[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-juliusbrussee-cavecrew-en":3,"guides-for-juliusbrussee-cavecrew":464,"similar-k179fxhy0wd4jfc8rbxxb0fx0s86nc3w-en":465},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":250,"isFallback":232,"parentExtension":256,"providers":257,"relations":262,"repo":264,"tags":460,"workflow":461},1778691765524.3733,"k179fxhy0wd4jfc8rbxxb0fx0s86nc3w",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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",{"claudeCode":12},"juliusbrussee/caveman","Caveman","https://github.com/juliusbrussee/caveman",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":230,"workflow":248},1778691840545.9246,"kn704fcay8z6ks8tx4m19d698586ntan","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":199,"practices":204,"prerequisites":205,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"targetMarket":218,"tier":219,"useCases":220,"workflow":225},[21,26,29,32,36,39,43,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem of context exhaustion in long AI sessions and the specific need for smaller subagent outputs.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a unique value proposition by significantly reducing token usage from subagent outputs, extending main context lifespan and improving efficiency, which goes beyond default LLM behavior.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a complete lifecycle for delegating tasks to specialized subagents and managing their compressed output, making it usable in real workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on the specific domain of decision guidance for delegating to specialized, caveman-style subagents to manage context size.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's functionality, including its purpose, subagents, and the benefits of compressed output.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill exposes well-defined, narrow tools like `cavecrew-investigator`, `cavecrew-builder`, and `cavecrew-reviewer`, which are specialized verb-noun actions.",{"category":44,"check":45,"severity":46,"summary":47},"Documentation","Configuration & parameter reference","not_applicable","The skill does not appear to have configurable options or parameters beyond the trigger phrases mentioned in the description.",{"category":33,"check":49,"severity":24,"summary":50},"Tool naming","The tool names (`cavecrew-investigator`, `cavecrew-builder`, `cavecrew-reviewer`) are descriptive and align with their defined actions.",{"category":33,"check":52,"severity":24,"summary":53},"Minimal I/O surface","The inputs for the subagents are implicitly defined by the prompt context, and the output contracts are clearly documented in the SKILL.md, returning only promised payloads.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension is licensed under the MIT license, which is permissive and clearly stated in the LICENSE file and README.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The last commit was on May 12, 2026, which is recent.",{"category":59,"check":63,"severity":46,"summary":64},"Dependency Management","The extension does not appear to have external third-party dependencies that require management.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill does not appear to handle or expose any secrets, and its operations are focused on code analysis and manipulation within the project scope.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill operates on code and structured output, with no indication of loading or executing untrusted third-party data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill is self-contained and does not fetch external code or data at runtime, mitigating supply-chain risks.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill focuses on code analysis and manipulation within the project scope, with no indication of writing to paths outside the project folder.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached process spawns or deny-retry loops were detected in the provided scripts.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's operations are confined to code analysis and manipulation within the project scope, with no outbound calls or submission of confidential data.