedAt":635},1778698929193,1778697652123,{"_creationTime":638,"_id":639,"community":640,"display":641,"identity":645,"providers":647,"relations":653,"tags":654,"workflow":655},1778694480889.9482,"k17ema0c4d9s4vbz79kv6m7pv186m97n",{"reviewCount":8},{"description":642,"installMethods":643,"name":644,"sourceUrl":590},"Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.",{"claudeCode":588},"context-engineering",{"basePath":646,"githubOwner":593,"githubRepo":594,"locale":18,"slug":644,"type":244},"plugins/customaize-agent/skills/context-engineering",{"evaluate":648,"extract":652},{"promptVersionExtension":204,"promptVersionScoring":205,"score":626,"tags":649,"targetMarket":216,"tier":217},[650,214,212,651,213],"context","llm",{"commitSha":268},{"parentExtensionId":603,"repoId":604},[212,650,213,651,214],{"evaluatedAt":656,"extractAt":608,"updatedAt":656},1778694738332,{"_creationTime":658,"_id":659,"community":660,"display":661,"identity":665,"providers":668,"relations":675,"tags":676,"workflow":677},1778694480889.9478,"k17eax901dfknza161zyet9ajd86ne2g",{"reviewCount":8},{"description":662,"installMethods":663,"name":664,"sourceUrl":590},"Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.",{"claudeCode":588},"Agent Evaluation",{"basePath":666,"githubOwner":593,"githubRepo":594,"locale":18,"slug":667,"type":244},"plugins/customaize-agent/skills/agent-evaluation","agent-evaluation",{"evaluate":669,"extract":673},{"promptVersionExtension":204,"promptVersionScoring":205,"score":626,"tags":670,"targetMarket":216,"tier":217},[671,651,672,214,212],"evaluation","testing",{"commitSha":268,"license":674},"GPL-3.0",{"parentExtensionId":603,"repoId":604},[212,671,651,214,672],{"evaluatedAt":678,"extractAt":608,"updatedAt":678},1778694704866,{"_creationTime":680,"_id":681,"community":682,"display":683,"identity":687,"providers":689,"relations":694,"tags":695,"workflow":696},1778694480889.9492,"k1727c6jd7tf7e9ze8ys8geyg586mw3y",{"reviewCount":8},{"description":684,"installMethods":685,"name":686,"sourceUrl":590},"Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization",{"claudeCode":588},"create-skill",{"basePath":688,"githubOwner":593,"githubRepo":594,"locale":18,"slug":686,"type":244},"plugins/customaize-agent/skills/create-skill",{"evaluate":690,"extract":693},{"promptVersionExtension":204,"promptVersionScoring":205,"score":691,"tags":692,"targetMarket":216,"tier":217},98,[213,211,406,214,212],{"commitSha":268},{"parentExtensionId":603,"repoId":604},[212,213,214,211,406],{"evaluatedAt":697,"extractAt":608,"updatedAt":697},1778694809113,{"_creationTime":699,"_id":700,"community":701,"display":702,"identity":707,"providers":709,"relations":716,"tags":719,"workflow":720},1778675562553.7437,"k175dz0exay5b3vg4k0nb0r0rd86myqc",{"reviewCount":8},{"description":703,"installMethods":704,"name":623,"sourceUrl":706},"Guide for creating effective skills for Apollo GraphQL and GraphQL development. Use this skill when: (1) users want to create a new skill, (2) users want to update an existing skill, (3) users ask about skill structure or best practices, (4) users need help writing SKILL.md files.\n",{"claudeCode":705},"apollographql/skills","https://github.com/apollographql/skills",{"basePath":620,"githubOwner":708,"githubRepo":243,"locale":18,"slug":623,"type":244},"apollographql",{"evaluate":710,"extract":715},{"promptVersionExtension":204,"promptVersionScoring":205,"score":711,"tags":712,"targetMarket":216,"tier":217},97,[213,713,714,211,212],"graphql","apollo",{"commitSha":268},{"parentExtensionId":717,"repoId":718},"k172cxtw1jjyfy3j32102fhz4986nn9c","kd70kp4977ph9vbpa67gwcs7j586n0sc",[212,714,213,713,211],{"evaluatedAt":721,"extractAt":722,"updatedAt":721},1778676145970,1778675562553]