[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-juliusbrussee-caveman-stats-en":3,"guides-for-juliusbrussee-caveman-stats":500,"similar-k1713vd42cpj5hpr0a1vvr8rg986nzre-en":501},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":241,"isFallback":223,"parentExtension":246,"providers":302,"relations":306,"repo":307,"tags":497,"workflow":498},1778691765524.374,"k1713vd42cpj5hpr0a1vvr8rg986nzre",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.\n",{"claudeCode":12},"juliusbrussee/caveman","caveman-stats","https://github.com/juliusbrussee/caveman",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":221,"workflow":239},1778691906284.8816,"kn723zkxmht6ztkgnz63c2kh5x86mzbt","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":215,"tier":216,"useCases":217},[21,26,29,33,37,41,45,48,52,56,60,63,66,69,73,76,79,82,85,88,92,96,99,103,106,109,112,115,118,121,125,128,132,137,141,144,147,150,154,157,160,163,166,169,172,176,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","The description clearly states what the skill does (shows token usage from session log) and when to use it (/caveman-stats), and names the artifact (session log) and user intent (view stats).",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","The frontmatter is concise and clearly summarizes the core capability and trigger.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","The skill body is concise and delegates deeper material to separate files like SKILL.md and README.md.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","The SKILL.md outlines the flow and references related markdown files for deeper information.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","This skill does not involve deep exploration or code review that would require forking.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","The README provides a clear invocation example and expected output.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","The documentation implicitly handles edge cases by stating numbers come directly from the log, implying no estimation or interpretation issues.",{"category":49,"check":50,"severity":39,"summary":51},"Code Execution","Tool Fallback","This skill does not rely on external tools like an MCP server; it interacts directly with the session log.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","The skill relies on direct log reading, implying that if the log is unavailable or malformed, it would naturally fail to produce output, effectively halting the workflow for that specific action.",{"category":57,"check":58,"severity":24,"summary":59},"Portability","Cross-skill coupling","The skill is self-contained and does not rely on other skills being loaded.",{"category":42,"check":61,"severity":24,"summary":62},"Problem relevance","The description clearly states the problem of needing real token usage and savings, directly addressing a user pain point.",{"category":42,"check":64,"severity":24,"summary":65},"Unique selling proposition","The skill offers a unique value by directly reading session logs for precise numbers, avoiding AI estimation and providing a clear baseline comparison.",{"category":42,"check":67,"severity":24,"summary":68},"Production readiness","The skill is fully implemented, reads directly from the session log, and provides immediate output as described.",{"category":70,"check":71,"severity":24,"summary":72},"Scope","Single responsibility principle","The skill has a single, well-defined responsibility: displaying session token usage statistics.",{"category":70,"check":74,"severity":24,"summary":75},"Description quality","The description accurately and concisely reflects the skill's behavior and purpose.",{"category":22,"check":77,"severity":39,"summary":78},"Scoped tools","This skill does not expose tools in the traditional sense; its functionality is triggered via a command.",{"category":30,"check":80,"severity":39,"summary":81},"Configuration & parameter reference","The skill has no configurable parameters or options beyond the invocation command itself.",{"category":70,"check":83,"severity":39,"summary":84},"Tool naming","This skill does not expose user-facing tools.",{"category":70,"check":86,"severity":39,"summary":87},"Minimal I/O surface","This skill does not expose tools with parameter schemas or response shapes.