[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mattpocock-caveman-de":3,"guides-for-mattpocock-caveman":596,"similar-k17ah0hhhwvmsj6h6vxmfmd9nn86mhff-de":597},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":254,"isFallback":260,"parentExtension":261,"providers":295,"relations":299,"repo":300,"tags":594,"workflow":595},1778692846401.1528,"k17ah0hhhwvmsj6h6vxmfmd9nn86mhff",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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",{"claudeCode":12},"mattpocock/skills","Caveman Mode","https://github.com/mattpocock/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":236,"workflow":252},1778693459372.4387,"kn7bwshb6np1b7b628r85xfe4s86mynn","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":205,"prerequisites":208,"promptVersionExtension":209,"promptVersionScoring":210,"purpose":211,"rationale":212,"score":213,"summary":214,"tags":215,"targetMarket":222,"tier":223,"useCases":224,"workflow":229},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of excessive token usage and verbosity, directly addressing the user's pain point.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a unique capability by drastically compressing communication while maintaining technical accuracy, going beyond default LLM behavior.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill is fully implemented and ready for use, providing a consistent and accurate communication mode for the stated purpose.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on communication compression, adhering to a single responsibility.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description is concise, accurate, and clearly outlines the skill's purpose, triggers, and behavior.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose tools in the traditional sense; it modifies communication style.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","The skill does not have configurable parameters or options beyond its trigger phrases and modes of operation.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This skill does not expose tools with names.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","The skill operates by altering its output style, not through explicit tool input/output schemas.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension is licensed under the MIT license, which is a permissive open-source license.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The last commit was on May 13, 2026, indicating recent maintenance.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The skill does not appear to use any third-party dependencies.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill does not handle or expose any secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill operates on communication style and does not load or execute external data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill does not fetch external content at runtime; all logic is bundled.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill only modifies output style and does not interact with the file system or external processes.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached processes or retry loops around denied tool calls are present.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill does not read or submit confidential data.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","Bundled content is free of hidden-steering tricks.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's logic is contained within plain, readable code in SKILL.md.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill makes no assumptions about user project structure, operating on the conversation context.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","With 27 open and 117 closed issues in the last 90 days, the closure rate is high (approx 81%), indicating good maintainer engagement.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The repository has a recent push date and a high star count, suggesting active development, though no explicit versioning is detected in the SKILL.md.",{"category":104,"check":105,"severity":42,"summary":106},"Code Execution","Validation","The skill does not execute code with parameters that require validation.",{"category":66,"check":108,"severity":42,"summary":109},"Unguarded Destructive Operations","The skill does not perform any destructive operations.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The skill's logic is straightforward and unlikely to generate complex errors; the documentation implies a fail-closed approach for clarity.",{"category":104,"check":114,"severity":42,"summary":115},"Logging","The skill does not perform destructive actions or outbound calls requiring logging.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The skill operates on communication style and does not process personal data.