[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mattpocock-qa-zh-CN":3,"guides-for-mattpocock-qa":556,"similar-k17by5c7r3tzqbt6y8q24kpc2586m3ad-zh-CN":557},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":241,"isFallback":246,"parentExtension":247,"providers":248,"relations":253,"repo":255,"tags":553,"workflow":554},1778692846401.1472,"k17by5c7r3tzqbt6y8q24kpc2586m3ad",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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\".",{"claudeCode":12},"mattpocock/skills","qa","https://github.com/mattpocock/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":239},1778692919160.6533,"kn7f45bk8t71njcvy43xpkt8gd86mqmq","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":216,"tier":217,"useCases":218},[21,26,29,33,37,40,44,47,52,56,60,63,66,69,73,76,79,82,85,88,92,96,99,103,106,109,112,115,118,121,125,128,132,136,139,142,145,148,152,155,158,161,164,167,170,174,178,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","The description clearly states the skill's purpose (filing GitHub issues conversationally after QA) and provides specific triggers and boundaries ('Use when user wants to report bugs, do QA, file issues conversationally, or mentions \"QA session\"').",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the skill's core capability and usage triggers within the typical length constraints.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","The SKILL.md body is well-structured, under 500 lines, and delegates detailed procedures to separate sections, adhering to progressive disclosure principles.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","The SKILL.md outlines the workflow and links into specific sections for each sub-task, demonstrating effective progressive disclosure.",{"category":34,"check":38,"severity":24,"summary":39},"Forked exploration","The skill's workflow involves background exploration of the codebase, and the SKILL.md implicitly supports this by stating the goal is context gathering rather than direct code modification, aligning with forked exploration.",{"category":41,"check":42,"severity":24,"summary":43},"Practical Utility","Usage examples","The SKILL.md provides detailed templates for filing issues (single and broken down), which serve as ready-to-use examples of the expected output format and content.",{"category":41,"check":45,"severity":24,"summary":46},"Edge cases","The SKILL.md documents failure modes like over-interviewing and the need for breakdown, along with recovery steps (move on, prefer thin issues) and limitations (no file paths).",{"category":48,"check":49,"severity":50,"summary":51},"Code Execution","Tool Fallback","not_applicable","This skill does not appear to rely on external MCP servers or tools; its functionality is self-contained within the agent's capabilities.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","The instructions emphasize not over-interviewing and moving on if the description is clear enough, implicitly halting a problematic line of inquiry and proceeding to the next logical step.",{"category":57,"check":58,"severity":24,"summary":59},"Portability","Cross-skill coupling","The skill is self-contained and does not appear to rely on other specific skills being loaded; its actions are clearly defined within its own scope.",{"category":41,"check":61,"severity":24,"summary":62},"Problem relevance","The description clearly identifies the problem of users needing to report bugs conversationally and the agent filing GitHub issues, directly addressing a common development pain point.",{"category":41,"check":64,"severity":24,"summary":65},"Unique selling proposition","The skill's unique value lies in its structured conversational approach to QA and automated issue filing, including background codebase exploration for context, which goes beyond simple LLM capabilities.",{"category":41,"check":67,"severity":24,"summary":68},"Production readiness","The skill is production-ready, providing a complete workflow for interactive QA and issue filing, including detailed instructions for issue templating and breakdown.",{"category":70,"check":71,"severity":24,"summary":72},"Scope","Single