[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-rohitg00-llm-council-zh-CN":3,"guides-for-rohitg00-llm-council":819,"similar-k1782531n7gq0bdhans1kp3tr586mr8x-zh-CN":820},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":250,"isFallback":233,"parentExtension":256,"providers":317,"relations":321,"repo":322,"tags":817,"workflow":818},1778696595410.5647,"k1782531n7gq0bdhans1kp3tr586mr8x",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Provider config from env (OPENAI/ANTHROPIC/FIREWORKS/OPENROUTER/custom OpenAI-compatible base URL). Persists transcript to a wiki page when --wiki \u003Cslug> is passed. Use when the user wants multiple AI perspectives, consensus-building, or the \"LLM Council\" approach for high-stakes reviews, plan critique, or contested learning rules.",{"claudeCode":12},"rohitg00/pro-workflow","LLM Council","https://github.com/rohitg00/pro-workflow",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":231,"workflow":248},1778696824062.2654,"kn74n7wkx9x63zgw2mxzdthzgx86nxgp","en",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":203,"practices":207,"prerequisites":208,"promptVersionExtension":211,"promptVersionScoring":212,"purpose":213,"rationale":214,"score":215,"summary":216,"tags":217,"targetMarket":224,"tier":225,"useCases":226},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,188,192],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly identifies the problem of AI learning vanishing between sessions and proposes the solution of persistent memory and wikis, directly addressing user pain points.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers significant value beyond a thin wrapper by implementing a multi-phase LLM deliberation process, persistent knowledge planes, self-correction memory, and auto-research loops, which are not default LLM behaviors.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension appears production-ready, offering a complete lifecycle from learning capture to advanced knowledge management and multi-LLM deliberation, with clear installation and usage instructions.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses on enhancing AI agent capabilities through memory, knowledge management, and multi-LLM deliberation, with a coherent set of related skills and commands.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately and concisely reflects the extension's capabilities, including its multi-LLM deliberation, provider configuration, and wiki persistence features.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill primarily uses LLM calls via its own script and does not expose fine-grained tools in the traditional verb-noun sense.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","Environment variables for provider configuration and command-line arguments are clearly documented in the SKILL.md and README.md.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","The skill does not expose distinct tools; its primary interface is through commands and LLM interactions.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","The skill's core functionality is LLM interaction, not exposed tools with specific input/output schemas.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The MIT license is clearly indicated on the README and GitHub repository, allowing for permissive use.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The last commit was on 2026-05-12, indicating recent maintenance.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","The project uses npm and has a lockfile, indicating reasonable dependency management.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The extension handles API keys via environment variables, which is a secure practice, and does not appear to log or expose secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill's design for LLM interaction and its use of command-line arguments suggest a focus on treating user input as data, not instructions, for the LLM.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The extension relies on npm dependencies and local scripts, with no indication of runtime remote code fetching or execution of untrusted content.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The scripts appear to operate within the expected user directories and do not attempt to modify files outside their designated scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No evidence of detached processes or retry loops around denied tool calls was found in the provided script snippets.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The extension uses API keys via environment variables and does not appear to have any documented outbound calls for telemetry or data submission beyond LLM API calls.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled markdown and script files do not contain suspicious Unicode characters, HTML comments, or other hidden text tricks.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The provided `council.js` script is plain JavaScript, not obfuscated, base64-encoded, or dynamically fetched.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The script references the user's home directory for configuration and output, which is a standard and portable assumption.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","In the last 90 days, 0 issues were opened and 5 were closed, indicating good responsiveness and a healthy issue management process.