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","The MIT license is clearly declared in a LICENSE file and is a permissive OSS license.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","The last commit was on May 12, 2026, which is recent.",{"category":93,"check":97,"severity":39,"summary":98},"Dependency Management","The skill does not appear to use any third-party dependencies.",{"category":100,"check":101,"severity":39,"summary":102},"Security","Secret Management","The skill does not handle any secrets.",{"category":100,"check":104,"severity":24,"summary":105},"Injection","The skill reads directly from a session log and does not load external data as instructions.",{"category":100,"check":107,"severity":24,"summary":108},"Transitive Supply-Chain Grenades","The skill does not fetch external files at runtime; all necessary information is local to the session log.",{"category":100,"check":110,"severity":24,"summary":111},"Sandbox Isolation","The skill only reads from the session log and does not modify any files outside its designated scope.",{"category":100,"check":113,"severity":24,"summary":114},"Sandbox escape primitives","No detached-process spawns or deny-retry loops were found in the provided code.",{"category":100,"check":116,"severity":24,"summary":117},"Data Exfiltration","The skill only reads local session data and does not submit any confidential information to a third party.",{"category":100,"check":119,"severity":24,"summary":120},"Hidden Text Tricks","The bundled content is free of hidden-steering tricks and uses clean printable ASCII.",{"category":122,"check":123,"severity":24,"summary":124},"Hooks","Opaque code execution","The JavaScript code is plain and readable, with no obfuscation like base64 payloads or eval.",{"category":57,"check":126,"severity":24,"summary":127},"Structural Assumption","The skill makes no assumptions about the user's project structure beyond the existence of the session log.",{"category":129,"check":130,"severity":24,"summary":131},"Trust","Issues Attention","With 66 issues opened and 70 closed in the last 90 days, the closure rate is approximately 51%, indicating good maintainer engagement.",{"category":133,"check":134,"severity":135,"summary":136},"Versioning","Release Management","warning","While the commit date is recent, there is no clear versioning signal like a semver tag or a CHANGELOG.md, and install instructions might reference `main`.",{"category":138,"check":139,"severity":39,"summary":140},"Execution","Validation","The skill's primary function is reading a log file; there are no complex input arguments or structured outputs requiring validation.",{"category":100,"check":142,"severity":39,"summary":143},"Unguarded Destructive Operations","The skill is read-only and does not perform any destructive operations.",{"category":49,"check":145,"severity":24,"summary":146},"Error Handling","The skill's logic appears to handle potential errors gracefully by reading directly from the log, implying failure to read would result in no output rather than crashing.",{"category":49,"check":148,"severity":24,"summary":149},"Logging","The skill writes a lifetime-savings suffix file, providing an audit trail for its actions.",{"category":151,"check":152,"severity":39,"summary":153},"Compliance","GDPR","The skill operates on session logs and does not process personal data.",{"category":151,"check":155,"severity":24,"summary":156},"Target market","The skill is language-agnostic and operates on session logs, making it globally applicable.",{"category":57,"check":158,"severity":24,"summary":159},"Runtime stability","The skill is written in JavaScript and should run on any POSIX-compatible shell with Node.js.",{"category":30,"check":161,"severity":24,"summary":162},"README","The README file exists and clearly states the extension's purpose and