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content and descriptions appear to be free of hidden-steering tricks, control characters, or other obfuscation methods.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's logic appears to be in plain, readable format within the SKILL.md file, with no obfuscated code.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill operates on code structures and file paths provided within the project context, without making assumptions about external project organization.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","66 issues opened and 70 closed in the last 90 days, indicating active maintenance with a healthy closure rate.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The SKILL.md frontmatter includes a 'version: 0.1.0', indicating a declared version.",{"category":104,"check":105,"severity":46,"summary":106},"Code Execution","Validation","The skill's primary function is guiding LLM behavior, not direct execution of user-provided input that requires schema validation.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill focuses on code analysis and decision guidance, not destructive operations that would require confirmation gates.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The SKILL.md documents output contracts and potential failure modes for subagents, providing guidance for error scenarios.",{"category":104,"check":114,"severity":46,"summary":115},"Logging","The skill's nature as a decision-making guide doesn't involve destructive actions or outbound calls that would necessitate a local audit log.",{"category":117,"check":118,"severity":46,"summary":119},"Compliance","GDPR","The skill operates on code and project structure, not personal data.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The extension is generally applicable to any codebase and does not exhibit regional or jurisdictional restrictions; therefore, the target market is global.",{"category":92,"check":124,"severity":24,"summary":125},"Runtime stability","The skill is designed to work with Claude Code and general LLM interactions, without assuming specific editors, shells, or OS environments beyond standard LLM interfaces.",{"category":44,"check":127,"severity":24,"summary":128},"README","The README provides a comprehensive overview, installation instructions, and usage examples.",{"category":33,"check":130,"severity":24,"summary":131},"Tool surface size","The skill exposes three well-defined subagent tools (`investigator`, `builder`, `reviewer`), fitting within the target range.",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","The three subagent tools (`investigator`, `builder`, `reviewer`) represent distinct, non-overlapping functionalities.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features, including the caveman subagents and their output compression, are implemented and documented.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for various platforms and mentions how to trigger the skill.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The SKILL.md outlines specific failure modes for subagents with observable symptoms and recovery steps.",{"category":147,"check":148,"severity":46,"summary":149},"Execution","Pinned dependencies","The skill does not utilize third-party dependencies or scripts requiring explicit pinning.",{"category":33,"check":151,"severity":46,"summary":152},"Dry-run preview","The skill's function is decision guidance and code analysis, not state-changing operations that would benefit from a dry-run mode.",{"category":154,"check":155,"severity":46,"summary":156},"Protocol","Idempotent retry & timeouts","The skill does not involve remote calls or state-changing operations that would require idempotency or timeouts.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The extension does not appear to emit any telemetry.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly defines the skill's purpose: guiding delegation to specialized subagents for context management, and names specific subagents and triggers.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and trigger phrases.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md content is well-structured and stays within a reasonable length, delegating bulk material to other files.