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The project uses npm and has versioning (`npm/v/pro-workflow`), with a recent commit indicating active development.",{"category":104,"check":105,"severity":24,"summary":106},"Code Execution","Validation","The `council.js` script handles arguments and parameters, and the LLM interactions imply validation of inputs and outputs at the LLM level.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The extension primarily interacts with LLMs and configuration files; destructive operations are not a primary function and are likely guarded by user interaction.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The provided script includes basic error handling for API calls and file operations, with timeouts and explicit error messages.",{"category":104,"check":114,"severity":24,"summary":115},"Logging","The script logs API call latency, tokens, and errors to the console, and persists session data to disk for audit.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The extension does not explicitly handle personal data beyond API keys; LLM interactions may process prompts, but the responsibility lies with the LLM provider's compliance.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The extension is provider-agnostic and uses standard environment variables and file paths, making it globally applicable.",{"category":92,"check":124,"severity":24,"summary":125},"Runtime stability","The script uses standard Node.js modules and OS-agnostic paths, making it portable across POSIX-like systems.",{"category":45,"check":127,"severity":24,"summary":128},"README","The README is comprehensive, detailing the problem, solution, installation, usage, and architecture.",{"category":33,"check":130,"severity":42,"summary":131},"Tool surface size","This is a skill that primarily interacts with LLMs and does not expose a large number of distinct tools.",{"category":40,"check":133,"severity":42,"summary":134},"Overlapping near-synonym tools","The skill does not expose discrete tools that could have overlapping synonyms.",{"category":45,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features, such as multi-LLM deliberation, provider configuration, and wiki persistence, are implemented and described.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear installation instructions via `/plugin marketplace add` and `/plugin install`, along with usage examples.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The script includes error messages for API failures, missing configuration, and invalid arguments, providing guidance on remediation.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","The project utilizes npm with a lockfile, indicating pinned dependencies for reproducible builds.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The extension's core function is LLM interaction and data persistence, not state-changing operations that would require a dry-run preview.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The `postJSON` function includes a timeout, and API calls are handled with error checking, which helps manage potential retries.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The extension does not appear to emit telemetry by default; API calls are for LLM interaction and are not considered opt-out telemetry.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly defines the purpose (multi-LLM deliberation) and use cases (high-stakes reviews, consensus-building) for the skill.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise and effectively summarizes the skill's core capability and usage triggers.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured, with core instructions and delegation to README for deeper material, keeping the main body concise.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The README links to detailed documentation and reference guides, allowing for progressive disclosure of information.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","This skill does not involve deep code review or exploration that would necessitate a forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README provides clear, end-to-end examples for various commands and features, demonstrating their usage and expected outcomes.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation implicitly handles edge cases by specifying provider configuration and error handling for API calls.",{"category":104,"check":183,"severity":42,"summary":184},"Tool Fallback","The skill does not rely on external MCP servers or tools that would require a fallback mechanism.",{"category":92,"check":186,"severity":24,"summary":187},"Stack assumptions","The skill clearly states its Node.js dependency and reliance on environment variables for configuration.",{"category":189,"check":190,"severity":24,"summary":191},"Safety","Halt on unexpected state","The script includes error handling for API calls and configuration issues, causing it to halt and report on unexpected states.",{"category":92,"check":193,"severity":24,"summary":194},"Cross-skill coupling","The skill operates standalone and clearly defines its scope, without implicit reliance on other skills.",1778696823952,"This skill implements a provider-agnostic multi-LLM deliberation process with three phases: independent responses, cross-model ranking, and chairman synthesis. It supports various LLM providers via environment variables and can persist transcripts