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill's functionality is language-agnostic and has no regional dependencies, making it globally applicable.",{"category":92,"check":124,"severity":24,"summary":125},"Runtime stability","The skill's logic is pure text manipulation and should run reliably across different environments.",{"category":45,"check":127,"severity":24,"summary":128},"README","The README file exists and clearly articulates the purpose and benefits of the skills repository, including this specific skill.",{"category":33,"check":130,"severity":42,"summary":131},"Tool surface size","This is a single-function skill, not a collection of tools.",{"category":40,"check":133,"severity":42,"summary":134},"Overlapping near-synonym tools","The skill does not expose multiple tools with similar functions.",{"category":45,"check":136,"severity":24,"summary":137},"Phantom features","All features advertised in the description and README are implemented by the skill's logic.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear installation instructions using `npx skills@latest add` and a setup command.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The skill's logic is straightforward, and error paths are implicitly handled by the LLM's ability to adhere to instructions or gracefully fail.",{"category":147,"check":148,"severity":42,"summary":149},"Execution","Pinned dependencies","The skill does not rely on external dependencies that would require pinning.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The skill does not perform state-changing operations or send data outward, so a dry-run is not applicable.",{"category":154,"check":155,"severity":42,"summary":156},"Protocol","Idempotent retry & timeouts","The skill operates synchronously within the LLM's turn and does not involve external calls or state-changing operations that require idempotency or timeouts.",{"category":117,"check":158,"severity":42,"summary":159},"Telemetry opt-in","The skill does not emit telemetry.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description precisely states the skill's function (ultra-compressed communication) and its triggers (specific phrases, commands).",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the skill's core capability and triggers.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md body is concise, focusing on rules and exceptions, and avoids excessive preamble.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md is short and direct, with no need for progressive disclosure.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","The skill does not involve deep exploration or code review that would necessitate forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","Clear examples are provided for different use cases, demonstrating the input and expected output.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The 'Auto-Clarity Exception' section details edge cases where the caveman mode is temporarily dropped, with recovery steps.",{"category":104,"check":183,"severity":42,"summary":184},"Tool Fallback","This skill does not rely on external tools that would require a fallback mechanism.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The skill implicitly handles unexpected states by resuming normal operation or reverting to full clarity when instructed, as described in its persistence and exception rules.",{"category":92,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill operates independently and does not rely on other specific skills being loaded.",1778693459150,"This skill modifies the LLM's output to be ultra-compressed, dropping filler words and articles while retaining technical accuracy. It can be activated by specific user phrases and deactivates automatically when clarity is needed for complex operations.",[195,196,197,198,199],"Ultra-compressed communication mode","Drops filler, articles, and pleasantries","Maintains full technical accuracy","Activated by specific user triggers","Temporarily drops compression for critical operations",[201,202,203,204],"Losing technical accuracy","Being unreadable or incomprehensible","Permanently altering the AI's base communication style without explicit triggers","Interfering with critical security or confirmation messages",[206,207],"Communication Efficiency","Concise Language",[],"3.0.0","4.4.0","To significantly reduce token usage and improve communication efficiency by adopting a highly compressed, yet technically accurate, language mode.","The extension has a single 'not_applicable' finding for Tool Fallback, which is expected for its nature. All other checks passed with high confidence.",98,"Excellent skill for reducing token usage by compressing language while maintaining