usage.",{"category":70,"check":164,"severity":39,"summary":165},"Tool surface size","This is a single-function skill triggered by a command, not a collection of tools.",{"category":22,"check":167,"severity":39,"summary":168},"Overlapping near-synonym tools","The skill has no user-facing tools to have overlapping names.",{"category":30,"check":170,"severity":24,"summary":171},"Phantom features","All advertised features in the README and description have corresponding implementation in the provided code.",{"category":173,"check":174,"severity":24,"summary":175},"Install","Installation instruction","The README provides clear installation and invocation instructions, including an example command.",{"category":177,"check":178,"severity":24,"summary":179},"Errors","Actionable error messages","The skill implicitly provides actionable error messages by directly reading the log; failure to read means no output, indicating the log is unavailable or malformed.",{"category":138,"check":181,"severity":39,"summary":182},"Pinned dependencies","The skill does not appear to use any third-party dependencies that would require pinning.",{"category":70,"check":184,"severity":39,"summary":185},"Dry-run preview","The skill is read-only and does not perform state-changing operations.",{"category":187,"check":188,"severity":39,"summary":189},"Protocol","Idempotent retry & timeouts","The skill does not involve remote calls or state-changing operations that require idempotency or timeouts.",{"category":151,"check":191,"severity":24,"summary":192},"Telemetry opt-in","The skill writes to a local suffix file for savings, which appears to be opt-in behavior and not broadcast telemetry.",1778691906001,"This skill reads the Claude Code session log to display real token usage and estimated savings without AI estimation. It is triggered by the `/caveman-stats` command and injects output via a mode-tracker hook.",[196,197,198,199],"Reads token usage directly from session logs","Estimates savings against a baseline","Outputs injection via mode-tracker hook","Writes lifetime-savings suffix file for statusline badge",[201,202,203],"Computing token usage via AI estimation","Modifying the session log or user's environment","Providing analysis beyond direct token counts and savings","3.0.0","4.4.0","To provide developers with precise, real-time insights into their token consumption and potential cost savings during a session by directly reading session logs.","The skill is well-documented, production-ready, and has a clear unique selling proposition. The only notable finding is the lack of formal versioning, which is a minor concern for such a focused tool.",96,"A highly polished and practical skill for tracking token usage directly from session logs.",[211,212,213,214],"developer-tools","code-analysis","logging","monitoring","global","community",[218,219,220],"Use when you need to understand exact token costs for a session.","Use to monitor usage and optimize prompt engineering for cost-efficiency.","Use to verify savings claims of other tools or techniques.",{"codeQuality":222,"collectedAt":224,"documentation":225,"maintenance":228,"popularity":234,"security":235,"testCoverage":238},{"hasLockfile":223},false,1778691884164,{"descriptionLength":226,"readmeSize":227},257,10896,{"closedIssues90d":229,"forks":230,"hasChangelog":223,"openIssues90d":231,"pushedAt":232,"stars":233},70,3292,66,1778615088000,59509,{"npmDownloads":8},{"hasNpmPackage":236,"license":237,"smitheryVerified":223},true,"MIT",{"hasCi":236,"hasTests":236},{"updatedAt":240},1778691906284,{"basePath":242,"githubOwner":243,"githubRepo":244,"locale":18,"slug":13,"type":245},"skills/caveman-stats","juliusbrussee","caveman","skill",{"_creationTime":247,"_id":248,"community":249,"display":250,"identity":254,"parentExtension":257,"providers":289,"relations":297,"tags":298,"workflow":299},1778691765524.373,"k170g496f5ze5hv8xa2e7b91ex86mz9m",{"reviewCount":8},{"description":251,"installMethods":252,"name":253,"sourceUrl":14},"Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.",{"claudeCode":244},"Caveman",{"basePath":255,"githubOwner":243,"githubRepo":244,"locale":18,"slug":244,"type":256},"","plugin",{"_creationTime":258,"_id":259,"community":260,"display":261,"identity":264,"providers":266,"relations":282,"tags":284,"workflow":285},1778691765524.3728,"k17dcfwpwpzjc43zt2qawvft3h86mmse",{"reviewCount":8},{"description":262,"installMethods":263,"name":244,"sourceUrl":14},"Ultra-compressed