[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-rohitg00-wiki-research-loop-en":3,"guides-for-rohitg00-wiki-research-loop":814,"similar-k174bn3jd3t970wt4r2va9ybts86nqvk-en":815},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":244,"isFallback":235,"parentExtension":250,"providers":312,"relations":316,"repo":317,"tags":812,"workflow":813},1778696595410.5693,"k174bn3jd3t970wt4r2va9ybts86nqvk",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"rohitg00/pro-workflow","Wiki Research Loop","https://github.com/rohitg00/pro-workflow",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":225,"workflow":242},1778697119776.7998,"kn76z11ssb8ga3qsh20479ps4h86msqy","en",{"checks":20,"evaluatedAt":187,"extensionSummary":188,"features":189,"nonGoals":195,"practices":200,"prerequisites":204,"promptVersionExtension":205,"promptVersionScoring":206,"purpose":207,"rationale":208,"score":209,"summary":210,"tags":211,"targetMarket":218,"tier":219,"useCases":220},[21,26,29,32,36,39,43,46,50,54,58,61,64,68,72,76,79,82,86,90,93,97,100,103,106,109,112,115,119,122,126,130,134,137,141,144,148,151,154,157,160,163,166,170,173,177,180,184],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly identifies the problem of repeating corrections and lost knowledge with AI assistants, and positions the extension as a solution for persistent knowledge bases and auto-research.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers significant value beyond basic AI capabilities by implementing a persistent, auto-growing wiki, self-correction memory, and a budget-capped research loop, which are not default behaviors.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension appears production-ready with a defined workflow, clear commands, pluggable fetchers, and robust halt conditions, covering the full lifecycle of its stated purpose.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on auto-growing a wiki through a research loop, integrating with existing wiki tools, and clearly defines its scope without venturing into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description is concise, readable, and accurately reflects the extension's functionality, including its BFS research loop, fetchers, deduplication, and halt conditions.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The description clearly states the artifact (wiki) and the user intent (research topic, grow wiki), provides positive triggers, and implicitly sets boundaries by detailing its specific research loop mechanism.",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter is dense and self-contained, summarizing the core capability and providing clear trigger phrases within a reasonable character count.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The SKILL.md body is concise, outlining the workflow, commands, and fetchers, and delegates deeper material to external files like the README.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","The SKILL.md outlines the primary workflow and links to the README for more detailed explanations and examples, demonstrating progressive disclosure.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","The skill is primarily a research loop and does not appear to involve deep code review or multi-file inspection that would necessitate a forked context.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","The README provides clear, ready-to-use examples for initializing wikis, adding seeds, running the research loop, and other core functionalities.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The SKILL.md documents halt conditions like budget caps, max depth, convergence, and kill switches, with observable symptoms and implicit recovery steps (e.g., removing the STOP file).",{"category":65,"check":66,"severity":56,"summary":67},"Code Execution","Tool Fallback","The skill primarily uses internal logic and Node.js scripts, not external MCPs or tools that would require fallback mechanisms.",{"category":69,"check":70,"severity":24,"summary":71},"Safety","Halt on unexpected state","The research loop explicitly halts on various conditions including budget, depth, convergence, and a manual kill switch, reporting the reason for the halt.",{"category":73,"check":74,"severity":24,"summary":75},"Portability","Cross-skill coupling","The skill operates as a standalone research loop and explicitly mentions its dependencies on `wiki-builder` and `wiki-query` in the README, implying they are separate but integrated components rather than implicit dependencies.",{"category":40,"check":77,"severity":24,"summary":78},"Tool naming","The commands are descriptive and follow a clear verb-noun structure (e.g., `run`, `seed`, `cancel`).",{"category":33,"check":80,"severity":24,"summary":81},"Minimal