[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-rohitg00-wiki-query-zh-CN":3,"guides-for-rohitg00-wiki-query":811,"similar-k179tztczyqqt5k15a9ea0yw9986mx15-zh-CN":812},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":244,"isFallback":227,"parentExtension":249,"providers":309,"relations":313,"repo":314,"tags":809,"workflow":810},1778696595410.569,"k179tztczyqqt5k15a9ea0yw9986mx15",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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).",{"claudeCode":12},"rohitg00/pro-workflow","wiki-query","https://github.com/rohitg00/pro-workflow",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":225,"workflow":242},1778697103686.184,"kn7cr46rzfn7p37c69y8r6b95d86n634","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":218,"tier":219,"useCases":220},[21,26,29,32,36,39,43,47,50,53,57,61,64,69,72,75,78,81,84,87,90,94,98,103,107,110,114,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of repeated corrections and knowledge loss in AI sessions, and identifies the specific artifact (pro-workflow wikis) and user intent (answering questions, avoiding duplication).",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a significant value beyond default LLM behavior by implementing persistent, FTS5-indexed wikis and self-correction memory, providing durable knowledge storage and retrieval.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill appears production-ready, leveraging SQLite FTS5 for retrieval and providing a clear interface for querying user-specific wikis, covering the core use case described.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on querying pro-workflow wikis using SQLite FTS5 BM25 retrieval, aligning with its stated purpose and not extending into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately and concisely reflects the skill's capabilities and intended use cases as detailed in the SKILL.md file.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill exposes narrow, verb-noun specialized tools like `search`, `related`, and `show`, which are easy for the agent to select and reduce attack surface.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md provides clear documentation for the commands, including parameters like `--wiki`, `--limit`, and `--json`, with implied defaults and explicit usage.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The exposed tools (`search`, `related`, `show`) are descriptive, kebab-case, and clearly indicate their function within the wiki query domain.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Tool inputs are structured flags (e.g., `--query`, `--wiki`), and outputs are well-defined JSON objects containing only relevant data like `wiki_slug`, `rel_path`, `title`, `snippet`, and `rank`.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The MIT license is clearly indicated in the README and linked via a badge, suggesting a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows a commit on 2026-05-12, indicating recent maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The script `query.js` uses Node.js and its dependencies are managed via `npm` as indicated by the `package.json` (implied by `npm install` in `SKILL.md` and `README.md`). The `npm install` command suggests dependencies are handled.",{"category":65,"check":66,"severity":67,"summary":68},"Security","Secret Management","not_applicable","This skill does not appear to use or handle any secrets.",{"category":65,"check":70,"severity":24,"summary":71},"Injection","The skill primarily interacts with a local SQLite database and processes user-provided queries via structured arguments, minimizing injection risks. The `query.js` script sanitizes inputs through argument parsing and database queries.",{"category":65,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill relies on local scripts and a local SQLite database, with no runtime fetching of external code or data that could introduce supply-chain risks.",{"category":65,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates on a local SQLite database and uses Node.js scripts, confined to its own execution environment and not modifying external files or paths.",{"category":65,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","The provided script does not contain any detached-process spawns or retry loops that could indicate sandbox escape attempts.",{"category":65,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's functionality is limited to querying a local database and returning structured results; it does not perform any outbound network calls or submit data to third parties.",{"category":65,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content appears free of hidden steering tricks, with clean printable ASCII and expected Unicode in the script and markdown files.",{"category":65,"check":88,"severity":24,"summary":89},"Opaque code execution","The provided JavaScript script is plain, readable source code and does not involve obfuscation, base64 payloads, or runtime fetching for execution.