accuracy.",[216,217,218,219,220,221],"communication","compression","efficiency","llm","text","utility","global","verified",[225,226,227,228],"When users request \"caveman mode\" or similar commands","When minimizing token usage is a priority","For brief, technically accurate responses","When communicating complex technical details concisely",[230,231,232,233,234,235],"User invokes caveman mode via specific phrases or commands.","Skill activates ultra-compressed communication mode.","Skill drops articles, filler, and pleasantries while retaining technical accuracy.","Skill maintains this mode across responses.","Skill temporarily reverts to full clarity for security warnings, confirmations, or complex sequences.","Skill deactivates caveman mode upon user command ('stop caveman', 'normal mode').",{"codeQuality":237,"collectedAt":239,"documentation":240,"maintenance":243,"security":249,"testCoverage":251},{"hasLockfile":238},false,1778693439272,{"descriptionLength":241,"readmeSize":242},264,11516,{"closedIssues90d":244,"forks":245,"hasChangelog":238,"openIssues90d":246,"pushedAt":247,"stars":248},117,6767,27,1778677522000,78489,{"hasNpmPackage":238,"license":250,"smitheryVerified":238},"MIT",{"hasCi":238,"hasTests":238},{"updatedAt":253},1778693459372,{"basePath":255,"githubOwner":256,"githubRepo":257,"locale":18,"slug":258,"type":259},"skills/productivity/caveman","mattpocock","skills","caveman","skill",true,{"_creationTime":262,"_id":263,"community":264,"display":265,"identity":269,"parentExtension":272,"providers":273,"relations":289,"tags":291,"workflow":292},1778692846401.1467,"k171mc92f05dc4v6jzgf6bng7d86mr9t",{"reviewCount":8},{"description":266,"installMethods":267,"name":268,"sourceUrl":14},"Skills for Real Engineers. Straight from my .claude directory.",{"claudeCode":268},"mattpocock-skills",{"basePath":270,"githubOwner":256,"githubRepo":257,"locale":18,"slug":257,"type":271},"","plugin",null,{"evaluate":274,"extract":284},{"promptVersionExtension":209,"promptVersionScoring":210,"score":275,"tags":276,"targetMarket":222,"tier":283},79,[277,278,279,280,281,282],"engineering","productivity","ai-tools","developer-tools","code-quality","refactoring","community",{"commitSha":285,"plugin":286},"HEAD",{"mcpCount":8,"provider":287,"skillCount":288},"classify",14,{"repoId":290},"kd70nm2vazehgqc4j28ve6cwv986mv1s",[279,281,280,277,278,282],{"evaluatedAt":293,"extractAt":294,"updatedAt":293},1778692867921,1778692846401,{"evaluate":296,"extract":298},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":297,"targetMarket":222,"tier":223},[216,217,218,219,220,221],{"commitSha":285,"license":250},{"parentExtensionId":263,"repoId":290},{"_creationTime":301,"_id":290,"identity":302,"providers":303,"workflow":590},1778692842371.0967,{"githubOwner":256,"githubRepo":257,"sourceUrl":14},{"classify":304,"discover":585,"github":588},{"commitSha":285,"extensions":305},[306,319,328,336,344,352,363,376,390,402,420,438,446,454,466,474,482,490,498,506,516,524,532,540,548,556,561,569,577],{"basePath":270,"displayName":268,"installMethods":307,"rationale":308,"selectedPaths":309,"source":318,"sourceLanguage":18,"type":271},{"claudeCode":268},"plugin manifest at .claude-plugin/plugin.json",[310,313,315],{"path":311,"priority":312},".claude-plugin/plugin.json","mandatory",{"path":314,"priority":312},"README.md",{"path":316,"priority":317},"LICENSE","high","rule",{"basePath":320,"description":321,"displayName":322,"installMethods":323,"rationale":324,"selectedPaths":325,"source":318,"sourceLanguage":18,"type":259},"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",[326],{"path":327,"priority":312},"SKILL.md",{"basePath":329,"description":330,"displayName":331,"installMethods":332,"rationale":333,"selectedPaths":334,"source":318,"sourceLanguage":18,"type":259},"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",[335],{"path":327,"priority":312},{"basePath":337,"description":338,"displayName":339,"installMethods":340,"rationale":341,"selectedPaths":342,"source":318,"sourceLanguage":18,"type":259},"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",[343],{"path":327,"priority":312},{"basePath":345,"description":346,"displayName":347,"installMethods":348,"rationale":349,"selectedPaths":350,"source":318,"sourceLanguage":18,"type":259},"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",[351],{"path":327,"priority":312},{"basePath":353,"description":354,"displayName":355,"installMethods":356,"rationale":357,"selectedPaths":358,"source":318,"sourceLanguage":18,"type":259},"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",[359,360],{"path":327,"priority":312},{"path":361,"priority":362},"scripts/hitl-loop.template.sh","low",{"basePath":364,"description":365,"displayName":366,"installMethods":367,"rationale":368,"selectedPaths":369,"source":318,"sourceLanguage":18,"type":259},"