to a wiki page.",[198,199,200,201,202],"Provider-agnostic multi-LLM deliberation","Three-phase process (independent, ranking, synthesis)","Supports OpenAI, Anthropic, OpenRouter, Fireworks, and custom providers via env vars","Persists transcripts to wiki pages","Configurable model rosters and chairman selection",[204,205,206],"Acting as a direct replacement for individual LLM API calls without the deliberation framework","Providing pre-defined AI perspectives without user-defined queries","Managing LLM provider accounts or billing",[],[209,210],"LLM API keys configured via environment variables (e.g., ANTHROPIC_API_KEY, OPENAI_API_KEY)","Node.js runtime","3.0.0","4.4.0","To enable users to leverage multiple AI perspectives for high-stakes reviews, consensus-building, or critical decision-making by facilitating a structured multi-LLM deliberation process.","No critical or warning findings. The score is high due to excellent documentation, clear purpose, strong security, and recent maintenance, with no significant areas for improvement noted.",99,"Excellent skill with comprehensive documentation, strong security, and clear utility for multi-LLM deliberation and knowledge management.",[218,219,220,221,222,223],"llm","deliberation","multi-llm","knowledge-management","wiki","cli","global","verified",[227,228,229,230],"Gaining multiple AI perspectives for complex problems","Building consensus on critical decisions or plan critiques","Utilizing the 'LLM Council' approach for high-stakes reviews","Creating persistent, searchable wiki pages from AI deliberations",{"codeQuality":232,"collectedAt":234,"documentation":235,"maintenance":238,"popularity":244,"security":246,"testCoverage":247},{"hasLockfile":233},true,1778696809839,{"descriptionLength":236,"readmeSize":237},465,22012,{"closedIssues90d":239,"forks":240,"hasChangelog":241,"openIssues90d":8,"pushedAt":242,"stars":243},5,203,false,1778554780000,2113,{"npmDownloads":245},611,{"hasNpmPackage":233,"smitheryVerified":241},{"hasCi":233,"hasTests":241},{"updatedAt":249},1778696824062,{"basePath":251,"githubOwner":252,"githubRepo":253,"locale":18,"slug":254,"type":255},"skills/llm-council","rohitg00","pro-workflow","llm-council","skill",{"_creationTime":257,"_id":258,"community":259,"display":260,"identity":266,"parentExtension":269,"providers":299,"relations":313,"tags":314,"workflow":315},1778696595410.5615,"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv",{"reviewCount":8},{"description":261,"installMethods":262,"name":265,"sourceUrl":14},"Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.",{"claudeCode":253,"cursor":263,"npm":253,"skillkit":264},"/add-plugin pro-workflow","npx skillkit install pro-workflow","Pro Workflow",{"basePath":267,"githubOwner":252,"githubRepo":253,"locale":18,"slug":253,"type":268},"","plugin",{"_creationTime":270,"_id":271,"community":272,"display":273,"identity":276,"providers":278,"relations":293,"tags":295,"workflow":296},1778696595410.5613,"k1741gyqaf0tj1ffq65gjpsm6x86mfhx",{"reviewCount":8},{"description":274,"installMethods":275,"name":265,"sourceUrl":14},"Battle-tested Claude Code workflows from power users",{"claudeCode":12},{"basePath":267,"githubOwner":252,"githubRepo":253,"locale":18,"slug":253,"type":277},"marketplace",{"evaluate":279,"extract":286},{"promptVersionExtension":280,"promptVersionScoring":212,"score":215,"tags":281,"targetMarket":224,"tier":225},"3.1.0",[282,283,284,285,221],"workflow","productivity","ai-assistance","developer-tools",{"commitSha":287,"license":288,"marketplace":289,"plugin":291},"HEAD","MIT",{"name":253,"pluginCount":290},1,{"mcpCount":8,"provider":292,"skillCount":8},"classify",{"repoId":294},"kd7am4e918eq98hrd9s31jm4vs86nn0b",[284,285,221,283,282],{"evaluatedAt":297,"extractAt":298,"updatedAt":297},1778696611346,1778696595410,{"evaluate":300,"extract":310},{"promptVersionExtension":211,"promptVersionScoring":212,"score":301,"tags":302,"targetMarket":224,"tier":309},96,[282,283,303,304,305,306,307,308],"ai-coding","self-correction","knowledge-base","sqlite","hooks","agents","community",{"commitSha":287,"license":288,"plugin":311},{"mcpCount":8,"provider":292,"skillCount":312},34,{"parentExtensionId":271,"repoId":294},[308,303,307,305,283,304,306,282],{"evaluatedAt":316,"extractAt":298,"updatedAt":316},1778696621396,{"evaluate":318,"extract":320},{"promptVersionExtension":211,"promptVersionScoring":212,"score":215,"tags":319,"targetMarket":224,"tier":225},[218,219,220,221,222,223],{"commitSha":287,"license":288},{"parentExtensionId":258,"repoId":294},{"_creationTime":323,"_id":294,"identity":324,"providers":325,"workflow":812},1778696588306.821,{"githubOwner":252,"githubRepo":253,"sourceUrl":14},{"classify":326,"discover":791,"extract":794,"github":795,"npm":811},{"commitSha":287,"extensions":327},[328,338,479,488,496,504,512,520,528,536,544,552,560,568,576,584,592,600,608,616,624,632,640,647,655,663,671,679,687,699,707,715,747,757,773,783],{"basePath":267,"description":274,"displayName":253,"installMethods":329,"rationale":330,"selectedPaths":331,"source":337,"sourceLanguage":18,"type":277},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[332,335],{"path":333,"priority":334},".claude-plugin/marketplace.json","mandatory",{"path":336,"priority":334},"README.md","rule",{"basePath":267,"description":261,"displayName":253,"installMethods":339,"license":288,"rationale":340,"selectedPaths":341,"source":337,"sourceLanguage":18,"type":268},{"claudeCode":253},"plugin