responsibility principle","The skill focuses solely on the task of conducting an interactive QA session and filing GitHub issues, maintaining a single, coherent responsibility.",{"category":70,"check":74,"severity":24,"summary":75},"Description quality","The description accurately and concisely reflects the skill's functionality and intended use cases.",{"category":22,"check":77,"severity":50,"summary":78},"Scoped tools","The skill does not expose any specific tools or commands; it operates through conversational interaction with the agent.",{"category":30,"check":80,"severity":50,"summary":81},"Configuration & parameter reference","The skill does not appear to have configurable parameters or explicit options beyond its conversational triggers.",{"category":70,"check":83,"severity":50,"summary":84},"Tool naming","The skill does not expose tools with names, operating via conversational prompts.",{"category":70,"check":86,"severity":50,"summary":87},"Minimal I/O surface","As the skill does not expose explicit tools, the concept of I/O surface for parameters and responses does not apply.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","The extension is distributed under the MIT license, which is permissive and allows for usability.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","The repository shows recent commits, indicating active maintenance.",{"category":93,"check":97,"severity":50,"summary":98},"Dependency Management","The extension does not appear to have external dependencies that require explicit management.",{"category":100,"check":101,"severity":50,"summary":102},"Security","Secret Management","The skill's functionality does not involve handling or exposing secrets.",{"category":100,"check":104,"severity":24,"summary":105},"Injection","The skill's instructions focus on structuring output and conversational flow, with no indication of executing or injecting arbitrary code.",{"category":100,"check":107,"severity":24,"summary":108},"Transitive Supply-Chain Grenades","The skill operates on provided text and codebase context without fetching external code or data at runtime.",{"category":100,"check":110,"severity":24,"summary":111},"Sandbox Isolation","The skill's actions are conversational and do not involve file system modifications or operations outside the agent's sandbox.",{"category":100,"check":113,"severity":24,"summary":114},"Sandbox escape primitives","No detached processes or retry loops around denied calls are evident in the skill's instructions.",{"category":100,"check":116,"severity":24,"summary":117},"Data Exfiltration","The skill's purpose is to file issues, not to exfiltrate user data to third parties.",{"category":100,"check":119,"severity":24,"summary":120},"Hidden Text Tricks","The bundled content is free of hidden text tricks and uses standard formatting.",{"category":122,"check":123,"severity":24,"summary":124},"Hooks","Opaque code execution","The skill's logic is presented in readable markdown and does not involve obfuscated code or runtime script execution.",{"category":57,"check":126,"severity":24,"summary":127},"Structural Assumption","The skill makes no assumptions about the user's project structure beyond the general expectation of a codebase for context exploration.",{"category":129,"check":130,"severity":24,"summary":131},"Trust","Issues Attention","The repository has a high number of closed issues relative to opened issues in the last 90 days, indicating good maintainer engagement.",{"category":133,"check":134,"severity":24,"summary":135},"Versioning","Release Management","The repository has a recent pushedAt date and a significant number of commits, indicating active development and versioning.",{"category":48,"check":137,"severity":50,"summary":138},"Validation","The skill operates through conversational interaction and does not use structured input/output schemas that would require validation libraries.",{"category":100,"check":140,"severity":24,"summary":141},"Unguarded Destructive Operations","Filing GitHub issues is not a destructive operation in the context of the user's system; the skill does not perform operations like `rm -rf`.",{"category":48,"check":143,"severity":24,"summary":144},"Error Handling","The skill provides clear instructions on how to proceed when issues are not clear or need breakdown, guiding the agent's behavior in different scenarios.",{"category":48,"check":146,"severity":50,"summary":147},"Logging","The skill's actions are conversational and do not involve destructive operations or outbound calls that would require local audit logging.",{"category":149,"check":150,"severity":50,"summary":151},"Compliance","GDPR","The skill's function is to file GitHub issues based on user reports and code context, not to process personal data.",{"category":149,"check":153,"severity":24,"summary":154},"Target market","The skill's functionality is general and not tied to any specific geographic or legal jurisdiction; it operates globally.",{"category":57,"check":156,"severity":24,"summary":157},"Runtime stability","The skill relies on standard conversational AI capabilities and does not make assumptions about specific editors, shells, or operating systems.",{"category":30,"check":159,"severity":24,"summary":160},"README","The README file exists and clearly outlines the purpose and installation of the skills.",{"category":70,"check":162,"severity":50,"summary":163},"Tool surface size","This is a skill that operates conversationally, not a tool with a surface area of multiple commands.",{"category":22,"check":165,"severity":50,"summary":166},"Overlapping near-synonym tools","The skill does not expose multiple tools, thus no overlapping synonyms exist.",{"category":30,"check":168,"severity":24,"summary":169},"Phantom features","All features described in the README and SKILL.md, such as interactive QA and issue filing, are supported by the skill's instructions.",{"category":171,"check":172,"severity":24,"summary":173},"Install","Installation instruction","The README provides clear installation instructions using `npx` and a setup command, along with guidance on its usage.",{"category":175,"check":176,"severity":24,"summary":177},"Errors","Actionable error messages","The instructions provide clear guidance on how to proceed when information is insufficient (e.g., asking clarifying questions, breaking down issues), acting as actionable steps.",{"category":179,"check":180,"severity":50,"summary":181},"Execution","Pinned dependencies","The skill does not appear to have external script dependencies that require pinning.",{"category":70,"check":183,"severity":50,"summary":184},"Dry-run preview","The skill's primary action is filing GitHub issues, which is a state-changing operation. However, it does not offer a specific `--dry-run` flag, but the detailed templating and breakdown instructions allow for a manual preview.",{"category":186,"check":187,"severity":50,"summary":188},"Protocol","Idempotent retry & timeouts","The skill operates conversationally and does not involve remote calls or state-changing operations that would require idempotency or timeouts.",{"category":149,"check":190,"severity":50,"summary":191},"Telemetry opt-in","There is no indication that this skill collects or emits telemetry data.",1778692919039,"This skill facilitates interactive Quality Assurance sessions by allowing users to report bugs conversationally. It explores the codebase for context and domain language to file durable, user-focused GitHub issues, with options for breaking down complex problems into multiple issues.",[195,196,197,198,199],"Interactive QA session with conversational bug reporting","Background codebase exploration for context and domain language","Automated filing of durable GitHub issues","Support for breaking down complex issues into multiple trackable items","Use of project-specific domain language in issue descriptions",[201,202,203,204],"Finding or implementing fixes for reported issues","Performing deep code reviews beyond context gathering","Replacing manual QA entirely; serves as an aid","Directly modifying or committing code","3.0.0","4.4.0","To streamline the bug reporting and QA process by enabling users to interact with an AI agent to identify, document, and file GitHub issues conversationally.","The skill is well-documented, highly