communication mode for Claude Code. Cuts ~75% of tokens while keeping full technical accuracy.",{"claudeCode":12},{"basePath":255,"githubOwner":243,"githubRepo":244,"locale":18,"slug":244,"type":265},"marketplace",{"evaluate":267,"extract":276},{"promptVersionExtension":268,"promptVersionScoring":205,"score":269,"tags":270,"targetMarket":215,"tier":275},"3.1.0",92,[271,272,273,274,211],"compression","llm","productivity","token-reduction","verified",{"commitSha":277,"marketplace":278,"plugin":280},"HEAD",{"name":244,"pluginCount":279},1,{"mcpCount":8,"provider":281,"skillCount":8},"classify",{"repoId":283},"kd7890f0sfy0ymf1pakpx7vqch86nmew",[271,211,272,273,274],{"evaluatedAt":286,"extractAt":287,"updatedAt":288},1778691801317,1778691765524,1778692173865,{"evaluate":290,"extract":294},{"promptVersionExtension":204,"promptVersionScoring":205,"score":291,"tags":292,"targetMarket":215,"tier":275},99,[271,272,293,211,273],"text",{"commitSha":277,"license":237,"plugin":295},{"mcpCount":8,"provider":281,"skillCount":296},6,{"parentExtensionId":259,"repoId":283},[271,211,272,273,293],{"evaluatedAt":300,"extractAt":287,"updatedAt":301},1778691819811,1778692174193,{"evaluate":303,"extract":305},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":304,"targetMarket":215,"tier":216},[211,212,213,214],{"commitSha":277},{"parentExtensionId":248,"repoId":283},{"_creationTime":308,"_id":283,"identity":309,"providers":310,"workflow":492},1778691760140.7458,{"githubOwner":243,"githubRepo":244,"sourceUrl":14},{"classify":311,"discover":476,"extract":479,"github":480,"npm":491},{"commitSha":277,"extensions":312},[313,323,334,378,387,395,420,426,435,444,453,465],{"basePath":314,"displayName":315,"installMethods":316,"rationale":317,"selectedPaths":318,"source":322,"sourceLanguage":18,"type":265},".agents/plugins","caveman-repo",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json",[319],{"path":320,"priority":321},"marketplace.json","mandatory","rule",{"basePath":255,"description":262,"displayName":244,"installMethods":324,"rationale":325,"selectedPaths":326,"source":322,"sourceLanguage":18,"type":265},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[327,329,331],{"path":328,"priority":321},".claude-plugin/marketplace.json",{"path":330,"priority":321},"README.md",{"path":332,"priority":333},"LICENSE","high",{"basePath":255,"description":251,"displayName":244,"installMethods":335,"rationale":336,"selectedPaths":337,"source":322,"sourceLanguage":18,"type":256},{"claudeCode":244},"plugin manifest at .claude-plugin/plugin.json (coalesced with duplicate plugin at plugins/caveman)",[338,340,341,342,345,347,349,351,353,355,357,359,361,363,366,368,370,372,374,376],{"path":339,"priority":321},".claude-plugin/plugin.json",{"path":330,"priority":321},{"path":332,"priority":333},{"path":343,"priority":344},"skills/cavecrew/SKILL.md","medium",{"path":346,"priority":344},"skills/caveman/SKILL.md",{"path":348,"priority":344},"skills/caveman-commit/SKILL.md",{"path":350,"priority":344},"skills/caveman-compress/SKILL.md",{"path":352,"priority":344},"skills/caveman-help/SKILL.md",{"path":354,"priority":344},"skills/caveman-review/SKILL.md",{"path":356,"priority":344},"skills/caveman-stats/SKILL.md",{"path":358,"priority":333},"agents/cavecrew-builder.md",{"path":360,"priority":333},"agents/cavecrew-investigator.md",{"path":362,"priority":333},"agents/cavecrew-reviewer.md",{"path":364,"priority":365},"bin/install.js","low",{"path":367,"priority":365},"bin/lib/openclaw.js",{"path":369,"priority":365},"bin/lib/settings.js",{"path":371,"priority":333},"commands/caveman-commit.toml",{"path":373,"priority":333},"commands/caveman-init.toml",{"path":375,"priority":333},"commands/caveman-review.toml",{"path":377,"priority":333},"commands/caveman.toml",{"basePath":379,"description":380,"displayName":381,"installMethods":382,"rationale":383,"selectedPaths":384,"source":322,"sourceLanguage":18,"type":245},".junie/skills/cavecrew","Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: \"delegate to subagent\", \"use cavecrew\", \"spawn investigator/builder/reviewer\", \"save context\", \"compressed agent output\".