I/O surface","The CLI commands use structured arguments (slug, query, flags) and the scripts process data from defined sources, with outputs like logs and JSON stats being clear and purposeful.",{"category":83,"check":84,"severity":24,"summary":85},"License","License usability","The project is licensed under the MIT license, as indicated by the shield in the README and a link to the LICENSE file.",{"category":87,"check":88,"severity":24,"summary":89},"Maintenance","Commit recency","The last commit was on May 12, 2026, which is within the last 3 months.",{"category":87,"check":91,"severity":24,"summary":92},"Dependency Management","The project appears to use npm, and while a lockfile isn't explicitly shown in the provided files, the presence of `npm install` commands in the README suggests standard dependency management practices.",{"category":94,"check":95,"severity":24,"summary":96},"Security","Secret Management","The script's fetchers reference environment variables like GH_TOKEN/GITHUB_TOKEN for API access, indicating they do not hardcode secrets.",{"category":94,"check":98,"severity":24,"summary":99},"Injection","The scripts process data from external sources (web, arXiv, GitHub) but do not appear to execute fetched content as instructions; they extract structured data.",{"category":94,"check":101,"severity":24,"summary":102},"Transitive Supply-Chain Grenades","The script fetches data from URLs but does not appear to execute remote code or download uncommitted content at runtime. Fetchers are defined within the bundle.",{"category":94,"check":104,"severity":24,"summary":105},"Sandbox Isolation","The scripts operate on local files within the wiki's directory and do not seem to interact with or modify files outside the intended scope.",{"category":94,"check":107,"severity":24,"summary":108},"Sandbox escape primitives","No evidence of detached processes, background children outliving hooks, or retry loops around denied tool calls was found in the provided scripts.",{"category":94,"check":110,"severity":24,"summary":111},"Data Exfiltration","The script fetches public data and uses optional authenticated API tokens for rate limits, with no indications of reading or submitting confidential data.",{"category":94,"check":113,"severity":24,"summary":114},"Hidden Text Tricks","The provided script and markdown files do not contain any hidden text, control characters, or other obfuscation techniques.",{"category":116,"check":117,"severity":24,"summary":118},"Hooks","Opaque code execution","The provided JavaScript files are plain, readable source code without obfuscation, base64 payloads, or runtime code fetching.",{"category":73,"check":120,"severity":24,"summary":121},"Structural Assumption","The script assumes a standard project structure for wikis and fetchers but does not rely on user-specific file paths outside the expected configuration directories.",{"category":123,"check":124,"severity":24,"summary":125},"Trust","Issues Attention","There are 0 open issues and 5 closed issues in the last 90 days, indicating active maintenance and a healthy closure rate.",{"category":127,"check":128,"severity":24,"summary":129},"Versioning","Release Management","The README includes an npm version badge, and the `CHANGELOG.md` is present, indicating a managed release process.",{"category":131,"check":132,"severity":24,"summary":133},"Execution","Validation","The CLI arguments are parsed, and script inputs like URLs and queries are handled within the fetch functions. Configuration parsing in `runOne` also demonstrates structured handling.",{"category":94,"check":135,"severity":24,"summary":136},"Unguarded Destructive Operations","The script primarily reads data and writes logs/wiki pages; destructive operations are not apparent, and file writes are within expected wiki directories.",{"category":138,"check":139,"severity":24,"summary":140},"Errors","Error Handling","The scripts include try-catch blocks, use `die` for fatal errors, and log errors encountered during fetching and processing, providing meaningful feedback.",{"category":65,"check":142,"severity":24,"summary":143},"Logging","The `research-loop.js` script writes detailed logs to a file per run, capturing actions, errors, and costs, serving as an audit trail.",{"category":145,"check":146,"severity":56,"summary":147},"Compliance","GDPR","The extension operates on public web data, arXiv, and GitHub repositories; no personal data is explicitly used or processed.",{"category":145,"check":149,"severity":24,"summary":150},"Target market","The extension is designed for general research and knowledge base building and does not exhibit any regional or jurisdictional logic, making