focused, and demonstrates excellent adherence to best practices, resulting in a verified tier and perfect score.",100,"Excellent skill for interactive QA and automated GitHub issue filing, with strong documentation and clear scope.",[13,212,213,214,215],"github","issue-tracking","codebase-exploration","developer-tools","global","verified",[219,220,221,222],"Users reporting bugs or issues conversationally","Performing Quality Assurance tasks with AI assistance","Filing well-documented GitHub issues based on observed problems","When a user explicitly mentions needing a 'QA session'",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"security":236,"testCoverage":238},{"hasLockfile":225},false,1778692901546,{"descriptionLength":228,"readmeSize":229},281,11516,{"closedIssues90d":231,"forks":232,"hasChangelog":225,"openIssues90d":233,"pushedAt":234,"stars":235},117,6767,27,1778677522000,78489,{"hasNpmPackage":225,"license":237,"smitheryVerified":225},"MIT",{"hasCi":225,"hasTests":225},{"updatedAt":240},1778692919160,{"basePath":242,"githubOwner":243,"githubRepo":244,"locale":18,"slug":13,"type":245},"skills/deprecated/qa","mattpocock","skills","skill",true,null,{"evaluate":249,"extract":251},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":250,"targetMarket":216,"tier":217},[13,212,213,214,215],{"commitSha":252},"HEAD",{"repoId":254},"kd70nm2vazehgqc4j28ve6cwv986mv1s",{"_creationTime":256,"_id":254,"identity":257,"providers":258,"workflow":549},1778692842371.0967,{"githubOwner":243,"githubRepo":244,"sourceUrl":14},{"classify":259,"discover":543,"github":546},{"commitSha":252,"extensions":260},[261,277,286,291,299,307,318,331,345,357,375,393,401,409,421,429,437,445,453,461,471,479,487,495,503,511,519,527,535],{"basePath":262,"displayName":263,"installMethods":264,"rationale":265,"selectedPaths":266,"source":275,"sourceLanguage":18,"type":276},"","mattpocock-skills",{"claudeCode":263},"plugin manifest at .claude-plugin/plugin.json",[267,270,272],{"path":268,"priority":269},".claude-plugin/plugin.json","mandatory",{"path":271,"priority":269},"README.md",{"path":273,"priority":274},"LICENSE","high","rule","plugin",{"basePath":278,"description":279,"displayName":280,"installMethods":281,"rationale":282,"selectedPaths":283,"source":275,"sourceLanguage":18,"type":245},"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",[284],{"path":285,"priority":269},"SKILL.md",{"basePath":242,"description":10,"displayName":13,"installMethods":287,"rationale":288,"selectedPaths":289,"source":275,"sourceLanguage":18,"type":245},{"claudeCode":12},"SKILL.md frontmatter at skills/deprecated/qa/SKILL.md",[290],{"path":285,"priority":269},{"basePath":292,"description":293,"displayName":294,"installMethods":295,"rationale":296,"selectedPaths":297,"source":275,"sourceLanguage":18,"type":245},"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",[298],{"path":285,"priority":269},{"basePath":300,"description":301,"displayName":302,"installMethods":303,"rationale":304,"selectedPaths":305,"source":275,"sourceLanguage":18,"type":245},"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",[306],{"path":285,"priority":269},{"basePath":308,"description":309,"displayName":310,"installMethods":311,"rationale":312,"selectedPaths":313,"source":275,"sourceLanguage":18,"type":245},"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",[314,315],{"path":285,"priority":269},{"path":316,"priority":317},"scripts/hitl-loop.template.sh","low",{"basePath":319,"description":320,"displayName":321,"installMethods":322,"rationale":323,"selectedPaths":324,"source":275,"sourceLanguage":18,"type":245},"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",[325,326,329],{"path":285,"priority":269},{"path":327,"priority":328},"ADR-FORMAT.md","medium",{"path":330,"priority":328},"CONTEXT-FORMAT.md",{"basePath":332,"description":333,"displayName":334,"installMethods":335,"rationale":336,"selectedPaths":337,"source":275,"sourceLanguage":18,"type":245},"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",[338,339,341,343],{"path":285,"priority":269},{"path":340,"priority":328},"DEEPENING.md",{"path":342,"priority":328},"INTERFACE-DESIGN.md