\n","cavecrew",{"claudeCode":12},"SKILL.md frontmatter at .junie/skills/cavecrew/SKILL.md (coalesced with duplicate skill at .agents/skills/cavecrew, skills/cavecrew, .roo/skills/cavecrew, .kiro/skills/cavecrew, plugins/caveman/skills/cavecrew)",[385],{"path":386,"priority":321},"SKILL.md",{"basePath":388,"description":389,"displayName":244,"installMethods":390,"rationale":391,"selectedPaths":392,"source":322,"sourceLanguage":18,"type":245},"skills/caveman","Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes /caveman. Also auto-triggers when token efficiency is requested.\n",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman/SKILL.md (coalesced with duplicate skill at plugins/caveman/skills/caveman)",[393,394],{"path":386,"priority":321},{"path":330,"priority":333},{"basePath":396,"description":397,"displayName":398,"installMethods":399,"rationale":400,"selectedPaths":401,"source":322,"sourceLanguage":18,"type":245},"skills/caveman-compress","Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or \"compress memory file\"\n","caveman-compress",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-compress/SKILL.md (coalesced with duplicate skill at plugins/caveman/skills/caveman-compress)",[402,403,404,406,408,410,412,414,416,418],{"path":386,"priority":321},{"path":330,"priority":333},{"path":405,"priority":344},"SECURITY.md",{"path":407,"priority":365},"scripts/__init__.py",{"path":409,"priority":365},"scripts/__main__.py",{"path":411,"priority":365},"scripts/benchmark.py",{"path":413,"priority":365},"scripts/cli.py",{"path":415,"priority":365},"scripts/compress.py",{"path":417,"priority":365},"scripts/detect.py",{"path":419,"priority":365},"scripts/validate.py",{"basePath":242,"description":10,"displayName":13,"installMethods":421,"rationale":422,"selectedPaths":423,"source":322,"sourceLanguage":18,"type":245},{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-stats/SKILL.md (coalesced with duplicate skill at plugins/caveman/skills/caveman-stats)",[424,425],{"path":386,"priority":321},{"path":330,"priority":333},{"basePath":427,"description":428,"displayName":429,"installMethods":430,"rationale":431,"selectedPaths":432,"source":322,"sourceLanguage":18,"type":245},"skills/caveman-commit","Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when \"why\" isn't obvious. Use when user says \"write a commit\", \"commit message\", \"generate commit\", \"/commit\", or invokes /caveman-commit. Auto-triggers when staging changes.\n","caveman-commit",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-commit/SKILL.md",[433,434],{"path":386,"priority":321},{"path":330,"priority":333},{"basePath":436,"description":437,"displayName":438,"installMethods":439,"rationale":440,"selectedPaths":441,"source":322,"sourceLanguage":18,"type":245},"skills/caveman-help","Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, \"caveman help\", \"what caveman commands\", \"how do I use caveman\".\n","caveman-help",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-help/SKILL.md",[442,443],{"path":386,"priority":321},{"path":330,"priority":333},{"basePath":445,"description":446,"displayName":447,"installMethods":448,"rationale":449,"selectedPaths":450,"source":322,"sourceLanguage":18,"type":245},"skills/caveman-review","Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says \"review this PR\", \"code review\", \"review the diff\", \"/review\", or invokes /caveman-review. Auto-triggers when reviewing pull requests.