it global in scope.",{"category":73,"check":152,"severity":24,"summary":153},"Runtime stability","The scripts use standard Node.js modules and are designed to run in a Node.js environment without specific OS or shell dependencies beyond basic POSIX compatibility.",{"category":47,"check":155,"severity":24,"summary":156},"README","The README file is comprehensive, detailing the problem, solution, installation, usage examples, architecture, and comparison with other projects.",{"category":33,"check":158,"severity":56,"summary":159},"Tool surface size","This is a skill with a primary CLI command, not a broad set of distinct tools.",{"category":40,"check":161,"severity":24,"summary":162},"Overlapping near-synonym tools","The CLI commands (`run`, `seed`, `seeds`, `cancel`, `status`) have distinct functions and do not appear to have overlapping near-synonym names.",{"category":47,"check":164,"severity":24,"summary":165},"Phantom features","All advertised features, such as the research loop, fetchers, and halt conditions, are implemented and described in the SKILL.md and README.",{"category":167,"check":168,"severity":24,"summary":169},"Install","Installation instruction","The README provides clear installation instructions using `/plugin marketplace add` and `/plugin install`, along with examples for Cursor and SkillKit.",{"category":138,"check":171,"severity":24,"summary":172},"Actionable error messages","Errors are logged with context, and specific halt conditions provide clear reasons (e.g., 'kill-switch', 'budget', 'queue-empty', 'converged').",{"category":131,"check":174,"severity":175,"summary":176},"Pinned dependencies","info","While `npm install` is mentioned, explicit lockfiles or pinned versions are not visible in the provided files, suggesting potential variability in dependency versions.",{"category":33,"check":178,"severity":56,"summary":179},"Dry-run preview","The skill's primary function is data collection and wiki page creation, which are not state-changing operations in a way that necessitates a dry-run preview.",{"category":181,"check":182,"severity":24,"summary":183},"Protocol","Idempotent retry & timeouts","Fetch operations include timeouts, and the script handles potential errors gracefully. Wiki page updates and seed claims appear to be designed with idempotency in mind.",{"category":145,"check":185,"severity":56,"summary":186},"Telemetry opt-in","The extension does not appear to emit any telemetry; logging is local to the user's machine.",1778697119644,"This skill implements an automated research loop to grow a wiki, using pluggable fetchers (web, arXiv, GitHub) and halt conditions like budget caps and convergence. It manages seeds, compiles wiki pages, and integrates with other wiki tools.",[190,191,192,193,194],"Automated wiki growth via research loop","Pluggable source fetchers (web, arXiv, GitHub)","Budget-capped and depth-limited research","Convergence detection for halting","Seed queue management and status tracking",[196,197,198,199],"Acting as a general-purpose web scraper without wiki context","Performing real-time research triggered by individual user prompts (handled by other skills)","Replacing manual curation entirely; requires initial seeds and review","Performing complex LLM-driven analysis beyond claim extraction",[201,202,203],"Automated knowledge acquisition","Content generation","Research workflow automation",[],"3.0.0","4.4.0","To automatically expand and maintain a knowledge base wiki by performing budget-capped, breadth-first research on specified topics.","Excellent documentation, clear purpose, and robust implementation of the research loop and wiki features. Minor point on dependency pinning and lack of explicit dry-run for page creation are noted but do not detract from overall high quality.",95,"A high-quality skill for automatically growing a knowledge base wiki through a budget-capped research loop.",[212,213,214,215,216,217],"wiki","research","automation","knowledge-base","llm","gpt","global","verified",[221,222,223,224],"Grow a knowledge base wiki on a new topic overnight","Research complex subjects by providing an initial seed query","Auto-populate a wiki with information from web, arXiv, and GitHub","Maintain a continuously updated knowledge