",{"path":344,"priority":328},"LANGUAGE.md",{"basePath":346,"description":347,"displayName":348,"installMethods":349,"rationale":350,"selectedPaths":351,"source":275,"sourceLanguage":18,"type":245},"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",[352,353,355],{"path":285,"priority":269},{"path":354,"priority":328},"LOGIC.md",{"path":356,"priority":328},"UI.md",{"basePath":358,"description":359,"displayName":360,"installMethods":361,"rationale":362,"selectedPaths":363,"source":275,"sourceLanguage":18,"type":245},"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",[364,365,367,369,371,373],{"path":285,"priority":269},{"path":366,"priority":328},"domain.md",{"path":368,"priority":328},"issue-tracker-github.md",{"path":370,"priority":328},"issue-tracker-gitlab.md",{"path":372,"priority":328},"issue-tracker-local.md",{"path":374,"priority":328},"triage-labels.md",{"basePath":376,"description":377,"displayName":378,"installMethods":379,"rationale":380,"selectedPaths":381,"source":275,"sourceLanguage":18,"type":245},"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",[382,383,385,387,389,391],{"path":285,"priority":269},{"path":384,"priority":328},"deep-modules.md",{"path":386,"priority":328},"interface-design.md",{"path":388,"priority":328},"mocking.md",{"path":390,"priority":328},"refactoring.md",{"path":392,"priority":328},"tests.md",{"basePath":394,"description":395,"displayName":396,"installMethods":397,"rationale":398,"selectedPaths":399,"source":275,"sourceLanguage":18,"type":245},"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",[400],{"path":285,"priority":269},{"basePath":402,"description":403,"displayName":404,"installMethods":405,"rationale":406,"selectedPaths":407,"source":275,"sourceLanguage":18,"type":245},"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",[408],{"path":285,"priority":269},{"basePath":410,"description":411,"displayName":412,"installMethods":413,"rationale":414,"selectedPaths":415,"source":275,"sourceLanguage":18,"type":245},"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",[416,417,419],{"path":285,"priority":269},{"path":418,"priority":328},"AGENT-BRIEF.md",{"path":420,"priority":328},"OUT-OF-SCOPE.md",{"basePath":422,"description":423,"displayName":424,"installMethods":425,"rationale":426,"selectedPaths":427,"source":275,"sourceLanguage":18,"type":245},"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",[428],{"path":285,"priority":269},{"basePath":430,"description":431,"displayName":432,"installMethods":433,"rationale":434,"selectedPaths":435,"source":275,"sourceLanguage":18,"type":245},"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",[436],{"path":285,"priority":269},{"basePath":438,"description":439,"displayName":440,"installMethods":441,"rationale":442,"selectedPaths":443,"source":275,"sourceLanguage":18,"type":245},"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",[444],{"path":285,"priority":269},{"basePath":446,"description":447,"displayName":448,"installMethods":449,"rationale":450,"selectedPaths":451,"source":275,"sourceLanguage":18,"type":245},"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",[452],{"path":285,"priority":269},{"basePath":454,"description":455,"displayName":456,"installMethods":457,"rationale":458,"selectedPaths":459,"source":275,"sourceLanguage":18,"type":245},"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",[460],{"path":285,"priority":269},{"basePath":462,"description":463,"displayName":464,"installMethods":465,"rationale":466,"selectedPaths":467,"source":275,"sourceLanguage":18,"type":245},"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",[468,469],{"path":285,"priority":269},{"path":470,"priority":317},"scripts/block-dangerous-git.sh",{"basePath":472,"description":473,"displayName":474,"installMethods":475,"rationale":476,"selectedPaths":477,"source":275,"sourceLanguage":18,"type":245},"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",[478],{"path":285,"priority":269},{"basePath":480,"description":481,"displayName":482,"installMethods":483,"rationale":484,"selectedPaths":485,"source":275,"sourceLanguage":18,"type":245},"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",[486],{"path":285,"priority":269},{"basePath":488,"description":489,"displayName":490,"installMethods":491,"rationale":492,"selectedPaths":493,"source":275,"sourceLanguage":18,"type":245},"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",[494],{"path":285,"priority":269},{"basePath":496,"description":497,"displayName":498,"installMethods":499,"rationale":500,"selectedPaths":501,"source":275,"sourceLanguage":18,"type":245},"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",[502],{"path":285,"priority":269},{"basePath":504,"description":505,"displayName":506,"installMethods":507,"rationale":508,"selectedPaths":509,"source":275,"sourceLanguage":18,"type":245},"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",[510],{"path":285,"priority":269},{"basePath":512,"description":513,"displayName":514,"installMethods":515,"rationale":516,"selectedPaths":517,"source":275,"sourceLanguage":18,"type":245},"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",[518],{"path":285,"priority":269},{"basePath":520,"description":521,"displayName":522,"installMethods":523,"rationale":524,"selectedPaths":525,"source":275,"sourceLanguage":18,"type":245},"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",[526],{"path":285,"priority":269},{"basePath":528,"description":529,"displayName":530,"installMethods":531,"rationale":532,"selectedPaths":533,"source":275,"sourceLanguage":18,"type":245},"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",[534],{"path":285,"priority":269},{"basePath":536,"description":537,"displayName":538,"installMethods":539,"rationale":540,"selectedPaths":541,"source":275,"sourceLanguage":18,"type":245},"skills/productivity/write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.","write-a-skill",{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/write-a-skill/SKILL.md",[542],{"path":285,"priority":269},{"sources":544},[545],"manual",{"closedIssues90d":231,"description":547,"forks":232,"license":237,"openIssues90d":233,"pushedAt":234,"readmeSize":229,"stars":235,"topics":548},"Skills for Real Engineers. Straight from my .claude directory.",[],{"classifiedAt":550,"discoverAt":551,"extractAt":552,"githubAt":552,"updatedAt":550},1778692846116,1778692842371,1778692844195,[214,215,212,213,13],{"evaluatedAt":240,"extractAt":555,"updatedAt":240},1778692846401,[],[558,584,613,642,665,696],{"_creationTime":559,"_id":560,"community":561,"display":562,"identity":567,"providers":571,"relations":578,"tags":580,"workflow":581},1778697652123.8928,"k171pew5empzzrfghyg9nqrk6n86nqa9",{"reviewCount":8},{"description":563,"installMethods":564,"name":212,"sourceUrl":566},"Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.",{"claudeCode":565},"steipete/clawdis","https://github.com/steipete/clawdis",{"basePath":568,"githubOwner":569,"githubRepo":570,"locale":18,"slug":212,"type":245},"skills/github","steipete","clawdis",{"evaluate":572,"extract":577},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":573,"targetMarket":216,"tier":217},[212,574,575,215,576],"cli","api","automation",{"commitSha":252},{"repoId":579},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[575,576,574,215,212],{"evaluatedAt":582,"extractAt":583,"updatedAt":582},1778698569289,1778697652123,{"_creationTime":585,"_id":586,"community":587,"display":588,"identity":594,"providers":598,"relations":606,"tags":609,"workflow":610},1778699018122.8052,"k1724eg9dj5dp6j1f2hxpdmja586mg1p",{"reviewCount":8},{"description":589,"installMethods":590,"name":592,"sourceUrl":593},"Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.",{"claudeCode":591},"wshobson/agents","typescript-advanced-types","https://github.com/wshobson/agents",{"basePath":595,"githubOwner":596,"githubRepo":597,"locale":18,"slug":592,"type":245},"plugins/javascript-typescript/skills/typescript-advanced-types","wshobson","agents",{"evaluate":599,"extract":605},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":600,"targetMarket":216,"tier":217},[601,602,603,604,215],"typescript","types","generics","programming",{"commitSha":252},{"parentExtensionId":607,"repoId":608},"k17821k05dymw6mmaehq84b46986mf3f","kd74de64zj0axtg5b8t7eqqe2x86nske",[215,603,604,602,601],{"evaluatedAt":611,"extractAt":612,"updatedAt":611},1778701655608,1778699018122,{"_creationTime":614,"_id":615,"community":616,"display":617,"identity":623,"providers":628,"relations":635,"tags":638,"workflow":639},1778696691708.329,"k170yjw596k3cg892bq130jyd186mhyz",{"reviewCount":8},{"description":618,"installMethods":619,"name":621,"sourceUrl":622},"Validate