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",[370,371,374],{"path":327,"priority":312},{"path":372,"priority":373},"ADR-FORMAT.md","medium",{"path":375,"priority":373},"CONTEXT-FORMAT.md",{"basePath":377,"description":378,"displayName":379,"installMethods":380,"rationale":381,"selectedPaths":382,"source":318,"sourceLanguage":18,"type":259},"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",[383,384,386,388],{"path":327,"priority":312},{"path":385,"priority":373},"DEEPENING.md",{"path":387,"priority":373},"INTERFACE-DESIGN.md",{"path":389,"priority":373},"LANGUAGE.md",{"basePath":391,"description":392,"displayName":393,"installMethods":394,"rationale":395,"selectedPaths":396,"source":318,"sourceLanguage":18,"type":259},"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",[397,398,400],{"path":327,"priority":312},{"path":399,"priority":373},"LOGIC.md",{"path":401,"priority":373},"UI.md",{"basePath":403,"description":404,"displayName":405,"installMethods":406,"rationale":407,"selectedPaths":408,"source":318,"sourceLanguage":18,"type":259},"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",[409,410,412,414,416,418],{"path":327,"priority":312},{"path":411,"priority":373},"domain.md",{"path":413,"priority":373},"issue-tracker-github.md",{"path":415,"priority":373},"issue-tracker-gitlab.md",{"path":417,"priority":373},"issue-tracker-local.md",{"path":419,"priority":373},"triage-labels.md",{"basePath":421,"description":422,"displayName":423,"installMethods":424,"rationale":425,"selectedPaths":426,"source":318,"sourceLanguage":18,"type":259},"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",[427,428,430,432,434,436],{"path":327,"priority":312},{"path":429,"priority":373},"deep-modules.md",{"path":431,"priority":373},"interface-design.md",{"path":433,"priority":373},"mocking.md",{"path":435,"priority":373},"refactoring.md",{"path":437,"priority":373},"tests.md",{"basePath":439,"description":440,"displayName":441,"installMethods":442,"rationale":443,"selectedPaths":444,"source":318,"sourceLanguage":18,"type":259},"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",[445],{"path":327,"priority":312},{"basePath":447,"description":448,"displayName":449,"installMethods":450,"rationale":451,"selectedPaths":452,"source":318,"sourceLanguage":18,"type":259},"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",[453],{"path":327,"priority":312},{"basePath":455,"description":456,"displayName":457,"installMethods":458,"rationale":459,"selectedPaths":460,"source":318,"sourceLanguage":18,"type":259},"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",[461,462,464],{"path":327,"priority":312},{"path":463,"priority":373},"AGENT-BRIEF.md",{"path":465,"priority":373},"OUT-OF-SCOPE.md",{"basePath":467,"description":468,"displayName":469,"installMethods":470,"rationale":471,"selectedPaths":472,"source":318,"sourceLanguage":18,"type":259},"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",[473],{"path":327,"priority":312},{"basePath":475,"description":476,"displayName":477,"installMethods":478,"rationale":479,"selectedPaths":480,"source":318,"sourceLanguage":18,"type":259},"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",[481],{"path":327,"priority":312},{"basePath":483,"description":484,"displayName":485,"installMethods":486,"rationale":487,"selectedPaths":488,"source":318,"sourceLanguage":18,"type":259},"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",[489],{"path":327,"priority":312},{"basePath":491,"description":492,"displayName":493,"installMethods":494,"rationale":495,"selectedPaths":496,"source":318,"sourceLanguage":18,"type":259},"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",[497],{"path":327,"priority":312},{"basePath":499,"description":500,"displayName":501,"installMethods":502,"rationale":503,"selectedPaths":504,"source":318,"sourceLanguage":18,"type":259},"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",[505],{"path":327,"priority":312},{"basePath":507,"description":508,"displayName":509,"installMethods":510,"rationale":511,"selectedPaths":512,"source":318,"sourceLanguage":18,"type":259},"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",[513,514],{"path":327,"priority":312},{"path":515,"priority":362},"scripts/block-dangerous-git.sh",{"basePath":517,"description":518,"displayName":519,"installMethods":520,"rationale":521,"selectedPaths":522,"source":318,"sourceLanguage":18,"type":259},"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",[523],{"path":327,"priority":312},{"basePath":525,"description":526,"displayName":527,"installMethods":528,"rationale":529,"selectedPaths":530,"source":318,"sourceLanguage":18,"type":259},"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",[531],{"path":327,"priority":312},{"basePath":533,"description":534,"displayName":535,"installMethods":536,"rationale":537,"selectedPaths