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The script assumes the presence of the SQLite database and the `pro-workflow` directory structure, which are part of its internal workings and not external project structure.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The repository has 0 open issues and 5 closed issues in the last 90 days, indicating active maintenance and prompt issue resolution.",{"category":99,"check":100,"severity":101,"summary":102},"Versioning","Release Management","info","The README mentions `v3.3` and `v3.3.0`, and the `npm` badge shows a version. However, there are no explicit versioning fields in the SKILL.md frontmatter or clear changelog entries tied to specific versions.",{"category":104,"check":105,"severity":24,"summary":106},"Execution","Validation","Input arguments are parsed and used in a way that implies validation for query and path parameters, and the database query itself would handle SQL validation.",{"category":65,"check":108,"severity":67,"summary":109},"Unguarded Destructive Operations","This skill is read-only and does not perform any destructive operations.",{"category":111,"check":112,"severity":24,"summary":113},"Code Execution","Error Handling","The script includes error handling for missing store, missing pages, and exits with non-zero codes for critical errors, providing messages to stderr.",{"category":111,"check":115,"severity":67,"summary":116},"Logging","The skill is read-only and focuses on user-facing output, not internal logging to an audit file.",{"category":118,"check":119,"severity":67,"summary":120},"Compliance","GDPR","The skill only operates on local wiki data and does not handle or process personal data.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The skill operates on local data and has no regional or jurisdictional restrictions, making it globally applicable.",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","The skill uses standard Node.js and SQLite, which are widely compatible, and the script has basic error handling for missing dependencies.",{"category":44,"check":128,"severity":24,"summary":129},"README","The README is comprehensive, detailing the problem, solution, installation, usage, architecture, and more, serving as excellent documentation.",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","The skill exposes three distinct tools: `search`, `related`, and `show`, which is within the optimal range.",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","The tools `search`, `related`, and `show` have distinct purposes and do not appear to be near-synonyms.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","All advertised features, such as BM25 retrieval and citation formatting, are directly implemented in the provided scripts and SKILL.md.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides clear `plugin marketplace add` and `plugin install` commands, along with alternative methods and a 60-second tour with commands.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","Error messages are specific, indicating what failed (e.g., 'built store missing', 'page not found') and suggesting remediation (e.g., 'Run: cd ... && npm install && npm run build').",{"category":104,"check":148,"severity":101,"summary":149},"Pinned dependencies","While `npm install` is mentioned, there is no explicit lockfile or pinned dependency version declared in the provided source files.",{"category":33,"check":151,"severity":67,"summary":152},"Dry-run preview","The skill is purely read-only and does not perform any state-changing operations or outbound data sends.",{"category":154,"check":155,"severity":67,"summary":156},"Protocol","Idempotent retry & timeouts","The skill operates on a local database and has no remote calls or state-changing operations that would require idempotency or timeouts.",{"category":118,"check":158,"severity":67,"summary":159},"Telemetry opt-in","The skill does not emit any telemetry.