\n","caveman-review",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-review/SKILL.md",[451,452],{"path":386,"priority":321},{"path":330,"priority":333},{"basePath":255,"description":454,"displayName":455,"installMethods":456,"license":237,"rationale":457,"selectedPaths":458,"source":322,"sourceLanguage":18,"type":464},"Caveman installer — detects your AI coding agents and installs caveman for each one.","caveman-installer",{"npm":455},"cli ecosystem detected at /",[459,461,462,463],{"path":460,"priority":321},"package.json",{"path":330,"priority":321},{"path":332,"priority":333},{"path":364,"priority":344},"cli",{"basePath":466,"description":467,"displayName":468,"installMethods":469,"license":237,"rationale":470,"selectedPaths":471,"source":322,"sourceLanguage":18,"type":464},"src/mcp-servers/caveman-shrink","MCP proxy that compresses prose fields (tool descriptions, etc.) using caveman rules. Same accuracy, fewer context tokens.","caveman-shrink",{"npm":468},"cli ecosystem detected at src/mcp-servers/caveman-shrink",[472,473,474],{"path":460,"priority":321},{"path":330,"priority":321},{"path":475,"priority":344},"index.js",{"sources":477},[478],"manual",{"npmPackage":455},{"closedIssues90d":229,"description":481,"forks":230,"homepage":482,"license":237,"openIssues90d":231,"pushedAt":232,"readmeSize":227,"stars":233,"topics":483},"🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman","https://getcaveman.dev/",[484,485,244,486,487,272,488,489,245,490],"ai","anthropic","claude","claude-code","meme","prompt-engineering","tokens",{"downloads":8},{"classifiedAt":493,"discoverAt":494,"extractAt":495,"githubAt":495,"npmAt":496,"updatedAt":493},1778691765329,1778691760140,1778691762475,1778691764072,[212,211,213,214],{"evaluatedAt":240,"extractAt":287,"updatedAt":499},1778692174731,[],[502,531,557,587,618,646],{"_creationTime":503,"_id":504,"community":505,"display":506,"identity":512,"providers":515,"relations":524,"tags":526,"workflow":527},1778699438912.8826,"k170fxxh22hdspg4vr94whgj1986mpr9",{"reviewCount":8},{"description":507,"installMethods":508,"name":510,"sourceUrl":511},"Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.",{"claudeCode":509},"yvgude/lean-ctx","lean-ctx","https://github.com/yvgude/lean-ctx",{"basePath":513,"githubOwner":514,"githubRepo":510,"locale":18,"slug":510,"type":245},"skills/lean-ctx","yvgude",{"evaluate":516,"extract":523},{"promptVersionExtension":204,"promptVersionScoring":205,"score":517,"tags":518,"targetMarket":215,"tier":275},100,[519,520,521,211,522,212],"context-compression","ai-agent","cli-tools","rust",{"commitSha":277},{"repoId":525},"kd7dxtfr9j3z54hs3bz0218e1n86may0",[520,521,212,519,211,522],{"evaluatedAt":528,"extractAt":529,"updatedAt":530},1778699456179,1778699438912,1778699517795,{"_creationTime":532,"_id":533,"community":534,"display":535,"identity":541,"providers":545,"relations":551,"tags":553,"workflow":554},1778694240519.7402,"k172jnxq28h65x6zn1p19r731586md2x",{"reviewCount":8},{"description":536,"installMethods":537,"name":539,"sourceUrl":540},"Track skill performance and emerging patterns",{"claudeCode":538},"mshadmanrahman/pm-pilot","meta-observer","https://github.com/mshadmanrahman/pm-pilot",{"basePath":542,"githubOwner":543,"githubRepo":544,"locale":18,"slug":539,"type":245},"skills/productivity/meta-observer","mshadmanrahman","pm-pilot",{"evaluate":546,"extract":550},{"promptVersionExtension":204,"promptVersionScoring":205,"score":517,"tags":547,"targetMarket":215,"tier":275},[214,548,273,213,549],"analytics","skills",{"commitSha":277},{"repoId":552},"kd728wqst6vwd95ymycxb97nrx86mnsn",[548,213,214,273,549],{"evaluatedAt":555,"extractAt":556,"updatedAt":555},1778694605108,1778694240519,{"_creationTime":558,"_id":559,"community":560,"display":561,"identity":567,"providers":572,"relations":580,"tags":583,"workflow":584},1778695548458.377,"k17esa27yncbsd0bz8hcg2crg986mjqk",{"reviewCount":8},{"description":562,"installMethods":563,"name":565,"sourceUrl":566},"Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.