manifest at .claude-plugin/plugin.json",[342,344,345,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469,471,473,475,477],{"path":343,"priority":334},".claude-plugin/plugin.json",{"path":336,"priority":334},{"path":346,"priority":347},"skills/agent-teams/SKILL.md","medium",{"path":349,"priority":347},"skills/auto-setup/SKILL.md",{"path":351,"priority":347},"skills/batch-orchestration/SKILL.md",{"path":353,"priority":347},"skills/bug-capture/SKILL.md",{"path":355,"priority":347},"skills/compact-guard/SKILL.md",{"path":357,"priority":347},"skills/context-engineering/SKILL.md",{"path":359,"priority":347},"skills/context-optimizer/SKILL.md",{"path":361,"priority":347},"skills/cost-tracker/SKILL.md",{"path":363,"priority":347},"skills/deslop/SKILL.md",{"path":365,"priority":347},"skills/file-watcher/SKILL.md",{"path":367,"priority":347},"skills/insights/SKILL.md",{"path":369,"priority":347},"skills/learn-rule/SKILL.md",{"path":371,"priority":347},"skills/llm-council/SKILL.md",{"path":373,"priority":347},"skills/llm-gate/SKILL.md",{"path":375,"priority":347},"skills/mcp-audit/SKILL.md",{"path":377,"priority":347},"skills/module-map/SKILL.md",{"path":379,"priority":347},"skills/orchestrate/SKILL.md",{"path":381,"priority":347},"skills/parallel-worktrees/SKILL.md",{"path":383,"priority":347},"skills/permission-tuner/SKILL.md",{"path":385,"priority":347},"skills/plan-interrogate/SKILL.md",{"path":387,"priority":347},"skills/pro-workflow/SKILL.md",{"path":389,"priority":347},"skills/replay-learnings/SKILL.md",{"path":391,"priority":347},"skills/safe-mode/SKILL.md",{"path":393,"priority":347},"skills/session-handoff/SKILL.md",{"path":395,"priority":347},"skills/smart-commit/SKILL.md",{"path":397,"priority":347},"skills/sprint-status/SKILL.md",{"path":399,"priority":347},"skills/survey-generator/SKILL.md",{"path":401,"priority":347},"skills/thoroughness-scoring/SKILL.md",{"path":403,"priority":347},"skills/token-efficiency/SKILL.md",{"path":405,"priority":347},"skills/wiki-builder/SKILL.md",{"path":407,"priority":347},"skills/wiki-query/SKILL.md",{"path":409,"priority":347},"skills/wiki-research-loop/SKILL.md",{"path":411,"priority":347},"skills/wiki-viewer/SKILL.md",{"path":413,"priority":347},"skills/wrap-up/SKILL.md",{"path":415,"priority":416},"agents/context-engineer.md","high",{"path":418,"priority":416},"agents/cost-analyst.md",{"path":420,"priority":416},"agents/debugger.md",{"path":422,"priority":416},"agents/orchestrator.md",{"path":424,"priority":416},"agents/permission-analyst.md",{"path":426,"priority":416},"agents/planner.md",{"path":428,"priority":416},"agents/reviewer.md",{"path":430,"priority":416},"agents/scout.md",{"path":432,"priority":416},"commands/auto-setup.md",{"path":434,"priority":416},"commands/commit.md",{"path":436,"priority":416},"commands/compact-guard.md",{"path":438,"priority":416},"commands/context-optimizer.md",{"path":440,"priority":416},"commands/cost-tracker.md",{"path":442,"priority":416},"commands/deslop.md",{"path":444,"priority":416},"commands/develop.md",{"path":446,"priority":416},"commands/doctor.md",{"path":448,"priority":416},"commands/handoff.md",{"path":450,"priority":416},"commands/insights.md",{"path":452,"priority":416},"commands/learn-rule.md",{"path":454,"priority":416},"commands/learn.md",{"path":456,"priority":416},"commands/list.md",{"path":458,"priority":416},"commands/mcp-audit.md",{"path":460,"priority":416},"commands/parallel.md",{"path":462,"priority":416},"commands/permission-tuner.md",{"path":464,"priority":416},"commands/replay.md",{"path":466,"priority":416},"commands/safe-mode.md",{"path":468,"priority":416},"commands/search.md",{"path":470,"priority":416},"commands/sprint-status.md",{"path":472,"priority":416},"commands/wiki.md",{"path":474,"priority":416},"commands/wrap-up.md",{"path":476,"priority":416},"hooks/hooks.json",{"path":478,"priority":416},".cursor-plugin/plugin.json",{"basePath":480,"description":481,"displayName":482,"installMethods":483,"rationale":484,"selectedPaths":485,"source":337,"sourceLanguage":18,"type":255},"skills/agent-teams","Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.","agent-teams",{"claudeCode":12},"SKILL.md frontmatter at skills/agent-teams/SKILL.md",[486],{"path":487,"priority":334},"SKILL.md",{"basePath":489,"description":490,"displayName":491,"installMethods":492,"rationale":493,"selectedPaths":494,"source":337,"sourceLanguage":18,"type":255},"skills/auto-setup","Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.","auto-setup",{"claudeCode":12},"SKILL.md frontmatter at skills/auto-setup/SKILL.md",[495],{"path":487,"priority":334},{"basePath":497,"description":498,"displayName":499,"installMethods":500,"rationale":501,"selectedPaths":502,"source":337,"sourceLanguage":18,"type":255},"skills/batch-orchestration","Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.","batch-orchestration",{"claudeCode":12},"SKILL.md frontmatter at skills/batch-orchestration/SKILL.md",[503],{"path":487,"priority":334},{"basePath":505,"description":506,"displayName":507,"installMethods":508,"rationale":509,"selectedPaths":510,"source":337,"sourceLanguage":18,"type":255},"skills/bug-capture","Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says \"file an issue\", \"log this as a bug\", \"capture this\".","bug-capture",{"claudeCode":12},"SKILL.md frontmatter at