base",{"codeQuality":226,"collectedAt":228,"documentation":229,"maintenance":232,"popularity":238,"security":240,"testCoverage":241},{"hasLockfile":227},true,1778697104218,{"descriptionLength":230,"readmeSize":231},460,22012,{"closedIssues90d":233,"forks":234,"hasChangelog":235,"openIssues90d":8,"pushedAt":236,"stars":237},5,203,false,1778554780000,2113,{"npmDownloads":239},611,{"hasNpmPackage":227,"smitheryVerified":235},{"hasCi":227,"hasTests":235},{"updatedAt":243},1778697119776,{"basePath":245,"githubOwner":246,"githubRepo":247,"locale":18,"slug":248,"type":249},"skills/wiki-research-loop","rohitg00","pro-workflow","wiki-research-loop","skill",{"_creationTime":251,"_id":252,"community":253,"display":254,"identity":260,"parentExtension":263,"providers":295,"relations":308,"tags":309,"workflow":310},1778696595410.5615,"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv",{"reviewCount":8},{"description":255,"installMethods":256,"name":259,"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":247,"cursor":257,"npm":247,"skillkit":258},"/add-plugin pro-workflow","npx skillkit install pro-workflow","Pro Workflow",{"basePath":261,"githubOwner":246,"githubRepo":247,"locale":18,"slug":247,"type":262},"","plugin",{"_creationTime":264,"_id":265,"community":266,"display":267,"identity":270,"providers":272,"relations":289,"tags":291,"workflow":292},1778696595410.5613,"k1741gyqaf0tj1ffq65gjpsm6x86mfhx",{"reviewCount":8},{"description":268,"installMethods":269,"name":259,"sourceUrl":14},"Battle-tested Claude Code workflows from power users",{"claudeCode":12},{"basePath":261,"githubOwner":246,"githubRepo":247,"locale":18,"slug":247,"type":271},"marketplace",{"evaluate":273,"extract":282},{"promptVersionExtension":274,"promptVersionScoring":206,"score":275,"tags":276,"targetMarket":218,"tier":219},"3.1.0",99,[277,278,279,280,281],"workflow","productivity","ai-assistance","developer-tools","knowledge-management",{"commitSha":283,"license":284,"marketplace":285,"plugin":287},"HEAD","MIT",{"name":247,"pluginCount":286},1,{"mcpCount":8,"provider":288,"skillCount":8},"classify",{"repoId":290},"kd7am4e918eq98hrd9s31jm4vs86nn0b",[279,280,281,278,277],{"evaluatedAt":293,"extractAt":294,"updatedAt":293},1778696611346,1778696595410,{"evaluate":296,"extract":305},{"promptVersionExtension":205,"promptVersionScoring":206,"score":297,"tags":298,"targetMarket":218,"tier":304},96,[277,278,299,300,215,301,302,303],"ai-coding","self-correction","sqlite","hooks","agents","community",{"commitSha":283,"license":284,"plugin":306},{"mcpCount":8,"provider":288,"skillCount":307},34,{"parentExtensionId":265,"repoId":290},[303,299,302,215,278,300,301,277],{"evaluatedAt":311,"extractAt":294,"updatedAt":311},1778696621396,{"evaluate":313,"extract":315},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":314,"targetMarket":218,"tier":219},[212,213,214,215,216,217],{"commitSha":283,"license":284},{"parentExtensionId":252,"repoId":290},{"_creationTime":318,"_id":290,"identity":319,"providers":320,"workflow":807},1778696588306.821,{"githubOwner":246,"githubRepo":247,"sourceUrl":14},{"classify":321,"discover":786,"extract":789,"github":790,"npm":806},{"commitSha":283,"extensions":322},[323,333,474,483,491,499,507,515,523,531,539,547,555,563,571,582,590,598,606,614,622,630,638,645,653,661,669,677,685,697,705,713,745,755,768,778],{"basePath":261,"description":268,"displayName":247,"installMethods":324,"rationale":325,"selectedPaths":326,"source":332,"sourceLanguage":18,"type":271},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[327,330],{"path":328,"priority":329},".claude-plugin/marketplace.json","mandatory",{"path":331,"priority":329},"README.md","rule",{"basePath":261,"description":255,"displayName":247,"installMethods":334,"license":284,"rationale":335,"selectedPaths":336,"source":332,"sourceLanguage":18,"type":262},{"claudeCode":247},"plugin manifest at .claude-plugin/plugin.json",[337,339,340,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,409,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472],{"path":338,"priority":329},".claude-plugin/plugin.json",{"path":331,"priority":329},{"path":341,"priority":342},"skills/agent-teams/SKILL.md","medium",{"path":344,"priority":342},"skills/auto-setup/SKILL.md",{"path":346,"priority":342},"skills/batch-orchestration/SKILL.md",{"path":348,"priority":342},"skills/bug-capture/SKILL.md",{"path":350,"priority":342},"skills/compact-guard/SKILL.md",{"path":352,"priority":342},"skills/context-engineering/SKILL.md",{"path":354,"priority":342},"skills/context-optimizer/SKILL.md",{"path":356,"priority":342},"skills/cost-tracker/SKILL.md",{"path":358,"priority":342},"skills/deslop/SKILL.md",{"path":360,"priority":342},"skills/file-watcher/SKILL.md",{"path":362,"priority":342},"skills/insights/SKILL.md",{"path":364,"priority":342},"skills/learn-rule/SKILL.md",{"path":366,"priority":342},"skills/llm-council/SKILL.md",{"path":368,"priority":342},"skills/llm-gate/SKILL.md",{"path":370,"priority":342},"skills/mcp-audit/SKILL.md",{"path":372,"priority":342},"skills/module-map/SKILL.md",{"path":374,"priority":342},"skills/orchestrate/SKILL.md",{"path":376,"priority":342},"skills/parallel-worktrees/SKILL.md",{"path":378,"priority":342},"skills/permission-tuner/SKILL.md",{"path":380,"priority":342},"skills/plan-interrogate/SKILL.md",{"path":382,"priority":342},"skills/pro-workflow/SKILL.md",{"path":384,"priority":342},"skills/replay-learnings/SKILL.md",{"path":386,"priority":342},"skills/safe-mode/SKILL.md",{"path":388,"priority":342},"skills/session-handoff/SKILL.md",{"path":390,"priority":342},"skills/smart-commit/SKILL.md",{"path":392,"priority":342},"skills/sprint-status/SKILL.md",{"path":394,"priority":342},"skills/survey-generator/SKILL.md",{"path":396,"priority":342},"skills/thoroughness-scoring/SKILL.md",{"path":398,"priority":342},"skills/token-efficiency/SKILL.md",{"path":400,"priority":342},"skills/wiki-builder/SKILL.md",{"path":402,"priority":342},"skills/wiki-query/SKILL.md",{"path":404,"priority":342},"skills/wiki-research-loop/SKILL.md",{"path":406,"priority":342},"skills/wiki-viewer/SKILL.md",{"path":408,"priority":342},"skills/wrap-up/SKILL.md",{"path":410,"priority":411},"agents/context-engineer.md","high",{"path":413,"priority":411},"agents/cost-analyst.md",{"path":415,"priority":411},"agents/debugger.md",{"path":417,"priority":411},"agents/orchestrator.md",{"path":419,"priority":411},"agents/permission-analyst.md",{"path":421,"priority":411},"agents/planner.md",{"path":423,"priority":411},"agents/reviewer.md",{"path":425,"priority":411},"agents/scout.md",{"path":427,"priority":411},"commands/auto-setup.md",{"path":429,"priority":411},"commands/commit.md",{"path":431,"priority":411},"commands/compact-guard.md",{"path":433,"priority":411},"commands/context-optimizer.md",{"path":435,"priority":411},"commands/cost-tracker.md",{"path":437,"priority":411},"commands/deslop.md",{"path":439,"priority":411},"commands/develop.md",{"path":441,"priority":411},"commands/doctor.md",{"path":443,"priority":411},"commands/handoff.md",{"path":445,"priority":411},"commands/insights.md",{"path":447,"priority":411},"commands/learn-rule.md",{"path":449,"priority":411},"commands/learn.md",{"path":451,"priority":411},"commands/list.md",{"path":453,"priority":411},"commands/mcp-audit.md",{"path":455,"priority":411},"commands/parallel.md",{"path":457,"priority":411},"commands/permission-tuner.md",{"path":459,"priority":411},"commands/replay.md",{"path":461,"priority":411},"commands/safe-mode.md",{"path":463,"priority":411},"commands/search.md",{"path":465,"priority":411},"commands/sprint-status.md",{"path":467,"priority":411},"commands/wiki.md",{"path":469,"priority":411},"commands/wrap-up.md",{"path":471,"priority":411},"hooks/hooks.json",{"path":473,"priority":411},".cursor-plugin/plugin.json",{"basePath":475,"description":476,"displayName":477,"installMethods":478,"rationale":479,"selectedPaths":480,"source":332,"sourceLanguage":18,"type":249},"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",[481],{"path":482,"priority":329},"SKILL.md",{"basePath":484,"description":485,"displayName":486,"installMethods":487,"rationale":488,"selectedPaths":489,"source":332,"sourceLanguage":18,"type":249},"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",[490],{"path":482,"priority":329},{"basePath":492,"description":493,"displayName":494,"installMethods":495,"rationale":496,"selectedPaths":497,"source":332,"sourceLanguage":18,"type":249},"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",[498],{"path":482,"priority":329},{"basePath":500,"description":501,"displayName":502,"installMethods":503,"rationale":504,"selectedPaths":505,"source":332,"sourceLanguage":18,"type":249},"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",[506],{"path":482,"priority":329},{"basePath":508,"description":509,"displayName":510,"installMethods":511,"rationale":512,"selectedPaths":513,"source":332,"sourceLanguage":18,"type":249},"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",[514],{"path":482,"priority":329},{"basePath":516,"description":517,"displayName":518,"installMethods":519,"rationale":520,"selectedPaths":521,"source":332,"sourceLanguage":18,"type":249},"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",[522],{"path":482,"priority":329},{"basePath":524,"description":525,"displayName":526,"installMethods":527,"rationale":528,"selectedPaths":529,"source":332,"sourceLanguage":18,"type":249},"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",[530],{"path":482,"priority":329},{"basePath":532,"description":533,"displayName":534,"installMethods":535,"rationale":536,"selectedPaths":537,"source":332,"sourceLanguage":18,"type":249},"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",[538],{"path":482,"priority":329},{"basePath":540,"description":541,"displayName":542,"installMethods":543,"rationale":544,"selectedPaths":545,"source":332,"sourceLanguage":18,"type":249},"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",[546],{"path":482,"priority":329},{"basePath":548,"description":549,"displayName":550,"installMethods":551,"rationale":552,"selectedPaths":553,"source":332,"sourceLanguage":18,"type":249},"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",[554],{"path":482,"priority":329},{"basePath":556,"description":557,"displayName":558,"installMethods":559,"rationale":560,"selectedPaths":561,"source":332,"sourceLanguage":18,"type":249},"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",[562],{"path":482,"priority":329},{"basePath":564,"description":565,"displayName":566,"installMethods":567,"rationale":568,"selectedPaths":569,"source":332,"sourceLanguage":18,"type":249},"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",[570],{"path":482,"priority":329},{"basePath":572,"description":573,"displayName":574,"installMethods":575,"rationale":576,"selectedPaths":577,"source":332,"sourceLanguage":18,"type":249},"skills/llm-council","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.","llm-council",{"claudeCode":12},"SKILL.md frontmatter at skills/llm-council/SKILL.md",[578,579],{"path":482,"priority":329},{"path":580,"priority":581},"scripts/council.js","low",{"basePath":583,"description":584,"displayName":585,"installMethods":586,"rationale":587,"selectedPaths":588,"source":332,"sourceLanguage":18,"type":249},"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",[589],{"path":482,"priority":329},{"basePath":591,"description":592,"displayName":593,"installMethods":594,"rationale":595,"selectedPaths":596,"source":332,"sourceLanguage":18,"type":249},"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",[597],{"path":482,"priority":329},{"basePath":599,"description":600,"displayName":601,"installMethods":602,"rationale":603,"selectedPaths":604,"source":332,"sourceLanguage":18,"type":249},"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",[605],{"path":482,"priority":329},{"basePath":607,"description":608,"displayName":609,"installMethods":610,"rationale":611,"selectedPaths":612,"source":332,"sourceLanguage":18,"type":249},"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",[613],{"path":482,"priority":329},{"basePath":615,"description":616,"displayName":617,"installMethods":618,"rationale":619,"selectedPaths":620,"source":332,"sourceLanguage":18,"type":249},"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",[621],{"path":482,"priority":329},{"basePath":623,"description":624,"displayName":625,"installMethods":626,"rationale":627,"selectedPaths":628,"source":332,"sourceLanguage":18,"type":249},"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",[629],{"path":482,"priority":329},{"basePath":631,"description":632,"displayName":633,"installMethods":634,"rationale":635,"selectedPaths":636,"source":332,"sourceLanguage":18,"type":249},"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",[637],{"path":482,"priority":329},{"basePath":639,"description":640,"displayName":247,"installMethods":641,"rationale":642,"selectedPaths":643,"source":332,"sourceLanguage":18,"type":249},"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",[644],{"path":482,"priority":329},{"basePath":646,"description":647,"displayName":648,"installMethods":649,"rationale":650,"selectedPaths":651,"source":332,"sourceLanguage":18,"type":249},"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",[652],{"path":482,"priority":329},{"basePath":654,"description":655,"displayName":656,"installMethods":657,"rationale":658,"selectedPaths":659,"source":332,"sourceLanguage":18,"type":249},"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",[660],{"path":482,"priority":329},{"basePath":662,"description":663,"displayName":664,"installMethods":665,"rationale":666,"selectedPaths":667,"source":332,"sourceLanguage":18,"type":249},"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",[668],{"path":482,"priority":329},{"basePath":670,"description":671,"displayName":672,"installMethods":673,"rationale":674,"selectedPaths":675,"source":332,"sourceLanguage":18,"type":249},"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",[676],{"path":482,"priority":329},{"basePath":678,"description":679,"displayName":680,"installMethods":681,"rationale":682,"selectedPaths":683,"source":332,"sourceLanguage":18,"type":249},"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",[684],{"path":482,"priority":329},{"basePath":686,"description":687,"displayName":688,"installMethods":689,"rationale":690,"selectedPaths":691,"source":332,"sourceLanguage":18,"type":249},"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",[692,693,695],{"path":482,"priority":329},{"path":694,"priority":581},"scripts/build-survey.js",{"path