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly states the skill's function (BM25 retrieval over wikis) and its use cases (answering questions, avoiding duplication, before drafting pages), including explicit non-goals implied by the focused scope.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise, clearly stating the skill's purpose and trigger phrases within the first 160 characters.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is concise, outlining commands and output formats without excessive detail, delegating deeper material implicitly to the project's overall documentation.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md is concise and does not embed large amounts of third-party material or long procedures inline.",{"category":170,"check":174,"severity":67,"summary":175},"Forked exploration","The skill is a query tool and does not involve deep exploration that would require a forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md and README provide clear, copy-pasteable command-line examples for `search`, `related`, and `show`, demonstrating input and expected output.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The script handles cases like missing queries, missing pages, and no matches, providing informative messages and exiting appropriately.",{"category":111,"check":183,"severity":67,"summary":184},"Tool Fallback","This skill is self-contained and does not rely on external MCP servers or tools that would require fallback paths.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The script checks for missing dependencies (store) and missing pages, halting execution with informative error messages rather than proceeding in an unexpected state.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and operates on its local SQLite database without implicit reliance on other skills.",1778697103144,"This skill provides BM25 retrieval capabilities over local SQLite-indexed wikis, returning top-K passages with citations. It includes commands for searching across wikis, finding related pages, and showing page content.",[195,196,197,198,199],"BM25 retrieval over SQLite FTS5 indexed wikis","Returns top-K passages with citations","Search across all wikis or specific ones","Find related wiki pages based on title/summary","Display full wiki page content",[201,202,203],"Providing semantic vector search (planned for future versions)","Real-time re-ranking of search results (planned for future versions)","Operating on external web content or non-local data","3.0.0","4.4.0","To enable users to efficiently search and retrieve information from their personal or project wikis, preventing duplicated effort and ensuring accurate citation.","The skill is highly polished with excellent documentation, clear scope, and robust error handling. The only minor detraction is the lack of explicit dependency pinning.",96,"A well-documented and robust skill for querying local wikis using BM25 retrieval, enhancing knowledge management.",[211,212,213,214,215,216,217],"wiki","search","retrieval","sqlite","fts5","bm25","knowledge-management","global","verified",[221,222,223,224],"Answering questions that a user's wikis already cover","Searching wikis when the user says 'what does the wiki say about X'","Before drafting a new wiki page to avoid duplication","Verifying citations before quoting a claim",{"codeQuality":226,"collectedAt":228,"documentation":229,"maintenance":232,"popularity":238,"security":240,"testCoverage":241},{"hasLockfile":227},true,1778697087019,{"descriptionLength":230,"readmeSize":231},310,22012,{"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},1778697103686,{"basePath":245,"githubOwner":246,"githubRepo":247,"locale":18,"slug":13,"type":248},"skills/wiki-query","rohitg00","pro-workflow","skill",{"_creationTime":250,"_id":251,"community":252,"display":253,"identity":259,"parentExtension":262,"providers":293,"relations":305,"tags":306,"workflow":307},1778696595410.5615,"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv",{"reviewCount":8},{"description":254,"installMethods":255,"name":258,"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":256,"npm":247,"skillkit":257},"/add-plugin pro-workflow","npx skillkit install pro-workflow","Pro Workflow",{"basePath":260,"githubOwner":246,"githubRepo":247,"locale":18,"slug":247,"type":261},"","plugin",{"_creationTime":263,"_id":264,"community":265,"display":266,"identity":269,"providers":271,"relations":287,"tags":289,"workflow":290},1778696595410.5613,"k1741gyqaf0tj1ffq65gjpsm6x86mfhx",{"reviewCount":8},{"description":267,"installMethods":268,"name":258,"sourceUrl":14},"Battle-tested Claude Code workflows from power users",{"claudeCode":12},{"basePath":260,"githubOwner":246,"githubRepo":247,"locale":18,"slug":247,"type":270},"marketplace",{"evaluate":272,"extract":280},{"promptVersionExtension":273,"promptVersionScoring":205,"score":274,"tags":275,"targetMarket":218,"tier":219},"3.1.0",99,[276,277,278,279,217],"workflow","productivity","ai-assistance","developer-tools",{"commitSha":281,"license":282,"marketplace":283,"plugin":285},"HEAD","MIT",{"name":247,"pluginCount":284},1,{"mcpCount":8,"provider":286,"skillCount":8},"classify",{"repoId":288},"kd7am4e918eq98hrd9s31jm4vs86nn0b",[278,279,217,277,276],{"evaluatedAt":291,"extractAt":292,"updatedAt":291},1778696611346,1778696595410,{"evaluate":294,"extract":302},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":295,"targetMarket":218,"tier":301},[276,277,296,297,298,214,299,300],"ai-coding","self-correction","knowledge-base","hooks","agents","community",{"commitSha":281,"license":282,"plugin":303},{"mcpCount":8,"provider":286,"skillCount":304},34,{"parentExtensionId":264,"repoId":288},[300,296,299,298,277,297,214,276],{"evaluatedAt":308,"extractAt":292,"updatedAt":308},1778696621396,{"evaluate":310,"extract":312},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":311,"targetMarket":218,"tier":219},[211,212,213,214,215,216,217],{"commitSha":281},{"parentExtensionId":251,"repoId":288},{"_creationTime":315,"_id":288,"identity":316,"providers":317,"workflow":804},1778696588306.821,{"githubOwner":246,"githubRepo":247,"sourceUrl":14},{"classify":318,"discover":783,"extract":786,"github":787,"npm":803},{"commitSha":281,"extensions":319},[320,330,471,480,488,496,504,512,520,528,536,544,552,560,568,579,587,595,603,611,619,627,635,642,650,658,666,674,682,694,702,710,742,749,765,775],{"basePath":260,"description":267,"displayName":247,"installMethods":321,"rationale":322,"selectedPaths":323,"source":329,"sourceLanguage":18,"type":270},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[324,327],{"path":325,"priority":326},".claude-plugin/marketplace.json","mandatory",{"path":328,"priority":326},"README.md","rule",{"basePath":260,"description":254,"displayName":247,"installMethods":331,"license":282,"rationale":332,"selectedPaths":333,"source":329,"sourceLanguage":18,"type":261},{"claudeCode":247},"plugin manifest at .claude-plugin/plugin.json",[334,336,337,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469],{"path":335,"priority":326},".claude-plugin/plugin.json",{"path":328,"priority":326},{"path":338,"priority":339},"skills/agent-teams/SKILL.md","medium",{"path":341,"priority":339},"skills/auto-setup/SKILL.md",{"path":343,"priority":339},"skills/batch-orchestration/SKILL.md",{"path":345,"priority":339},"skills/bug-capture/SKILL.md",{"path":347,"priority":339},"skills/compact-guard/SKILL.md",{"path":349,"priority":339},"skills/context-engineering/SKILL.md",{"path":351,"priority":339},"skills/context-optimizer/SKILL.md",{"path":353,"priority":339},"skills/cost-tracker/SKILL.md",{"path":355,"priority":339},"skills/deslop/SKILL.md",{"path":357,"priority":339},"skills/file-watcher/SKILL.md",{"path":359,"priority":339},"skills/insights/SKILL.md",{"path":361,"priority":339},"skills/learn-rule/SKILL.md",{"path":363,"priority":339},"skills/llm-council/SKILL.md",{"path":365,"priority":339},"skills/llm-gate/SKILL.md",{"path":367,"priority":339},"skills/mcp-audit/SKILL.md",{"path":369,"priority":339},"skills/module-map/SKILL.md",{"path":371,"priority":339},"skills/orchestrate/SKILL.md",{"path":373,"priority":339},"skills/parallel-worktrees/SKILL.md",{"path":375,"priority":339},"skills/permission-tuner/SKILL.md",{"path":377,"priority":339},"skills/plan-interrogate/SKILL.md",{"path":379,"priority":339},"skills/pro-workflow/SKILL.md",{"path":381,"priority":339},"skills/replay-learnings/SKILL.md",{"path":383,"priority":339},"skills/safe-mode/SKILL.md",{"path":385,"priority":339},"skills/session-handoff/SKILL.md",{"path":387,"priority":339},"skills/smart-commit/SKILL.md",{"path":389,"priority":339},"skills/sprint