skills/bug-capture/SKILL.md",[511],{"path":487,"priority":334},{"basePath":513,"description":514,"displayName":515,"installMethods":516,"rationale":517,"selectedPaths":518,"source":337,"sourceLanguage":18,"type":255},"skills/compact-guard","Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.","compact-guard",{"claudeCode":12},"SKILL.md frontmatter at skills/compact-guard/SKILL.md",[519],{"path":487,"priority":334},{"basePath":521,"description":522,"displayName":523,"installMethods":524,"rationale":525,"selectedPaths":526,"source":337,"sourceLanguage":18,"type":255},"skills/context-engineering","Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.","context-engineering",{"claudeCode":12},"SKILL.md frontmatter at skills/context-engineering/SKILL.md",[527],{"path":487,"priority":334},{"basePath":529,"description":530,"displayName":531,"installMethods":532,"rationale":533,"selectedPaths":534,"source":337,"sourceLanguage":18,"type":255},"skills/context-optimizer","Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.","context-optimizer",{"claudeCode":12},"SKILL.md frontmatter at skills/context-optimizer/SKILL.md",[535],{"path":487,"priority":334},{"basePath":537,"description":538,"displayName":539,"installMethods":540,"rationale":541,"selectedPaths":542,"source":337,"sourceLanguage":18,"type":255},"skills/cost-tracker","Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.","cost-tracker",{"claudeCode":12},"SKILL.md frontmatter at skills/cost-tracker/SKILL.md",[543],{"path":487,"priority":334},{"basePath":545,"description":546,"displayName":547,"installMethods":548,"rationale":549,"selectedPaths":550,"source":337,"sourceLanguage":18,"type":255},"skills/deslop","Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, and strips defensive code. Use when cleaning up code, simplifying, removing boilerplate, or before committing.","deslop",{"claudeCode":12},"SKILL.md frontmatter at skills/deslop/SKILL.md",[551],{"path":487,"priority":334},{"basePath":553,"description":554,"displayName":555,"installMethods":556,"rationale":557,"selectedPaths":558,"source":337,"sourceLanguage":18,"type":255},"skills/file-watcher","Configure file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use to set up reactive workflows.","file-watcher",{"claudeCode":12},"SKILL.md frontmatter at skills/file-watcher/SKILL.md",[559],{"path":487,"priority":334},{"basePath":561,"description":562,"displayName":563,"installMethods":564,"rationale":565,"selectedPaths":566,"source":337,"sourceLanguage":18,"type":255},"skills/insights","Show session analytics, learning patterns, correction trends, heatmaps, and productivity metrics. Computes stats from project memory and session history. Use when asking for stats, statistics, progress, how am I doing, coding history, or dashboard.","insights",{"claudeCode":12},"SKILL.md frontmatter at skills/insights/SKILL.md",[567],{"path":487,"priority":334},{"basePath":569,"description":570,"displayName":571,"installMethods":572,"rationale":573,"selectedPaths":574,"source":337,"sourceLanguage":18,"type":255},"skills/learn-rule","Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says \"remember this\", \"don't forget\", \"note this\", or \"learn from this\".","learn-rule",{"claudeCode":12},"SKILL.md frontmatter at skills/learn-rule/SKILL.md",[575],{"path":487,"priority":334},{"basePath":251,"description":10,"displayName":254,"installMethods":577,"rationale":578,"selectedPaths":579,"source":337,"sourceLanguage":18,"type":255},{"claudeCode":12},"SKILL.md frontmatter at skills/llm-council/SKILL.md",[580,581],{"path":487,"priority":334},{"path":582,"priority":583},"scripts/council.js","low",{"basePath":585,"description":586,"displayName":587,"installMethods":588,"rationale":589,"selectedPaths":590,"source":337,"sourceLanguage":18,"type":255},"skills/llm-gate","LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.","llm-gate",{"claudeCode":12},"SKILL.md frontmatter at skills/llm-gate/SKILL.md",[591],{"path":487,"priority":334},{"basePath":593,"description":594,"displayName":595,"installMethods":596,"rationale":597,"selectedPaths":598,"source":337,"sourceLanguage":18,"type":255},"skills/mcp-audit","Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.","mcp-audit",{"claudeCode":12},"SKILL.md frontmatter at skills/mcp-audit/SKILL.md",[599],{"path":487,"priority":334},{"basePath":601,"description":602,"displayName":603,"installMethods":604,"rationale":605,"selectedPaths":606,"source":337,"sourceLanguage":18,"type":255},"skills/module-map","Produce a one-screen map of an unfamiliar area of the codebase: entry points, modules, data flow, callers. Designed to be read in fifteen seconds. Use when the user says \"I do not know this area\", \"give me the map\", \"zoom out\", \"orient me\".","module-map",{"claudeCode":12},"SKILL.md frontmatter at skills/module-map/SKILL.md",[607],{"path":487,"priority":334},{"basePath":609,"description":610,"displayName":611,"installMethods":612,"rationale":613,"selectedPaths":614,"source":337,"sourceLanguage":18,"type":255},"skills/orchestrate","Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.","orchestrate",{"claudeCode":12},"SKILL.md frontmatter at skills/orchestrate/SKILL.md",[615],{"path":487,"priority":334},{"basePath":617,"description":618,"displayName":619,"installMethods":620,"rationale":621,"selectedPaths":622,"source":337,"sourceLanguage":18,"type":255},"skills/parallel-worktrees","Create and manage git worktrees for parallel coding sessions with zero dead time. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.","parallel-worktrees",{"claudeCode":12},"SKILL.md frontmatter at skills/parallel-worktrees/SKILL.md",[623],{"path":487,"priority":334},{"basePath":625,"description":626,"displayName":627,"installMethods":628,"rationale":629,"selectedPaths":630,"source":337,"sourceLanguage":18,"type":255},"skills/permission-tuner","Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.","permission-tuner",{"claudeCode":12},"SKILL.md frontmatter at skills/permission-tuner/SKILL.md",[631],{"path":487,"priority":334},{"basePath":633,"description":634,"displayName":635,"installMethods":636,"rationale":637,"selectedPaths":638,"source":337,"sourceLanguage":18,"type":255},"skills/plan-interrogate","Stress-test a plan by walking its decision tree one question at a time. Use when the user wants to pressure-test a design before implementation.","plan-interrogate",{"claudeCode":12},"SKILL.md frontmatter at skills/plan-interrogate/SKILL.md",[639],{"path":487,"priority":334},{"basePath":641,"description":642,"displayName":253,"installMethods":643,"rationale":644,"selectedPaths":645,"source":337,"sourceLanguage":18,"type":255},"skills/pro-workflow","Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.",{"claudeCode":12},"SKILL.md frontmatter at skills/pro-workflow/SKILL.md",[646],{"path":487,"priority":334},{"basePath":648,"description":649,"displayName":650,"installMethods":651,"rationale":652,"selectedPaths":653,"source":337,"sourceLanguage":18,"type":255},"skills/replay-learnings","Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying \"what do I know about\", \"previous mistakes\", \"lessons learned\", or \"remind me about\".","replay-learnings",{"claudeCode":12},"SKILL.md frontmatter at skills/replay-learnings/SKILL.md",[654],{"path":487,"priority":334},{"basePath":656,"description":657,"displayName":658,"installMethods":659,"rationale":660,"selectedPaths":661,"source":337,"sourceLanguage":18,"type":255},"skills/safe-mode","Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.","safe-mode",{"claudeCode":12},"SKILL.md frontmatter at skills/safe-mode/SKILL.md",[662],{"path":487,"priority":334},{"basePath":664,"description":665,"displayName":666,"installMethods":667,"rationale":668,"selectedPaths":669,"source":337,"sourceLanguage":18,"type":255},"skills/session-handoff","Generate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resume work. Use when ending a session, saying \"continue later\", \"save progress\", \"session summary\", or \"pick up where I left off\".","session-handoff",{"claudeCode":12},"SKILL.md frontmatter at skills/session-handoff/SKILL.md",[670],{"path":487,"priority":334},{"basePath":672,"description":673,"displayName":674,"installMethods":675,"rationale":676,"selectedPaths":677,"source":337,"sourceLanguage":18,"type":255},"skills/smart-commit","Run quality gates, review staged changes for issues, and create a well-crafted conventional commit. Use when saying \"commit\", \"git commit\", \"save my changes\", or ready to commit after making changes.","smart-commit",{"claudeCode":12},"SKILL.md frontmatter at skills/smart-commit/SKILL.md",[678],{"path":487,"priority":334},{"basePath":680,"description":681,"displayName":682,"installMethods":683,"rationale":684,"selectedPaths":685,"source":337,"sourceLanguage":18,"type":255},"skills/sprint-status","Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.","sprint-status",{"claudeCode":12},"SKILL.md frontmatter at skills/sprint-status/SKILL.md",[686],{"path":487,"priority":334},{"basePath":688,"description":689,"displayName":690,"installMethods":691,"rationale":692,"selectedPaths":693,"source":337,"sourceLanguage":18,"type":255},"skills/survey-generator","Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in `\u003Cwiki>/derived/surveys/\u003Cslug>.md` with full bibliography rows in `sources.md`. Provider-agnostic (Anthropic/OpenAI/OpenRouter/Fireworks/custom OpenAI-compat). Use when the user asks for a \"survey\", \"literature review\", \"lit review\", or \"deep dive\" on a technical topic.","survey-generator",{"claudeCode":12},"SKILL.md frontmatter at skills/survey-generator/SKILL.md",[694,695,697],{"path":487,"priority":334},{"path":696,"priority":583},"scripts/build-survey.js",{"path":698,"priority":583},"templates/research_bundle.template.json",{"basePath":700,"description":701,"displayName":702,"installMethods":703,"rationale":704,"selectedPaths":705,"source":337,"sourceLanguage":18,"type":255},"skills/thoroughness-scoring","Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.","thoroughness-scoring",{"claudeCode":12},"SKILL.md frontmatter at skills/thoroughness-scoring/SKILL.md",[706],{"path":487,"priority":334},{"basePath":708,"description":709,"displayName":710,"installMethods":711,"rationale":712,"selectedPaths":713,"source":337,"sourceLanguage":18,"type":255},"skills/token-efficiency","Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.","token-efficiency",{"claudeCode":12},"SKILL.md frontmatter at skills/token-efficiency/SKILL.md",[714],{"path":487,"priority":334},{"basePath":716,"description":717,"displayName":718,"installMethods":719,"rationale":720,"selectedPaths":721,"source":337,"sourceLanguage":18,"type":255},"skills/wiki-builder","Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base. Each wiki is a folder of markdown pages with provenance, plus a shadow FTS5 index so any session can recall it. Use when the user says \"start a