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines the flow and correctly links to other files for detailed information, demonstrating progressive disclosure.",{"category":170,"check":174,"severity":46,"summary":175},"Forked exploration","The skill is a decision guide and does not involve deep code exploration that would necessitate forking context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","Sufficient examples are provided in the SKILL.md and README, demonstrating the use of subagents and their expected outputs.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The SKILL.md documents failure modes for the subagents, such as `too-big.`, `needs-confirm.`, and `ambiguous.`, with associated recovery guidance.",{"category":104,"check":183,"severity":46,"summary":184},"Tool Fallback","The skill does not appear to rely on an external MCP server; it functions as a direct skill.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The documentation details failure modes for subagents like 'too-big.', 'ambiguous.', and 'regressed.', which effectively halt specific workflow steps and provide feedback.",{"category":92,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill operates standalone and clearly defines its scope, cross-linking to related concepts without implicit reliance on other skills.",1778691840403,"This skill acts as a decision guide, determining when to delegate tasks to specific 'caveman-style' subagents (`investigator`, `builder`, `reviewer`) for code location, editing, or review. Its core benefit is compressing subagent output tokens, significantly extending the main agent's context lifespan across long sessions.",[195,196,197,198],"Delegates to specialized subagents for code investigation, building, and review.","Compresses subagent output to reduce main context token usage by ~75%.","Provides structured output contracts for subagent results.","Offers decision guidance on when to use cavecrew subagents versus vanilla Explore or main thread actions.",[200,201,202,203],"Providing general prose-based code analysis or architectural opinions.","Performing deep code reviews requiring subjective feedback.","Handling large refactors or changes across more than two files via the builder agent.","Replacing the main agent's core capabilities when context is not a constraint.",[],[],"3.0.0","4.4.0","To enable agents to perform complex code-related tasks more efficiently by intelligently delegating to specialized subagents and reducing token consumption, thereby extending the agent's context and capability over longer sessions.","The extension is exceptionally well-documented and robust, with a clear purpose and excellent practical utility. All checks passed with high marks.",99,"A highly polished skill that intelligently delegates tasks to specialized subagents to optimize context usage and efficiency.",[213,214,215,216,217],"code-delegation","agent-workflow","context-management","code-analysis","developer-tools","global","verified",[221,222,223,224],"When needing to find specific code definitions or usages across a project.","When performing small, scoped edits to one or two files.","When reviewing code changes for bugs or issues.","To manage LLM context window limitations during long coding sessions.",[226,227,228,229],"Main thread determines if delegation is needed based on task complexity and context.","Selects appropriate cavecrew subagent (`investigator`, `builder`, or `reviewer`) based on the task.","Subagent executes, producing compressed, structured output.","Main thread injects compressed output back into context, preserving session length.",{"codeQuality":231,"collectedAt":233,"documentation":234,"maintenance":237,"popularity":243,"security":244,"testCoverage":247},{"hasLockfile":232},false,1778691820065,{"descriptionLength":235,"readmeSize":236},553,10896,{"closedIssues90d":238,"forks":239,"hasChangelog":232,"openIssues90d":240,"pushedAt":241,"stars":242},70,3292,66,1778615088000,59509,{"npmDownloads":8},{"hasNpmPackage":245,"license":246,"smitheryVerified":232},true,"MIT",{"hasCi":245,"hasTests":245},{"updatedAt":249},1778691840545,{"basePath":251,"githubOwner":252,"githubRepo":253,"locale":18,"slug":254,"type":255},".junie/skills/cavecrew","juliusbrussee","caveman","cavecrew","skill",null,{"evaluate":258,"extract":260},