-status/SKILL.md",{"path":391,"priority":339},"skills/survey-generator/SKILL.md",{"path":393,"priority":339},"skills/thoroughness-scoring/SKILL.md",{"path":395,"priority":339},"skills/token-efficiency/SKILL.md",{"path":397,"priority":339},"skills/wiki-builder/SKILL.md",{"path":399,"priority":339},"skills/wiki-query/SKILL.md",{"path":401,"priority":339},"skills/wiki-research-loop/SKILL.md",{"path":403,"priority":339},"skills/wiki-viewer/SKILL.md",{"path":405,"priority":339},"skills/wrap-up/SKILL.md",{"path":407,"priority":408},"agents/context-engineer.md","high",{"path":410,"priority":408},"agents/cost-analyst.md",{"path":412,"priority":408},"agents/debugger.md",{"path":414,"priority":408},"agents/orchestrator.md",{"path":416,"priority":408},"agents/permission-analyst.md",{"path":418,"priority":408},"agents/planner.md",{"path":420,"priority":408},"agents/reviewer.md",{"path":422,"priority":408},"agents/scout.md",{"path":424,"priority":408},"commands/auto-setup.md",{"path":426,"priority":408},"commands/commit.md",{"path":428,"priority":408},"commands/compact-guard.md",{"path":430,"priority":408},"commands/context-optimizer.md",{"path":432,"priority":408},"commands/cost-tracker.md",{"path":434,"priority":408},"commands/deslop.md",{"path":436,"priority":408},"commands/develop.md",{"path":438,"priority":408},"commands/doctor.md",{"path":440,"priority":408},"commands/handoff.md",{"path":442,"priority":408},"commands/insights.md",{"path":444,"priority":408},"commands/learn-rule.md",{"path":446,"priority":408},"commands/learn.md",{"path":448,"priority":408},"commands/list.md",{"path":450,"priority":408},"commands/mcp-audit.md",{"path":452,"priority":408},"commands/parallel.md",{"path":454,"priority":408},"commands/permission-tuner.md",{"path":456,"priority":408},"commands/replay.md",{"path":458,"priority":408},"commands/safe-mode.md",{"path":460,"priority":408},"commands/search.md",{"path":462,"priority":408},"commands/sprint-status.md",{"path":464,"priority":408},"commands/wiki.md",{"path":466,"priority":408},"commands/wrap-up.md",{"path":468,"priority":408},"hooks/hooks.json",{"path":470,"priority":408},".cursor-plugin/plugin.json",{"basePath":472,"description":473,"displayName":474,"installMethods":475,"rationale":476,"selectedPaths":477,"source":329,"sourceLanguage":18,"type":248},"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",[478],{"path":479,"priority":326},"SKILL.md",{"basePath":481,"description":482,"displayName":483,"installMethods":484,"rationale":485,"selectedPaths":486,"source":329,"sourceLanguage":18,"type":248},"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",[487],{"path":479,"priority":326},{"basePath":489,"description":490,"displayName":491,"installMethods":492,"rationale":493,"selectedPaths":494,"source":329,"sourceLanguage":18,"type":248},"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",[495],{"path":479,"priority":326},{"basePath":497,"description":498,"displayName":499,"installMethods":500,"rationale":501,"selectedPaths":502,"source":329,"sourceLanguage":18,"type":248},"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",[503],{"path":479,"priority":326},{"basePath":505,"description":506,"displayName":507,"installMethods":508,"rationale":509,"selectedPaths":510,"source":329,"sourceLanguage":18,"type":248},"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",[511],{"path":479,"priority":326},{"basePath":513,"description":514,"displayName":515,"installMethods":516,"rationale":517,"selectedPaths":518,"source":329,"sourceLanguage":18,"type":248},"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",[519],{"path":479,"priority":326},{"basePath":521,"description":522,"displayName":523,"installMethods":524,"rationale":525,"selectedPaths":526,"source":329,"sourceLanguage":18,"type":248},"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",[527],{"path":479,"priority":326},{"basePath":529,"description":530,"displayName":531,"installMethods":532,"rationale":533,"selectedPaths":534,"source":329,"sourceLanguage":18,"type":248},"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",[535],{"path":479,"priority":326},{"basePath":537,"description":538,"displayName":539,"installMethods":540,"rationale":541,"selectedPaths":542,"source":329,"sourceLanguage":18,"type":248},"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",[543],{"path":479,"priority":326},{"basePath":545,"description":546,"displayName":547,"installMethods":548,"rationale":549,"selectedPaths":550,"source":329,"sourceLanguage":18,"type":248},"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",[551],{"path":479,"priority":326},{"basePath":553,"description":554,"displayName":555,"installMethods":556,"rationale":557,"selectedPaths":558,"source":329,"sourceLanguage":18,"type":248},"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",[559],{"path":479,"priority":326},{"basePath":561,"description":562,"displayName":563,"installMethods":564,"rationale":565,"selectedPaths":566,"source":329,"sourceLanguage":18,"type":248},"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",[567],{"path":479,"priority":326},{"basePath":569,"description":570,"displayName":571,"installMethods":572,"rationale":573,"selectedPaths":574,"source":329,"sourceLanguage":18,"type":248},"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",[575,576],{"path":479,"priority":326},{"path":577,"priority":578},"scripts/council.js","low",{"basePath":580,"description":581,"displayName":582,"installMethods":583,"rationale":584,"selectedPaths":585,"source":329,"sourceLanguage":18,"type":248},"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",[586],{"path":479,"priority":326},{"basePath":588,"description":589,"displayName":590,"installMethods":591,"rationale":592,"selectedPaths":593,"source":329,"sourceLanguage":18,"type":248},"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",[594],{"path":479,"priority":326},{"basePath":596,"description":597,"displayName":598,"installMethods":599,"rationale":600,"selectedPaths":601,"source":329,"sourceLanguage":18,"type":248},"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",[602],{"path":479,"priority":326},{"basePath":604,"description":605,"displayName":606,"installMethods":607,"rationale":608,"selectedPaths":609,"source":329,"sourceLanguage":18,"type":248},"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",[610],{"path":479,"priority":326},{"basePath":612,"description":613,"displayName":614,"installMethods":615,"rationale":616,"selectedPaths":617,"source":329,"sourceLanguage":18,"type":248},"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",[618],{"path":479,"priority":326},{"basePath":620,"description":621,"displayName":622,"installMethods":623,"rationale":624,"selectedPaths":625,"source":329,"sourceLanguage":18,"type":248},"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",[626],{"path":479,"priority":326},{"basePath":628,"description":629,"displayName":630,"installMethods":631,"rationale":632,"selectedPaths":633,"source":329,"sourceLanguage":18,"type":248},"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",[634],{"path":479,"priority":326},{"basePath":636,"description":637,"displayName":247,"installMethods":638,"rationale":639,"selectedPaths":640,"source":329,"sourceLanguage":18,"type":248},"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",[641],{"path":479,"priority":326},{"basePath":643,"description":644,"displayName":645,"installMethods":646,"rationale":647,"selectedPaths":648,"source":329,"sourceLanguage":18,"type":248},"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",[649],{"path":479,"priority":326},{"basePath":651,"description":652,"displayName":653,"installMethods":654,"rationale":655,"selectedPaths":656,"source":329,"sourceLanguage":18,"type":248},"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",[657],{"path":479,"priority":326},{"basePath":659,"description":660,"displayName":661,"installMethods":662,"rationale":663,"selectedPaths":664,"source":329,"sourceLanguage":18,"type":248},"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",[665],{"path":479,"priority":326},{"basePath":667,"description":668,"displayName":669,"installMethods":670,"rationale":671,"selectedPaths":672,"source":329,"sourceLanguage":18,"type":248},"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",[673],{"path":479,"priority":326},{"basePath":675,"description":676,"displayName":677,"installMethods":678,"rationale":679,"selectedPaths":680,"source":329,"sourceLanguage":18,"type":248},"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",[681],{"path":479,"priority":326},{"basePath":683,"description":684,"displayName":685,"installMethods":686,"rationale":687,"selectedPaths":688,"source":329,"sourceLanguage":18,"type":248},"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",[689,690,692],{"path":479,"priority":326},{"path":691,"priority":578},"scripts/build-survey.js",{"path":693,"priority":578},"templates/research_bundle.template.json",{"basePath":695,"description":696,"displayName":697,"installMethods":698,"rationale":699,"selectedPaths":700,"source":329,"sourceLanguage":18,"type":248},"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",[701],{"path":479,"priority":326},{"basePath":703,"description":704,"displayName":705,"installMethods":706,"rationale":707,"selectedPaths":708,"source":329,"sourceLanguage":18,"type":248},"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",[709],{"path":479,"priority":326},{"basePath":711,"description":712,"displayName":713,"installMethods":714,"rationale":715,"selectedPaths":716,"source":329,"sourceLanguage":18,"type":248},"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",[717,718,720,722,724,726,728,730,732,734,736,738,740],{"path":479,"priority":326},{"path":719,"priority":339},"references/wiki-flavors.md",{"path":721,"priority":578},"scripts/init_wiki.sh",{"path":723,"priority":578},"scripts/wiki-cli.js",{"path":725,"priority":578},"templates/index.md",{"path":727,"priority":578},"templates/maintenance-log.md",{"path":729,"priority":578},"templates/prompts/compile-concept-page.md",{"path":731,"priority":578},"templates/prompts/compile-index.md",{"path":733,"priority":578},"templates/prompts/compile-source-page.md",{"path":735,"priority":578},"templates/prompts/lint-wiki.md",{"path":737,"priority":578},"templates/prompts/query-and-file.md",{"path":739,"priority":578},"templates/sources.md",{"path":741,"priority":578},"templates/wiki.config.md",{"basePath":245,"description":10,"displayName":13,"installMethods":743,"rationale":744,"selectedPaths":745,"source":329,"sourceLanguage":18,"type":248},{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-query/SKILL.md",[746,747],{"path":479,"priority":326},{"path":748,"priority":578},"scripts/query.js",{"basePath":750,"description":751,"displayName":752,"installMethods":753,"rationale":754,"selectedPaths":755,"source":329,"sourceLanguage":18,"type":248},"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",[756,757,759,761,763],{"path":479,"priority":326},{"path":758,"priority":578},"scripts/research-loop.js",{"path":760,"priority":578},"scripts/source-fetchers/arxiv.js",{"path":762,"priority":578},"scripts/source-fetchers/github.js",{"path":764,"priority":578},"scripts/source-fetchers/web.js",{"basePath":766,"description":767,"displayName":768,"installMethods":769,"rationale":770,"selectedPaths":771,"source":329,"sourceLanguage":18,"type":248},"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",[772,773],{"path":479,"priority":326},{"path":774,"priority":578},"scripts/render.js",{"basePath":776,"description":777,"displayName":778,"installMethods":779,"rationale":780,"selectedPaths":781,"source":329,"sourceLanguage":18,"type":248},"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",[782],{"path":479,"priority":326},{"sources":784},[785],"manual",{"npmPackage":247},{"closedIssues90d":233,"description":788,"forks":234,"homepage":789,"openIssues90d":8,"pushedAt":236,"readmeSize":231,"stars":237,"topics":790},"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",[791,792,793,276,794,795,296,796,797,798,799,800,515,279,801,299,277,297,802],"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":805,"discoverAt":806,"extractAt":807,"githubAt":807,"npmAt":808,"updatedAt":805},1778696594915,1778696588306,1778696590961,1778696593284,[216,215,217,213,212,214,211],{"evaluatedAt":243,"extractAt":292,"updatedAt":243},[],[813,843,871,896,914,941],{"_creationTime":814,"_id":815,"community":816,"display":817,"identity":823,"providers":829,"relations":837,"tags":839,"workflow":840},1778692098392.723,"k171q2y70k2z7p5t62a7zrpw6s86n4kw",{"reviewCount":8},{"description":818,"installMethods":819,"name":821,"sourceUrl":822},"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":820},"larksuite/cli","Lark Wiki