":538,"source":318,"sourceLanguage":18,"type":259},"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",[539],{"path":327,"priority":312},{"basePath":541,"description":542,"displayName":543,"installMethods":544,"rationale":545,"selectedPaths":546,"source":318,"sourceLanguage":18,"type":259},"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",[547],{"path":327,"priority":312},{"basePath":549,"description":550,"displayName":551,"installMethods":552,"rationale":553,"selectedPaths":554,"source":318,"sourceLanguage":18,"type":259},"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",[555],{"path":327,"priority":312},{"basePath":255,"description":10,"displayName":258,"installMethods":557,"rationale":558,"selectedPaths":559,"source":318,"sourceLanguage":18,"type":259},{"claudeCode":12},"SKILL.md frontmatter at skills/productivity/caveman/SKILL.md",[560],{"path":327,"priority":312},{"basePath":562,"description":563,"displayName":564,"installMethods":565,"rationale":566,"selectedPaths":567,"source":318,"sourceLanguage":18,"type":259},"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",[568],{"path":327,"priority":312},{"basePath":570,"description":571,"displayName":572,"installMethods":573,"rationale":574,"selectedPaths":575,"source":318,"sourceLanguage":18,"type":259},"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",[576],{"path":327,"priority":312},{"basePath":578,"description":579,"displayName":580,"installMethods":581,"rationale":582,"selectedPaths":583,"source":318,"sourceLanguage":18,"type":259},"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",[584],{"path":327,"priority":312},{"sources":586},[587],"manual",{"closedIssues90d":244,"description":266,"forks":245,"license":250,"openIssues90d":246,"pushedAt":247,"readmeSize":242,"stars":248,"topics":589},[],{"classifiedAt":591,"discoverAt":592,"extractAt":593,"githubAt":593,"updatedAt":591},1778692846116,1778692842371,1778692844195,[216,217,218,219,220,221],{"evaluatedAt":253,"extractAt":294,"updatedAt":253},[],[598,629,658,681,708,734],{"_creationTime":599,"_id":600,"community":601,"display":602,"identity":608,"providers":613,"relations":622,"tags":625,"workflow":626},1778694269038.6682,"k1752cypc448mke749yjbkc65186mg6f",{"reviewCount":8},{"description":603,"installMethods":604,"name":606,"sourceUrl":607},"This skill should be used when the user asks to \"compress context\", \"summarize conversation history\", \"implement compaction\", \"reduce token usage\", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.",{"claudeCode":605},"muratcankoylan/Agent-Skills-for-Context-Engineering","Context Compression","https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",{"basePath":609,"githubOwner":610,"githubRepo":611,"locale":18,"slug":612,"type":259},"skills/context-compression","muratcankoylan","Agent-Skills-for-Context-Engineering","context-compression",{"evaluate":614,"extract":621},{"promptVersionExtension":209,"promptVersionScoring":210,"score":615,"tags":616,"targetMarket":222,"tier":223},100,[617,219,618,619,217,620],"context-engineering","agent","summarization","evaluation",{"commitSha":285,"license":250},{"parentExtensionId":623,"repoId":624},"k1754dy3wbsv2a5gr1a983zzs586njca","kd7f12maf5nxmx5xttjx7scfnx86m1tv",[618,217,617,620,219,619],{"evaluatedAt":627,"extractAt":628,"updatedAt":627},1778694410149,1778694269038,{"_creationTime":630,"_id":631,"community":632,"display":633,"identity":638,"providers":642,"relations":649,"tags":653,"workflow":654},1778692096490.2632,"k17ea12pc4vjjjep7wxsq3s5jn86m791",{"reviewCount":8},{"description":634,"installMethods":635,"name":258,"sourceUrl":637},"Ultra-komprimierter Kommunikationsmodus. Reduziert Token-Verbrauch um ca. 75 %, indem es wie ein Höhlenmensch spricht, aber die volle technische Genauigkeit beibehält. Unterstützt Intensitätsstufen: Lite, Full (Standard), Ultra, Wenyan-Lite, Wenyan-Full, Wenyan-Ultra. Verwenden Sie es, wenn der Benutzer \"Höhlenmensch-Modus\", \"sprich wie ein Höhlenmensch\", \"benutze Höhlenmensch\", \"weniger Tokens\", \"sei kurz\" sagt oder /caveman aufruft. Löst auch automatisch aus, wenn Token-Effizienz angefordert wird.