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":259,"targetMarket":218,"tier":219},[213,214,215,216,217],{"commitSha":261,"license":246},"HEAD",{"repoId":263},"kd7890f0sfy0ymf1pakpx7vqch86nmew",{"_creationTime":265,"_id":263,"identity":266,"providers":267,"workflow":455},1778691760140.7458,{"githubOwner":252,"githubRepo":253,"sourceUrl":14},{"classify":268,"discover":438,"extract":441,"github":442,"npm":454},{"commitSha":261,"extensions":269},[270,281,294,340,346,354,379,388,397,406,415,427],{"basePath":271,"displayName":272,"installMethods":273,"rationale":274,"selectedPaths":275,"source":279,"sourceLanguage":18,"type":280},".agents/plugins","caveman-repo",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json",[276],{"path":277,"priority":278},"marketplace.json","mandatory","rule","marketplace",{"basePath":282,"description":283,"displayName":253,"installMethods":284,"rationale":285,"selectedPaths":286,"source":279,"sourceLanguage":18,"type":280},"","Ultra-compressed communication mode for Claude Code. Cuts ~75% of tokens while keeping full technical accuracy.",{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[287,289,291],{"path":288,"priority":278},".claude-plugin/marketplace.json",{"path":290,"priority":278},"README.md",{"path":292,"priority":293},"LICENSE","high",{"basePath":282,"description":295,"displayName":253,"installMethods":296,"rationale":297,"selectedPaths":298,"source":279,"sourceLanguage":18,"type":339},"Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.",{"claudeCode":253},"plugin manifest at .claude-plugin/plugin.json (coalesced with duplicate plugin at plugins/caveman)",[299,301,302,303,306,308,310,312,314,316,318,320,322,324,327,329,331,333,335,337],{"path":300,"priority":278},".claude-plugin/plugin.json",{"path":290,"priority":278},{"path":292,"priority":293},{"path":304,"priority":305},"skills/cavecrew/SKILL.md","medium",{"path":307,"priority":305},"skills/caveman/SKILL.md",{"path":309,"priority":305},"skills/caveman-commit/SKILL.md",{"path":311,"priority":305},"skills/caveman-compress/SKILL.md",{"path":313,"priority":305},"skills/caveman-help/SKILL.md",{"path":315,"priority":305},"skills/caveman-review/SKILL.md",{"path":317,"priority":305},"skills/caveman-stats/SKILL.md",{"path":319,"priority":293},"agents/cavecrew-builder.md",{"path":321,"priority":293},"agents/cavecrew-investigator.md",{"path":323,"priority":293},"agents/cavecrew-reviewer.md",{"path":325,"priority":326},"bin/install.js","low",{"path":328,"priority":326},"bin/lib/openclaw.js",{"path":330,"priority":326},"bin/lib/settings.js",{"path":332,"priority":293},"commands/caveman-commit.toml",{"path":334,"priority":293},"commands/caveman-init.toml",{"path":336,"priority":293},"commands/caveman-review.toml",{"path":338,"priority":293},"commands/caveman.toml","plugin",{"basePath":251,"description":10,"displayName":254,"installMethods":341,"rationale":342,"selectedPaths":343,"source":279,"sourceLanguage":18,"type":255},{"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)",[344],{"path":345,"priority":278},"SKILL.md",{"basePath":347,"description":348,"displayName":253,"installMethods":349,"rationale":350,"selectedPaths":351,"source":279,"sourceLanguage":18,"type":255},"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)",[352,353],{"path":345,"priority":278},{"path":290,"priority":293},{"basePath":355,"description":356,"displayName":357,"installMethods":358,"rationale":359,"selectedPaths":360,"source":279,"sourceLanguage":18,"type":255},"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)",[361,362,363,365,367,369,371,373,375,377],{"path":345,"priority":278},{"path":290,"priority":293},{"path":364,"priority":305},"SECURITY.md",{"path":366,"priority":326},"scripts/__init__.py",{"path":368,"priority":326},"scripts/__main__.py",{"path":370,"priority":326},"scripts/benchmark.py",{"path":372,"priority":326},"scripts/cli.py",{"path":374,"priority":326},"scripts/compress.py",{"path":376,"priority":326},"scripts/detect.py",{"path":378,"priority":326},"scripts/validate.py",{"basePath":380,"description":381,"displayName":382,"installMethods":383,"rationale":384,"selectedPaths":385,"source":279,"sourceLanguage":18,"type":255},"skills/caveman-stats","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","caveman-stats",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-stats/SKILL.md (coalesced with duplicate skill at plugins/caveman/skills/caveman-stats)",[386,387],{"path":345,"priority":278},{"path":290,"priority":293},{"basePath":389,"description":390,"displayName":391,"installMethods":392,"rationale":393,"selectedPaths":394,"source":279,"sourceLanguage":18,"type":255},"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",[395,396],{"path":345,"priority":278},{"path":290,"priority":293},{"basePath":398,"description":399,"displayName":400,"installMethods":401,"rationale":402,"selectedPaths":403,"source":279,"sourceLanguage":18,"type":255},"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",[404,405],{"path":345,"priority":278},{"path":290,"priority":293},{"basePath":407,"description":408,"displayName":409,"installMethods":410,"rationale":411,"selectedPaths":412,"source":279,"sourceLanguage":18,"type":255},"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",[413,414],{"path":345,"priority":278},{"path":290,"priority":293},{"basePath":282,"description":416,"displayName":417,"installMethods":418,"license":246,"rationale":419,"selectedPaths":420,"source":279,"sourceLanguage":18,"type":426},"Caveman installer — detects your AI coding agents and installs caveman for each one.","caveman-installer",{"npm":417},"cli ecosystem detected at /",[421,423,424,425],{"path":422,"priority":278},"package.json",{"path":290,"priority":278},{"path":292,"priority":293},{"path":325,"priority":305},"cli",{"basePath":428,"description":429,"displayName":430,"installMethods":431,"license":246,"rationale":432,"selectedPaths":433,"source":279,"sourceLanguage":18,"type":426},"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":430},"cli ecosystem detected at src/mcp-servers/caveman-shrink",[434,435,436],{"path":422,"priority":278},{"path":290,"priority":278},{"path":437,"priority":305},"index.js",{"sources":439},[440],"manual",{"npmPackage":417},{"closedIssues90d":238,"description":443,"forks":239,"homepage":444,"license":246,"openIssues90d":240,"pushedAt":241,"readmeSize":236,"stars":242,"topics":445},"🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman","https://getcaveman.dev/",[446,447,253,448,449,450,451,452,255,453],"ai","anthropic","claude","claude-code","llm","meme","prompt-engineering","tokens",{"downloads":8},{"classifiedAt":456,"discoverAt":457,"extractAt":458,"githubAt":458,"npmAt":459,"updatedAt":456},1778691765329,1778691760140,1778691762475,1778691764072,[214,216,213,215,217],{"evaluatedAt":249,"extractAt":462,"updatedAt":463},1778691765524,1778692174361,[],[466,495,524,554,585,613],{"_creationTime":467,"_id":468,"community":469,"display":470,"identity":476,"providers":479,"relations":488,"tags":490,"workflow":491},1778699438912.8826,"k170fxxh22hdspg4vr94whgj1986mpr9",{"reviewCount":8},{"description":471,"installMethods":472,"name":474,"sourceUrl":475},"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":473},"yvgude/lean-ctx","lean-ctx","https://github.com/yvgude/lean-ctx",{"basePath":477,"githubOwner":478,"githubRepo":474,"locale":18,"slug":474,"type":255},"skills/lean-ctx","yvgude",{"evaluate":480,"extract":487},{"promptVersionExtension":206,"promptVersionScoring":207,"score":481,"tags":482,"targetMarket":218,"tier":219},100,[483,484,485,217,486,216],"context-compression","ai-agent","cli-tools","rust",{"commitSha":261},{"repoId":489},"kd7dxtfr9j3z54hs3bz0218e1n86may0",[484,485,216,483,217,486],{"evaluatedAt":492,"extractAt":493,"updatedAt":494},1778699456179,1778699438912,1778699517795,{"_creationTime":496,"_id":497,"community":498,"display":499,"identity":505,"providers":509,"relations":516,"tags":519,"workflow":520},1778693511416.3655,"k17dre81ghdhwnja4h61m340qd86m942",{"reviewCount":8},{"description":500,"installMethods":501,"name":503,"sourceUrl":504},"Run context-mode diagnostics. Checks runtimes, hooks, FTS5,\nplugin registration, npm and marketplace versions.