a Claude Code plugin structure, frontmatter, and MCP tool references",{"claudeCode":620},"ruvnet/ruflo","Validate Plugin","https://github.com/ruvnet/ruflo",{"basePath":624,"githubOwner":625,"githubRepo":626,"locale":18,"slug":627,"type":245},"plugins/ruflo-plugin-creator/skills/validate-plugin","ruvnet","ruflo","validate-plugin",{"evaluate":629,"extract":634},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":630,"targetMarket":216,"tier":217},[631,276,215,632,633],"validation","claude-code","mcp",{"commitSha":252,"license":237},{"parentExtensionId":636,"repoId":637},"k17f4y1y2y777p7zrxxhbnf03n86mr5j","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[632,215,633,276,631],{"evaluatedAt":640,"extractAt":641,"updatedAt":640},1778701241052,1778696691708,{"_creationTime":643,"_id":644,"community":645,"display":646,"identity":650,"providers":652,"relations":660,"tags":662,"workflow":663},1778696691708.3264,"k179thjzaw5kepc7zhdj9sat3n86mcqp",{"reviewCount":8},{"description":647,"installMethods":648,"name":649,"sourceUrl":622},"Validate pending migrations for foreign key consistency, rollback safety, and best practices",{"claudeCode":620},"migrate-validate",{"basePath":651,"githubOwner":625,"githubRepo":626,"locale":18,"slug":649,"type":245},"plugins/ruflo-migrations/skills/migrate-validate",{"evaluate":653,"extract":659},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":654,"targetMarket":216,"tier":217},[655,656,657,631,658,215],"database","migrations","sql","code-quality",{"commitSha":252},{"parentExtensionId":661,"repoId":637},"k176me0sh9b6bc3gzttnywx4w986njzh",[658,655,215,656,657,631],{"evaluatedAt":664,"extractAt":641,"updatedAt":664},1778701008912,{"_creationTime":666,"_id":667,"community":668,"display":669,"identity":675,"providers":679,"relations":688,"tags":691,"workflow":692},1778699514767.176,"k17f4qpem03b53manh7vcdvtr986mmjg",{"reviewCount":8},{"description":670,"installMethods":671,"name":673,"sourceUrl":674},"AI 代理的上下文运行时 — 包含 59 个 MCP 工具、10 种读取模式、95+ 种 shell 模式、支持 18 种语言的 tree-sitter AST。将 LLM 上下文压缩高达 99%。用于读取文件、运行 shell 命令、搜索代码或探索目录。如果不存在，则自动安装。",{"claudeCode":672},"yvgude/lean-ctx","lean-ctx","https://github.com/yvgude/lean-ctx",{"basePath":676,"githubOwner":677,"githubRepo":673,"locale":678,"slug":673,"type":245},"skills/lean-ctx","yvgude","zh-CN",{"evaluate":680,"extract":687},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":681,"targetMarket":216,"tier":217},[682,683,684,215,685,686],"context-compression","ai-agent","cli-tools","rust","code-analysis",{"commitSha":252},{"repoId":689,"translatedFrom":690},"kd7dxtfr9j3z54hs3bz0218e1n86may0","k170fxxh22hdspg4vr94whgj1986mpr9",[683,684,686,682,215,685],{"evaluatedAt":693,"extractAt":694,"updatedAt":695},1778699456179,1778699438912,1778699514767,{"_creationTime":697,"_id":698,"community":699,"display":700,"identity":706,"providers":710,"relations":717,"tags":720,"workflow":721},1778698175626.3276,"k17cj6pbcgtrw523a4sw8mhcxn86mzvv",{"reviewCount":8},{"description":701,"installMethods":702,"name":704,"sourceUrl":705},"Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.",{"claudeCode":703},"trailofbits/skills","Semgrep Rule Creator","https://github.com/trailofbits/skills",{"basePath":707,"githubOwner":708,"githubRepo":244,"locale":18,"slug":709,"type":245},"plugins/semgrep-rule-creator/skills/semgrep-rule-creator","trailofbits","semgrep-rule-creator",{"evaluate":711,"extract":716},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":712,"targetMarket":216,"tier":217},[713,714,715,658,215],"semgrep","security","static-analysis",{"commitSha":252},{"parentExtensionId":718,"repoId":719},"k1757483sd0rdv04r5773w2tb986mb9g","kd7d5sbrd9m157hjv9c7v4wfyn86mk2f",[658,215,714,713,715],{"evaluatedAt":722,"extractAt":723,"updatedAt":722},1778699451460,1778698175626]