":696,"priority":581},"templates/research_bundle.template.json",{"basePath":698,"description":699,"displayName":700,"installMethods":701,"rationale":702,"selectedPaths":703,"source":332,"sourceLanguage":18,"type":249},"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",[704],{"path":482,"priority":329},{"basePath":706,"description":707,"displayName":708,"installMethods":709,"rationale":710,"selectedPaths":711,"source":332,"sourceLanguage":18,"type":249},"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",[712],{"path":482,"priority":329},{"basePath":714,"description":715,"displayName":716,"installMethods":717,"rationale":718,"selectedPaths":719,"source":332,"sourceLanguage":18,"type":249},"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",[720,721,723,725,727,729,731,733,735,737,739,741,743],{"path":482,"priority":329},{"path":722,"priority":342},"references/wiki-flavors.md",{"path":724,"priority":581},"scripts/init_wiki.sh",{"path":726,"priority":581},"scripts/wiki-cli.js",{"path":728,"priority":581},"templates/index.md",{"path":730,"priority":581},"templates/maintenance-log.md",{"path":732,"priority":581},"templates/prompts/compile-concept-page.md",{"path":734,"priority":581},"templates/prompts/compile-index.md",{"path":736,"priority":581},"templates/prompts/compile-source-page.md",{"path":738,"priority":581},"templates/prompts/lint-wiki.md",{"path":740,"priority":581},"templates/prompts/query-and-file.md",{"path":742,"priority":581},"templates/sources.md",{"path":744,"priority":581},"templates/wiki.config.md",{"basePath":746,"description":747,"displayName":748,"installMethods":749,"rationale":750,"selectedPaths":751,"source":332,"sourceLanguage":18,"type":249},"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",[752,753],{"path":482,"priority":329},{"path":754,"priority":581},"scripts/query.js",{"basePath":245,"description":10,"displayName":248,"installMethods":756,"rationale":757,"selectedPaths":758,"source":332,"sourceLanguage":18,"type":249},{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-research-loop/SKILL.md",[759,760,762,764,766],{"path":482,"priority":329},{"path":761,"priority":581},"scripts/research-loop.js",{"path":763,"priority":581},"scripts/source-fetchers/arxiv.js",{"path":765,"priority":581},"scripts/source-fetchers/github.js",{"path":767,"priority":581},"scripts/source-fetchers/web.js",{"basePath":769,"description":770,"displayName":771,"installMethods":772,"rationale":773,"selectedPaths":774,"source":332,"sourceLanguage":18,"type":249},"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",[775,776],{"path":482,"priority":329},{"path":777,"priority":581},"scripts/render.js",{"basePath":779,"description":780,"displayName":781,"installMethods":782,"rationale":783,"selectedPaths":784,"source":332,"sourceLanguage":18,"type":249},"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",[785],{"path":482,"priority":329},{"sources":787},[788],"manual",{"npmPackage":247},{"closedIssues90d":233,"description":791,"forks":234,"homepage":792,"openIssues90d":8,"pushedAt":236,"readmeSize":231,"stars":237,"topics":793},"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",[794,795,796,277,797,798,299,799,800,801,802,803,518,280,804,302,278,300,805],"claude","claude-code","cursor","agent-orchestration","ai-agents","ai-workflow","claude-code-plugin","claude-code-skills","claude-skills","codex","gemini-cli","worktrees",{"downloads":239},{"classifiedAt":808,"discoverAt":809,"extractAt":810,"githubAt":810,"npmAt":811,"updatedAt":808},1778696594915,1778696588306,1778696590961,1778696593284,[214,217,215,216,213,212],{"evaluatedAt":243,"extractAt":294,"updatedAt":243},[],[816,846,874,892,922,950],{"_creationTime":817,"_id":818,"community":819,"display":820,"identity":826,"providers":830,"relations":839,"tags":842,"workflow":843},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":821,"installMethods":822,"name":824,"sourceUrl":825},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":823},"Yeachan-Heo/oh-my-claudecode","oh-my-claudecode","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":827,"githubOwner":828,"githubRepo":824,"locale":18,"slug":829,"type":249},"skills/ask","Yeachan-Heo","ask",{"evaluate":831,"extract":838},{"promptVersionExtension":205,"promptVersionScoring":206,"score":832,"tags":833,"targetMarket":218,"tier":219},100,[834,214,216,835,836,837],"cli","prompting","code-review","artifact-generation",{"commitSha":283,"license":284},{"parentExtensionId":840,"repoId":841},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[837,214,834,836,216,835],{"evaluatedAt":844,"extractAt":845,"updatedAt":844},1778699303045,1778699234184,{"_creationTime":847,"_id":848,"community":849,"display":850,"identity":856