\n",{"claudeCode":636},"juliusbrussee/caveman","https://github.com/juliusbrussee/caveman",{"basePath":639,"githubOwner":640,"githubRepo":258,"locale":641,"slug":258,"type":259},"skills/caveman","juliusbrussee","de",{"evaluate":643,"extract":648},{"promptVersionExtension":209,"promptVersionScoring":210,"score":644,"tags":645,"targetMarket":222,"tier":223},99,[217,219,646,216,647],"token-efficiency","prompt-engineering",{"commitSha":285,"license":250},{"parentExtensionId":650,"repoId":651,"translatedFrom":652},"k170g496f5ze5hv8xa2e7b91ex86mz9m","kd7890f0sfy0ymf1pakpx7vqch86nmew","k175qp58x34qgtcj9b1tpxeern86mqvz",[216,217,219,647,646],{"evaluatedAt":655,"extractAt":656,"updatedAt":657},1778691864047,1778691765524,1778692096490,{"_creationTime":659,"_id":660,"community":661,"display":662,"identity":666,"providers":668,"relations":675,"tags":677,"workflow":678},1778692112007.519,"k174p06y3q0ewnh9wyjm8v94hd86nzz1",{"reviewCount":8},{"description":663,"installMethods":664,"name":665,"sourceUrl":637},"Komprimiert natürlichsprachige Speicherdateien (CLAUDE.md, Todos, Einstellungen) in das Caveman-Format, um Eingabetoken zu sparen. Behält alle technischen Inhalte, Codes, URLs und Strukturen bei. Die komprimierte Version überschreibt die Originaldatei. Ein menschenlesbares Backup wird als DATEI.original.md gespeichert. Trigger: /caveman-compress DATEIPFAD oder \"memory file komprimieren\"\n",{"claudeCode":636},"caveman-compress",{"basePath":667,"githubOwner":640,"githubRepo":258,"locale":641,"slug":665,"type":259},"skills/caveman-compress",{"evaluate":669,"extract":674},{"promptVersionExtension":209,"promptVersionScoring":210,"score":644,"tags":670,"targetMarket":222,"tier":223},[217,671,672,673,221],"token-saving","markdown","text-processing",{"commitSha":285},{"parentExtensionId":650,"repoId":651,"translatedFrom":676},"k176a757cfd35jb9npje9qqzed86nvpn",[217,672,673,671,221],{"evaluatedAt":679,"extractAt":656,"updatedAt":680},1778691883875,1778692112007,{"_creationTime":682,"_id":683,"community":684,"display":685,"identity":691,"providers":695,"relations":702,"tags":704,"workflow":705},1778697652123.8982,"k175ckmrqc4x6sjm90k7ejbj3s86ntxs",{"reviewCount":8},{"description":686,"installMethods":687,"name":689,"sourceUrl":690},"Use the Slack tool to react, pin/unpin, send, edit, delete messages, or fetch Slack member info.",{"claudeCode":688},"steipete/clawdis","slack","https://github.com/steipete/clawdis",{"basePath":692,"githubOwner":693,"githubRepo":694,"locale":18,"slug":689,"type":259},"skills/slack","steipete","clawdis",{"evaluate":696,"extract":701},{"promptVersionExtension":209,"promptVersionScoring":210,"score":615,"tags":697,"targetMarket":222,"tier":223},[689,698,216,699,700],"messaging","automation","api",{"commitSha":285},{"repoId":703},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[700,699,216,698,689],{"evaluatedAt":706,"extractAt":707,"updatedAt":706},1778698950505,1778697652123,{"_creationTime":709,"_id":710,"community":711,"display":712,"identity":718,"providers":722,"relations":727,"tags":730,"workflow":731},1778696833339.6218,"k176gr5qszggh36kjn8a1cwehs86n2jd",{"reviewCount":8},{"description":713,"installMethods":714,"name":716,"sourceUrl":717},"Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels.\nUse when user asks to: search email, read email, send email, create email draft, mark as read,\narchive email, star email, or manage Gmail labels. Lightweight alternative to full Google\nWorkspace MCP server with standalone OAuth authentication.\n",{"claudeCode":715},"sanjay3290/ai-skills","gmail","https://github.com/sanjay3290/ai-skills",{"basePath":719,"githubOwner":720,"githubRepo":721,"locale":18,"slug":716,"type":259},"skills/gmail","sanjay3290","ai-skills",{"evaluate":723,"extract":726},{"promptVersionExtension":209,"promptVersionScoring":210,"score":615,"tags":724,"targetMarket":222,"tier":223},[716,725,216,699,278],"email",{"commitSha":285},{"parentExtensionId":728,"repoId":729},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[699,216,725,716,278],{"evaluatedAt":732,"extractAt":733,"updatedAt":732},1778696939862,1778696833339,{"_creationTime":735,"_id":736,"community":737,"display":738,"identity":744,"providers":748,"relations":755,"tags":758,"workflow":759},1778695720086.7673,"k17fyn4zyen5dk0r3hdgaj845d86mqe0",{"reviewCount":8},{"description":739,"installMethods":740,"name":742,"sourceUrl":743},"Produces an attendee-facing agenda that sets what will be discussed, who owns each topic, and how time will be spent. Supports ten meeting type variants (standup, planning, review, decision-making, brainstorm, 1-on-1, stakeholder-review, project-kickoff, working-session, exec-briefing). Emits a shareable summary suitable for Slack or email plus a full agenda with time-boxed topics, type tags, owners, attendee prep, and logistics.",{"claudeCode":741},"product-on-purpose/pm-skills","foundation-meeting-agenda","https://github.com/product-on-purpose/pm-skills",{"basePath":745,"githubOwner":746,"githubRepo":747,"locale":18,"slug":742,"type":259},"skills/foundation-meeting-agenda","product-on-purpose","pm-skills",{"evaluate":749,"extract":754},{"promptVersionExtension":209,"promptVersionScoring":210,"score":615,"tags":750,"targetMarket":222,"tier":223},[751,752,278,753,216],"meeting","agenda","planning",{"commitSha":285},{"parentExtensionId":756,"repoId":757},"k1721116hsfj7zg78w03432n8986n6y8","kd78ksv1wjj826ds5j1sh2kqnx86mhqf",[752,216,751,753,278],{"evaluatedAt":760,"extractAt":761,"updatedAt":760},1778696117198,1778695720086]