CLI","https://github.com/larksuite/cli",{"basePath":824,"githubOwner":825,"githubRepo":826,"locale":827,"slug":828,"type":248},"skills/lark-wiki","larksuite","cli","zh-CN","lark-wiki",{"evaluate":830,"extract":836},{"promptVersionExtension":204,"promptVersionScoring":205,"score":831,"tags":832,"targetMarket":218,"tier":219},100,[833,834,211,217,835,826],"lark","feishu","automation",{"commitSha":281,"license":282},{"repoId":838},"kd7akv5cxs7vx53ys6jsrv85v186mha4",[835,826,834,217,833,211],{"evaluatedAt":841,"extractAt":842,"updatedAt":841},1778692680305,1778692098392,{"_creationTime":844,"_id":845,"community":846,"display":847,"identity":853,"providers":856,"relations":864,"tags":867,"workflow":868},1778675056600.238,"k17bzapecn7k6jdgt1ag6rda2s86m06p",{"reviewCount":8},{"description":848,"installMethods":849,"name":851,"sourceUrl":852},"Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.",{"claudeCode":850},"alirezarezvani/claude-skills","rag-architect","https://github.com/alirezarezvani/claude-skills",{"basePath":854,"githubOwner":855,"githubRepo":799,"locale":18,"slug":851,"type":248},"engineering/skills/rag-architect","alirezarezvani",{"evaluate":857,"extract":863},{"promptVersionExtension":204,"promptVersionScoring":205,"score":831,"tags":858,"targetMarket":218,"tier":219},[859,860,861,862,213,217],"rag","llm","embedding","vector-search",{"commitSha":281},{"parentExtensionId":865,"repoId":866},"k173223hfbd6c4mx6r1jdx23wn86mbpb","kd7ff9s1w43mfyy1n7hf87816186m6px",[861,217,860,859,213,862],{"evaluatedAt":869,"extractAt":870,"updatedAt":869},1778678924736,1778675056600,{"_creationTime":872,"_id":873,"community":874,"display":875,"identity":879,"providers":882,"relations":891,"tags":893,"workflow":894},1778675056600.2317,"k17cxt9ps1s1vkzp0d0eq7pkt986m6gg",{"reviewCount":8},{"description":876,"installMethods":877,"name":878,"sourceUrl":852},"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":850},"LLM Wiki",{"basePath":880,"githubOwner":855,"githubRepo":799,"locale":18,"slug":881,"type":248},"engineering/llm-wiki/skills/llm-wiki","llm-wiki",{"evaluate":883,"extract":890},{"promptVersionExtension":204,"promptVersionScoring":205,"score":831,"tags":884,"targetMarket":218,"tier":219},[217,885,886,887,888,211,889],"obsidian","second-brain","pkm","rag-alternative","personal-knowledge-management",{"commitSha":281,"license":282},{"parentExtensionId":892,"repoId":866},"k171h6s4fcrd2pepndhe1tnjgd86mbgr",[217,885,889,887,888,886,211],{"evaluatedAt":895,"extractAt":870,"updatedAt":895},1778678327640,{"_creationTime":897,"_id":898,"community":899,"display":900,"identity":903,"providers":904,"relations":910,"tags":911,"workflow":912},1778696595410.5647,"k1782531n7gq0bdhans1kp3tr586mr8x",{"reviewCount":8},{"description":570,"installMethods":901,"name":902,"sourceUrl":14},{"claudeCode":12},"LLM Council",{"basePath":569,"githubOwner":246,"githubRepo":247,"locale":18,"slug":571,"type":248},{"evaluate":905,"extract":909},{"promptVersionExtension":204,"promptVersionScoring":205,"score":274,"tags":906,"targetMarket":218,"tier":219},[860,907,908,217,211,826],"deliberation","multi-llm",{"commitSha":281,"license":282},{"parentExtensionId":251,"repoId":288},[826,907,217,860,908,211],{"evaluatedAt":913,"extractAt":292,"updatedAt":913},1778696824062,{"_creationTime":915,"_id":916,"community":917,"display":918,"identity":924,"providers":928,"relations":935,"tags":937,"workflow":938},1778696691708.2996,"k175z5j3knm69exj7qpfwy3e1586nh3w",{"reviewCount":8},{"description":919,"installMethods":920,"name":922,"sourceUrl":923},"Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.\n",{"claudeCode":921},"ruvnet/ruflo","embeddings","https://github.com/ruvnet/ruflo",{"basePath":925,"githubOwner":926,"githubRepo":927,"locale":18,"slug":922,"type":248},".agents/skills/embeddings","ruvnet","ruflo",{"evaluate":929,"extract":934},{"promptVersionExtension":204,"promptVersionScoring":205,"score":274,"tags":930,"targetMarket":218,"tier":219},[922,862,931,932,933,212,213],"hnsw","sql-js","ai",{"commitSha":281},{"repoId":936},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[933,922,931,213,212,932,862],{"evaluatedAt":939,"extractAt":940,"updatedAt":939},1778698905205,1778696691708,{"_creationTime":942,"_id":943,"community":944,"display":945,"identity":947,"providers":948,"relations":954,"tags":955,"workflow":956},1778696595410.5688,"k175aswqxy754yaatfbja8ntnd86nprj",{"reviewCount":8},{"description":712,"installMethods":946,"name":713,"sourceUrl":14},{"claudeCode":12},{"basePath":711,"githubOwner":246,"githubRepo":247,"locale":18,"slug":713,"type":248},{"evaluate":949,"extract":953},{"promptVersionExtension":204,"promptVersionScoring":205,"score":274,"tags":950,"targetMarket":218,"tier":219},[211,298,214,951,952,826],"markdown","research",{"commitSha":281},{"parentExtensionId":251,"repoId":288},[826,298,951,952,214,211],{"evaluatedAt":957,"extractAt":292,"updatedAt":957},1778697086509]