wiki\", \"add to wiki\", \"compile a page\", \"wiki on X\", or wants a long-lived knowledge base on a topic, paper, product, person, project, or codebase.","wiki-builder",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-builder/SKILL.md",[722,723,725,727,729,731,733,735,737,739,741,743,745],{"path":487,"priority":334},{"path":724,"priority":347},"references/wiki-flavors.md",{"path":726,"priority":583},"scripts/init_wiki.sh",{"path":728,"priority":583},"scripts/wiki-cli.js",{"path":730,"priority":583},"templates/index.md",{"path":732,"priority":583},"templates/maintenance-log.md",{"path":734,"priority":583},"templates/prompts/compile-concept-page.md",{"path":736,"priority":583},"templates/prompts/compile-index.md",{"path":738,"priority":583},"templates/prompts/compile-source-page.md",{"path":740,"priority":583},"templates/prompts/lint-wiki.md",{"path":742,"priority":583},"templates/prompts/query-and-file.md",{"path":744,"priority":583},"templates/sources.md",{"path":746,"priority":583},"templates/wiki.config.md",{"basePath":748,"description":749,"displayName":750,"installMethods":751,"rationale":752,"selectedPaths":753,"source":337,"sourceLanguage":18,"type":255},"skills/wiki-query","Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. Returns top-K passages with citations. Use when answering a question that any of the user's wikis already covers, when the user says \"what does the wiki say about X\", \"ask wiki\", \"search wikis\", or before drafting a new wiki page (to avoid duplication).","wiki-query",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-query/SKILL.md",[754,755],{"path":487,"priority":334},{"path":756,"priority":583},"scripts/query.js",{"basePath":758,"description":759,"displayName":760,"installMethods":761,"rationale":762,"selectedPaths":763,"source":337,"sourceLanguage":18,"type":255},"skills/wiki-research-loop","Auto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from the queue, fetches sources, drafts a wiki page, dedupes claims against existing pages, enqueues follow-up seeds. Halts on budget cap, depth cap, or convergence. Use when the user says \"research \u003Ctopic>\", \"grow the \u003Cslug> wiki\", \"auto-research\", or wants a knowledge base that builds itself overnight.","wiki-research-loop",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-research-loop/SKILL.md",[764,765,767,769,771],{"path":487,"priority":334},{"path":766,"priority":583},"scripts/research-loop.js",{"path":768,"priority":583},"scripts/source-fetchers/arxiv.js",{"path":770,"priority":583},"scripts/source-fetchers/github.js",{"path":772,"priority":583},"scripts/source-fetchers/web.js",{"basePath":774,"description":775,"displayName":776,"installMethods":777,"rationale":778,"selectedPaths":779,"source":337,"sourceLanguage":18,"type":255},"skills/wiki-viewer","Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's \"Unreasonable Effectiveness of HTML\" — favors information density and shareability over markdown-only outputs.","wiki-viewer",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-viewer/SKILL.md",[780,781],{"path":487,"priority":334},{"path":782,"priority":583},"scripts/render.js",{"basePath":784,"description":785,"displayName":786,"installMethods":787,"rationale":788,"selectedPaths":789,"source":337,"sourceLanguage":18,"type":255},"skills/wrap-up","End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying \"wrap up\", \"done for the day\", \"finish coding\", or ending a coding session.","wrap-up",{"claudeCode":12},"SKILL.md frontmatter at skills/wrap-up/SKILL.md",[790],{"path":487,"priority":334},{"sources":792},[793],"manual",{"npmPackage":253},{"closedIssues90d":239,"description":796,"forks":240,"homepage":797,"openIssues90d":8,"pushedAt":242,"readmeSize":237,"stars":243,"topics":798},"Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.","https://rohitg00.github.io/pro-workflow/infographic.html",[799,800,801,282,802,803,303,804,805,806,807,808,523,285,809,307,283,304,810],"claude","claude-code","cursor","agent-orchestration","ai-agents","ai-workflow","claude-code-plugin","claude-code-skills","claude-skills","codex","gemini-cli","worktrees",{"downloads":245},{"classifiedAt":813,"discoverAt":814,"extractAt":815,"githubAt":815,"npmAt":816,"updatedAt":813},1778696594915,1778696588306,1778696590961,1778696593284,[223,219,221,218,220,222],{"evaluatedAt":249,"extractAt":298,"updatedAt":249},[],[821,851,878,906,931,960],{"_creationTime":822,"_id":823,"community":824,"display":825,"identity":831,"providers":835,"relations":844,"tags":847,"workflow":848},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":826,"installMethods":827,"name":829,"sourceUrl":830},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":828},"Yeachan-Heo/oh-my-claudecode","oh-my-claudecode","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":832,"githubOwner":833,"githubRepo":829,"locale":18,"slug":834,"type":255},"skills/ask","Yeachan-Heo","ask",{"evaluate":836,"extract":843},{"promptVersionExtension":211,"promptVersionScoring":212,"score":837,"tags":838,"targetMarket":224,"tier":225},100,[223,839,218,840,841,842],"automation","prompting","code-review","artifact-generation",{"commitSha":287,"license":288},{"parentExtensionId":845,"repoId":846},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[842,839,223,841,218,840],{"evaluatedAt":849,"extractAt":850,"updatedAt":849},1778699303045,1778699234184,{"_creationTime":852,"_id":853,"community":854,"display":855,"identity":861,"providers":866,"relations":872,"tags":874,"workflow":875},1778692098392.723,"k171q2y70k2z7p5t62a7zrpw6s86n4kw",{"reviewCount":8},{"description":856,"installMethods":857,"name":859,"sourceUrl":860},"飞书知识库：管理知识空间、空间成员和文档节点。