\nTrigger: /context-mode:ctx-doctor\n",{"claudeCode":502},"mksglu/context-mode","ctx-doctor","https://github.com/mksglu/context-mode",{"basePath":506,"githubOwner":507,"githubRepo":508,"locale":18,"slug":503,"type":255},"skills/ctx-doctor","mksglu","context-mode",{"evaluate":510,"extract":515},{"promptVersionExtension":206,"promptVersionScoring":207,"score":481,"tags":511,"targetMarket":218,"tier":219},[215,217,512,513,514],"productivity","debugging","diagnostics",{"commitSha":261},{"parentExtensionId":517,"repoId":518},"k17ezy748es7sfnbnp9phht43h86m53y","kd764b2fctbqg4b8j8y6xvmkvs86m29m",[215,513,217,514,512],{"evaluatedAt":521,"extractAt":522,"updatedAt":523},1778693603549,1778693511416,1778693817685,{"_creationTime":525,"_id":526,"community":527,"display":528,"identity":534,"providers":539,"relations":547,"tags":550,"workflow":551},1778695548458.377,"k17esa27yncbsd0bz8hcg2crg986mjqk",{"reviewCount":8},{"description":529,"installMethods":530,"name":532,"sourceUrl":533},"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":531},"pjt222/agent-almanac","Metal","https://github.com/pjt222/agent-almanac",{"basePath":535,"githubOwner":536,"githubRepo":537,"locale":18,"slug":538,"type":255},"skills/metal","pjt222","agent-almanac","metal",{"evaluate":540,"extract":546},{"promptVersionExtension":206,"promptVersionScoring":207,"score":481,"tags":541,"targetMarket":218,"tier":219},[216,542,543,544,545],"conceptualization","agent-definition","repository-structure","software-architecture",{"commitSha":261,"license":246},{"parentExtensionId":548,"repoId":549},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[543,216,542,544,545],{"evaluatedAt":552,"extractAt":553,"updatedAt":552},1778699463464,1778695548458,{"_creationTime":555,"_id":556,"community":557,"display":558,"identity":564,"providers":569,"relations":578,"tags":580,"workflow":581},1778698056313.1528,"k176pxdjxvnyex7jv6abt3myd586n5vv",{"reviewCount":8},{"description":559,"installMethods":560,"name":562,"sourceUrl":563},"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":561},"thedotmack/claude-mem","Pathfinder","https://github.com/thedotmack/claude-mem",{"basePath":565,"githubOwner":566,"githubRepo":567,"locale":18,"slug":568,"type":255},"plugin/skills/pathfinder","thedotmack","claude-mem","pathfinder",{"evaluate":570,"extract":576},{"promptVersionExtension":206,"promptVersionScoring":207,"score":481,"tags":571,"targetMarket":218,"tier":219},[216,572,573,574,575],"architecture","documentation","refactoring","flowchart",{"commitSha":261,"license":577},"Apache-2.0",{"repoId":579},"kd70jnxgm695az2wtf37zbqdj986mp7k",[572,216,573,575,574],{"evaluatedAt":582,"extractAt":583,"updatedAt":584},1778698228002,1778698056313,1778698443446,{"_creationTime":586,"_id":587,"community":588,"display":589,"identity":595,"providers":598,"relations":607,"tags":609,"workflow":610},1778694578248.103,"k17712r7xw99tfa8w7xzre9a4d86m8re",{"reviewCount":8},{"description":590,"installMethods":591,"name":593,"sourceUrl":594},"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":592},"netdata/netdata","codacy-audit","https://github.com/netdata/netdata",{"basePath":596,"githubOwner":597,"githubRepo":597,"locale":18,"slug":593,"type":255},".agents/skills/codacy-audit","netdata",{"evaluate":599,"extract":606},{"promptVersionExtension":206,"promptVersionScoring":207,"score":481,"tags":600,"targetMarket":218,"tier":219},[601,216,602,603,604,605],"codacy","ci","pr-review","linting","security-analysis",{"commitSha":261},{"repoId":608},"kd70yp91ybn40a638h3hzz6nbd86m2cw",[602,601,216,604,603,605],{"evaluatedAt":611,"extractAt":612,"updatedAt":611},1778694601008,1778694578248,{"_creationTime":614,"_id":615,"community":616,"display":617,"identity":623,"providers":627,"relations":635,"tags":638,"workflow":639},1778692488329.0144,"k1724vjyyetw8qcfh8anb4c3tn86ngy7",{"reviewCount":8},{"description":618,"installMethods":619,"name":621,"sourceUrl":622},"Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.",{"claudeCode":620},"luiseiman/claude-kit","domain-extract","https://github.com/luiseiman/claude-kit",{"basePath":624,"githubOwner":625,"githubRepo":626,"locale":18,"slug":621,"type":255},"skills/domain-extract","luiseiman","claude-kit",{"evaluate":628,"extract":634},{"promptVersionExtension":206,"promptVersionScoring":207,"score":481,"tags":629,"targetMarket":218,"tier":219},[630,631,632,216,633],"domain-extraction","knowledge-management","rule-generation","automation",{"commitSha":261},{"parentExtensionId":636,"repoId":637},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[633,216,630,631,632],{"evaluatedAt":640,"extractAt":641,"updatedAt":640},1778693090713,1778692488329]