,"providers":860,"relations":867,"tags":870,"workflow":871},1778696833339.6243,"k174g80xa9zxhydbncvpf0xzy986nvx5",{"reviewCount":8},{"description":851,"installMethods":852,"name":854,"sourceUrl":855},"Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.",{"claudeCode":853},"sanjay3290/ai-skills","manus","https://github.com/sanjay3290/ai-skills",{"basePath":857,"githubOwner":858,"githubRepo":859,"locale":18,"slug":854,"type":249},"skills/manus","sanjay3290","ai-skills",{"evaluate":861,"extract":866},{"promptVersionExtension":205,"promptVersionScoring":206,"score":832,"tags":862,"targetMarket":218,"tier":219},[863,864,213,214,865],"ai-agent","autonomous-execution","api-integration",{"commitSha":283},{"parentExtensionId":868,"repoId":869},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[863,865,214,864,213],{"evaluatedAt":872,"extractAt":873,"updatedAt":872},1778697107270,1778696833339,{"_creationTime":875,"_id":876,"community":877,"display":878,"identity":881,"providers":882,"relations":888,"tags":889,"workflow":890},1778696595410.5698,"k171sdysmt658g1cdd7hgt8p8h86nms7",{"reviewCount":8},{"description":780,"installMethods":879,"name":880,"sourceUrl":14},{"claudeCode":12},"Wrap-Up Ritual",{"basePath":779,"githubOwner":246,"githubRepo":247,"locale":18,"slug":781,"type":249},{"evaluate":883,"extract":887},{"promptVersionExtension":205,"promptVersionScoring":206,"score":832,"tags":884,"targetMarket":218,"tier":219},[277,216,278,885,215,886],"memory","code-quality",{"commitSha":283,"license":284},{"parentExtensionId":252,"repoId":290},[886,215,216,885,278,277],{"evaluatedAt":891,"extractAt":294,"updatedAt":891},1778697164619,{"_creationTime":893,"_id":894,"community":895,"display":896,"identity":902,"providers":907,"relations":915,"tags":917,"workflow":918},1778692549705.5178,"k174cf2tsjpdqmm0p10s8ybq5h86ngnx",{"reviewCount":8},{"description":897,"installMethods":898,"name":900,"sourceUrl":901},"Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.",{"claudeCode":899},"Lum1104/Understand-Anything","Understand Knowledge","https://github.com/Lum1104/Understand-Anything",{"basePath":903,"githubOwner":904,"githubRepo":905,"locale":18,"slug":906,"type":249},"understand-anything-plugin/skills/understand-knowledge","Lum1104","Understand-Anything","understand-knowledge",{"evaluate":908,"extract":914},{"promptVersionExtension":205,"promptVersionScoring":206,"score":832,"tags":909,"targetMarket":218,"tier":219},[910,216,212,911,912,913],"knowledge-graph","entity-extraction","topic-clustering","python",{"commitSha":283,"license":284},{"repoId":916},"kd78egfytykkxxbpr6k3t7wsph86n83x",[911,910,216,913,912,212],{"evaluatedAt":919,"extractAt":920,"updatedAt":921},1778692723004,1778692549705,1778692826052,{"_creationTime":923,"_id":924,"community":925,"display":926,"identity":932,"providers":936,"relations":942,"tags":945,"workflow":946},1778675291492.6484,"k17agpm4ma1bjqydbc6e6w2sr186m0k8",{"reviewCount":8},{"description":927,"installMethods":928,"name":930,"sourceUrl":931},"Investigación recursiva profunda con loop auto-regulado hasta nivel PhD. Aplicable a cualquier dominio (ciencia, tecnología, negocio, arte, humanidades). Usa WDM + Inversión Munger para decisiones autónomas, tiering de fuentes confiables, y checkpointing a disco para sobrevivir límites de contexto.",{"claudeCode":929},"Anjos2/recursive-research","recursive-research","https://github.com/Anjos2/recursive-research",{"basePath":933,"githubOwner":934,"githubRepo":930,"locale":935,"slug":930,"type":249},"plugins/recursive-research/skills/recursive-research","Anjos2","es",{"evaluate":937,"extract":941},{"promptVersionExtension":205,"promptVersionScoring":206,"score":832,"tags":938,"targetMarket":218,"tier":219},[213,281,216,939,940],"decision-making","documentation",{"commitSha":283},{"parentExtensionId":943,"repoId":944},"k178rg6vs234c409g28ca6arbd86n5a1","kd753d1f20n4nwaapq6yp8vhd186nzxp",[939,940,281,216,213],{"evaluatedAt":947,"extractAt":948,"updatedAt":949},1778675358883,1778675291492,1778675391687,{"_creationTime":951,"_id":952,"community":953,"display":954,"identity":956,"providers":957,"relations":962,"tags":963,"workflow":964},1778696595410.5688,"k175aswqxy754yaatfbja8ntnd86nprj",{"reviewCount":8},{"description":715,"installMethods":955,"name":716,"sourceUrl":14},{"claudeCode":12},{"basePath":714,"githubOwner":246,"githubRepo":247,"locale":18,"slug":716,"type":249},{"evaluate":958,"extract":961},{"promptVersionExtension":205,"promptVersionScoring":206,"score":275,"tags":959,"targetMarket":218,"tier":219},[212,215,301,960,213,834],"markdown",{"commitSha":283},{"parentExtensionId":252,"repoId":290},[834,215,960,213,301,212],{"evaluatedAt":965,"extractAt":294,"updatedAt":965},1778697086509]