创建和查询知识空间、查看和管理空间成员、管理节点层级结构、在知识库中组织文档和快捷方式。当用户需要在知识库中查找或创建文档、浏览知识空间结构、查看或管理空间成员、移动或复制节点时使用。",{"claudeCode":858},"larksuite/cli","Lark Wiki CLI","https://github.com/larksuite/cli",{"basePath":862,"githubOwner":863,"githubRepo":223,"locale":864,"slug":865,"type":255},"skills/lark-wiki","larksuite","zh-CN","lark-wiki",{"evaluate":867,"extract":871},{"promptVersionExtension":211,"promptVersionScoring":212,"score":837,"tags":868,"targetMarket":224,"tier":225},[869,870,222,221,839,223],"lark","feishu",{"commitSha":287,"license":288},{"repoId":873},"kd7akv5cxs7vx53ys6jsrv85v186mha4",[839,223,870,221,869,222],{"evaluatedAt":876,"extractAt":877,"updatedAt":876},1778692680305,1778692098392,{"_creationTime":879,"_id":880,"community":881,"display":882,"identity":888,"providers":891,"relations":899,"tags":902,"workflow":903},1778675056600.238,"k17bzapecn7k6jdgt1ag6rda2s86m06p",{"reviewCount":8},{"description":883,"installMethods":884,"name":886,"sourceUrl":887},"Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.",{"claudeCode":885},"alirezarezvani/claude-skills","rag-architect","https://github.com/alirezarezvani/claude-skills",{"basePath":889,"githubOwner":890,"githubRepo":807,"locale":18,"slug":886,"type":255},"engineering/skills/rag-architect","alirezarezvani",{"evaluate":892,"extract":898},{"promptVersionExtension":211,"promptVersionScoring":212,"score":837,"tags":893,"targetMarket":224,"tier":225},[894,218,895,896,897,221],"rag","embedding","vector-search","retrieval",{"commitSha":287},{"parentExtensionId":900,"repoId":901},"k173223hfbd6c4mx6r1jdx23wn86mbpb","kd7ff9s1w43mfyy1n7hf87816186m6px",[895,221,218,894,897,896],{"evaluatedAt":904,"extractAt":905,"updatedAt":904},1778678924736,1778675056600,{"_creationTime":907,"_id":908,"community":909,"display":910,"identity":914,"providers":917,"relations":926,"tags":928,"workflow":929},1778675056600.2317,"k17cxt9ps1s1vkzp0d0eq7pkt986m6gg",{"reviewCount":8},{"description":911,"installMethods":912,"name":913,"sourceUrl":887},"Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include \"second brain\", \"Obsidian wiki\", \"personal knowledge management\", \"ingest this paper/article/book\", \"build a research wiki\", \"compound knowledge\", \"Memex\", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.",{"claudeCode":885},"LLM Wiki",{"basePath":915,"githubOwner":890,"githubRepo":807,"locale":18,"slug":916,"type":255},"engineering/llm-wiki/skills/llm-wiki","llm-wiki",{"evaluate":918,"extract":925},{"promptVersionExtension":211,"promptVersionScoring":212,"score":837,"tags":919,"targetMarket":224,"tier":225},[221,920,921,922,923,222,924],"obsidian","second-brain","pkm","rag-alternative","personal-knowledge-management",{"commitSha":287,"license":288},{"parentExtensionId":927,"repoId":901},"k171h6s4fcrd2pepndhe1tnjgd86mbgr",[221,920,924,922,923,921,222],{"evaluatedAt":930,"extractAt":905,"updatedAt":930},1778678327640,{"_creationTime":932,"_id":933,"community":934,"display":935,"identity":941,"providers":944,"relations":951,"tags":955,"workflow":956},1778675389065.5505,"k17efbbhbjt47j1pr8as1ck3d586npx0",{"reviewCount":8},{"description":936,"installMethods":937,"name":939,"sourceUrl":940},"深入的递归研究，具有自我调节的循环，可达博士级别。适用于任何领域（科学、技术、商业、艺术、人文学科）。使用 WDM + Munger 反演进行自主决策、可靠来源分级和磁盘检查点以克服上下文限制。",{"claudeCode":938},"Anjos2/recursive-research","recursive-research","https://github.com/Anjos2/recursive-research",{"basePath":942,"githubOwner":943,"githubRepo":939,"locale":864,"slug":939,"type":255},"plugins/recursive-research/skills/recursive-research","Anjos2",{"evaluate":945,"extract":950},{"promptVersionExtension":211,"promptVersionScoring":212,"score":837,"tags":946,"targetMarket":224,"tier":225},[947,221,218,948,949],"research","decision-making","documentation",{"commitSha":287},{"parentExtensionId":952,"repoId":953,"translatedFrom":954},"k178rg6vs234c409g28ca6arbd86n5a1","kd753d1f20n4nwaapq6yp8vhd186nzxp","k17agpm4ma1bjqydbc6e6w2sr186m0k8",[948,949,221,218,947],{"evaluatedAt":957,"extractAt":958,"updatedAt":959},1778675358883,1778675291492,1778675389065,{"_creationTime":961,"_id":962,"community":963,"display":964,"identity":970,"providers":975,"relations":983,"tags":986,"workflow":987},1778692818788.4202,"k17ambp6v3xcg52bx2sbp8fj9x86nvmv",{"reviewCount":8},{"description":965,"installMethods":966,"name":968,"sourceUrl":969},"分析 Karpathy 模式的 LLM Wiki 知识库，并生成一个交互式知识图谱，包含实体提取、隐含规则和主题聚类。",{"claudeCode":967},"Lum1104/Understand-Anything","Understand Knowledge","https://github.com/Lum1104/Understand-Anything",{"basePath":971,"githubOwner":972,"githubRepo":973,"locale":864,"slug":974,"type":255},"understand-anything-plugin/skills/understand-knowledge","Lum1104","Understand-Anything","understand-knowledge",{"evaluate":976,"extract":982},{"promptVersionExtension":211,"promptVersionScoring":212,"score":837,"tags":977,"targetMarket":224,"tier":225},[978,218,222,979,980,981],"knowledge-graph","entity-extraction","topic-clustering","python",{"commitSha":287,"license":288},{"repoId":984,"translatedFrom":985},"kd78egfytykkxxbpr6k3t7wsph86n83x","k174cf2tsjpdqmm0p10s8ybq5h86ngnx",[979,978,218,981,980,222],{"evaluatedAt":988,"extractAt":989,"updatedAt":990},1778692723004,1778692549705,1778692818788]