\n",{"claudeCode":564},"pjt222/agent-almanac","Metal","https://github.com/pjt222/agent-almanac",{"basePath":568,"githubOwner":569,"githubRepo":570,"locale":18,"slug":571,"type":245},"skills/metal","pjt222","agent-almanac","metal",{"evaluate":573,"extract":579},{"promptVersionExtension":204,"promptVersionScoring":205,"score":517,"tags":574,"targetMarket":215,"tier":275},[212,575,576,577,578],"conceptualization","agent-definition","repository-structure","software-architecture",{"commitSha":277,"license":237},{"parentExtensionId":581,"repoId":582},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[576,212,575,577,578],{"evaluatedAt":585,"extractAt":586,"updatedAt":585},1778699463464,1778695548458,{"_creationTime":588,"_id":589,"community":590,"display":591,"identity":597,"providers":602,"relations":611,"tags":613,"workflow":614},1778698056313.1528,"k176pxdjxvnyex7jv6abt3myd586n5vv",{"reviewCount":8},{"description":592,"installMethods":593,"name":595,"sourceUrl":596},"Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to \"find the ideal path,\" unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.",{"claudeCode":594},"thedotmack/claude-mem","Pathfinder","https://github.com/thedotmack/claude-mem",{"basePath":598,"githubOwner":599,"githubRepo":600,"locale":18,"slug":601,"type":245},"plugin/skills/pathfinder","thedotmack","claude-mem","pathfinder",{"evaluate":603,"extract":609},{"promptVersionExtension":204,"promptVersionScoring":205,"score":517,"tags":604,"targetMarket":215,"tier":275},[212,605,606,607,608],"architecture","documentation","refactoring","flowchart",{"commitSha":277,"license":610},"Apache-2.0",{"repoId":612},"kd70jnxgm695az2wtf37zbqdj986mp7k",[605,212,606,608,607],{"evaluatedAt":615,"extractAt":616,"updatedAt":617},1778698228002,1778698056313,1778698443446,{"_creationTime":619,"_id":620,"community":621,"display":622,"identity":628,"providers":631,"relations":640,"tags":642,"workflow":643},1778694578248.103,"k17712r7xw99tfa8w7xzre9a4d86m8re",{"reviewCount":8},{"description":623,"installMethods":624,"name":626,"sourceUrl":627},"Codacy Cloud workflow for this repository -- run Codacy's analyzers locally before `git push` (mirrors what Codacy CI runs), and fetch/cluster Codacy issues for any PR via the v3 API. Use when the user mentions Codacy, \"codacy analysis\", `codacy-analysis-cli`, \"codacy issues on PR\", \"fix codacy CI\", \"codacy markdownlint findings\", or any Codacy gate failing on a netdata-org PR. Ships scripts analyze-local.sh (docker/binary runner for codacy-analysis-cli) and pr-issues.sh (paginated v3 issue fetch + group-by tool/pattern/severity/file). Token-safe -- CODACY_TOKEN never reaches assistant-visible stdout. Read-only by design in the current SOW; write actions (mark FP, mark fixed) are deferred.",{"claudeCode":625},"netdata/netdata","codacy-audit","https://github.com/netdata/netdata",{"basePath":629,"githubOwner":630,"githubRepo":630,"locale":18,"slug":626,"type":245},".agents/skills/codacy-audit","netdata",{"evaluate":632,"extract":639},{"promptVersionExtension":204,"promptVersionScoring":205,"score":517,"tags":633,"targetMarket":215,"tier":275},[634,212,635,636,637,638],"codacy","ci","pr-review","linting","security-analysis",{"commitSha":277},{"repoId":641},"kd70yp91ybn40a638h3hzz6nbd86m2cw",[635,634,212,637,636,638],{"evaluatedAt":644,"extractAt":645,"updatedAt":644},1778694601008,1778694578248,{"_creationTime":647,"_id":648,"community":649,"display":650,"identity":656,"providers":660,"relations":668,"tags":671,"workflow":672},1778692488329.0144,"k1724vjyyetw8qcfh8anb4c3tn86ngy7",{"reviewCount":8},{"description":651,"installMethods":652,"name":654,"sourceUrl":655},"Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.",{"claudeCode":653},"luiseiman/claude-kit","domain-extract","https://github.com/luiseiman/claude-kit",{"basePath":657,"githubOwner":658,"githubRepo":659,"locale":18,"slug":654,"type":245},"skills/domain-extract","luiseiman","claude-kit",{"evaluate":661,"extract":667},{"promptVersionExtension":204,"promptVersionScoring":205,"score":517,"tags":662,"targetMarket":215,"tier":275},[663,664,665,212,666],"domain-extraction","knowledge-management","rule-generation","automation",{"commitSha":277},{"parentExtensionId":669,"repoId":670},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[666,212,663,664,665],{"evaluatedAt":673,"extractAt":674,"updatedAt":673},1778693090713,1778692488329]