[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-rohitg00-learn-rule-en":3,"guides-for-rohitg00-learn-rule":812,"similar-k179kekkybmxzk1e4b4me8zr7h86n8w5-en":813},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":242,"isFallback":233,"parentExtension":247,"providers":310,"relations":314,"repo":315,"tags":810,"workflow":811},1778696595410.5645,"k179kekkybmxzk1e4b4me8zr7h86n8w5",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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\".",{"claudeCode":12},"rohitg00/pro-workflow","learn-rule","https://github.com/rohitg00/pro-workflow",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":240},1778696809347.3054,"kn7336m2fbn2mwf7dgg6rtjhch86nvsz","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":216,"tier":217,"useCases":218},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,114,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of repeating mistakes and forgotten learnings, and identifies the user as a \"Claude Code user\" facing this wall.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers a persistent SQLite store for self-correction memory and knowledge wikis, which is a significant enhancement over default LLM behavior and provides value beyond simple prompting.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a complete lifecycle for learning rules and knowledge management, including storage, retrieval, and optional auto-research, making it suitable for real-world workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on capturing, storing, and retrieving learning rules and knowledge, with a clear focus on memory and knowledge management within the Claude Code environment.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's purpose of capturing and managing learning rules, aligning well with the provided SKILL.md content.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill appears to operate as a single unit and does not expose multiple distinct tools, making the check for narrow vs. generalist tools not applicable.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","The skill's functionality is driven by natural language triggers and internal logic rather than explicit parameters or configuration files exposed to the user, rendering this check not applicable.",{"category":33,"check":49,"severity":24,"summary":50},"Tool naming","The skill is invoked via natural language triggers and the `/learn-rule` command, which are descriptive and domain-appropriate.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","The skill operates primarily through natural language interaction and internal state management, without exposing explicit tool parameter schemas or complex response shapes that would necessitate this check.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The project explicitly states an MIT license in the README and shields, indicating a permissive open-source license.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The last commit was on 2026-05-12, which is within the last 3 months.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","The project is an npm package with a lockfile, suggesting dependency management is handled.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill focuses on learning and memory and does not appear to handle or expose secrets directly.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill's documentation emphasizes treating content as data and focuses on learning rules, implying a resistance to executing arbitrary instructions from loaded data.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill operates on user-defined rules and internal state, with no indication of fetching external code or content at runtime for execution.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates within the Claude Code environment, managing its own state and not modifying files outside its designated scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","There are no indications of detached process spawns or deny-retry loops in the provided skill description or context.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill is designed to capture user-defined rules and knowledge, with no mechanisms for exfiltrating confidential data to third parties.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The provided documentation and SKILL.md content appear to be free of hidden steering tricks or obfuscated instructions.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill description and SKILL.md do not suggest any use of obfuscated code, base64 payloads, or runtime script fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill relies on the Claude Code environment and its internal state management, making no assumptions about user project file layouts.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","With 0 open and 5 closed issues in the last 90 days, maintainer engagement appears high.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The project has a `package.json` with a version and is available via npm, indicating versioned releases.",{"category":104,"check":105,"severity":42,"summary":106},"Execution","Validation","The skill's primary interaction is through natural language and internal state management, not through user-provided arguments that require schema validation.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill's core function is to capture and store information, not to perform destructive operations on the user's system.",{"category":111,"check":112,"severity":24,"summary":113},"Code Execution","Error Handling","The skill's documentation implies robust error handling for state persistence and user interaction, aiming for clear reporting and user approval.",{"category":111,"check":115,"severity":42,"summary":116},"Logging","As this skill focuses on in-session learning and does not perform destructive actions or outbound calls, a local audit log is not a primary requirement.",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","The skill captures user-defined rules and knowledge, and does not appear to operate on or submit personal data to third parties.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The skill's functionality is general and not tied to any specific geographic or legal jurisdiction; it is globally applicable.",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","The skill operates within the Claude Code environment and does not rely on specific OS, shell, or editor assumptions.",{"category":45,"check":128,"severity":24,"summary":129},"README","The README is extensive, well-structured, and clearly states the project's purpose and capabilities.",{"category":33,"check":131,"severity":42,"summary":132},"Tool surface size","This is a single skill invoked via natural language or a specific command, not a collection of tools.",{"category":40,"check":134,"severity":42,"summary":135},"Overlapping near-synonym tools","The skill primarily uses natural language triggers and a single command (`/learn-rule`), avoiding overlapping synonyms.",{"category":45,"check":137,"severity":24,"summary":138},"Phantom features","All advertised features related to learning rules and persistence are implemented and described in the SKILL.md and README.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides clear installation instructions using `/plugin marketplace add` and other methods, along with a 60-second tour demonstrating usage.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","The documentation implies that errors related to rule persistence and user interaction will be actionable, requiring user approval and providing context.",{"category":104,"check":148,"severity":24,"summary":149},"Pinned dependencies","The project is an npm package and has a lockfile, indicating pinned dependencies.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The skill's core function of capturing and storing learning rules is not a state-changing operation that typically requires a dry-run preview.",{"category":154,"check":155,"severity":42,"summary":156},"Protocol","Idempotent retry & timeouts","The skill operates locally and synchronously, not involving remote calls or state-changing operations that require idempotency or timeouts.",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","There is no mention of telemetry being collected; the focus is on local state and user-defined learning rules.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill clearly defines its purpose as capturing learning rules with category, mistake, and correction, and specifies triggers like \"remember this\" or \"after a mistake\", with explicit use cases and guardrails.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The SKILL.md frontmatter is concise, clearly stating the name and description, which are self-contained and immediately understandable.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-organized with clear sections and does not appear excessively long or bloat the context window.",{"category":170,"check":171,"severity":42,"summary":172},"Context","Progressive Disclosure","The skill's functionality is straightforward and does not involve complex procedures or large amounts of embedded material that would require progressive disclosure.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","The skill's purpose is direct learning capture, not deep exploration or code review, making `context: fork` not applicable.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md provides a clear example demonstrating the input format, the intended output, and the user interaction flow.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The 'Guardrails' section in SKILL.md addresses edge cases like waiting for approval, rule specificity, and context inclusion.",{"category":111,"check":183,"severity":42,"summary":184},"Tool Fallback","This skill does not appear to rely on external MCP servers or tools that would require fallbacks.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The 'Guardrails' section emphasizes waiting for user approval before persisting, which implies a halt on unexpected or unapproved states.",{"category":92,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill focuses on its core function of learning rules and does not appear to implicitly rely on other skills or cross-link without explicit declaration.",1778696809236,"This skill enables users to capture lessons and corrections as persistent, categorized learning rules within the Claude Code environment. It stores, categorizes, and retrieves these rules, integrating with a local SQLite store for session memory and optionally linking them to project-specific wikis.",[195,196,197,198,199],"Capture learning rules with category, mistake, and correction","Persistently store and categorize rules","Retrieve rules for future sessions","Scope rules to specific project wikis","Auto-detection of rule addition via specific triggers",[201,202,203],"Replacing all forms of AI learning","Managing general project documentation","Acting as a broad knowledge retrieval system outside of learned rules","3.0.0","4.4.0","To enhance AI productivity by preventing repeated mistakes and building a persistent knowledge base from user corrections and insights.","The skill is well-documented, secure, and adheres to best practices. Its core functionality of capturing learning rules is robust and well-supported by clear documentation and examples.",98,"A highly polished skill for capturing and managing persistent learning rules.",[211,212,213,214,215],"learning","memory","rules","persistence","llm","global","verified",[219,220,221,222],"Use after mistakes are identified to prevent recurrence","Use when the user explicitly asks to remember something","Use to build a persistent knowledge base for specific projects or topics","Use to enforce consistent coding conventions and best practices",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"popularity":236,"security":238,"testCoverage":239},{"hasLockfile":225},true,1778696795484,{"descriptionLength":228,"readmeSize":229},271,22012,{"closedIssues90d":231,"forks":232,"hasChangelog":233,"openIssues90d":8,"pushedAt":234,"stars":235},5,203,false,1778554780000,2113,{"npmDownloads":237},611,{"hasNpmPackage":225,"smitheryVerified":233},{"hasCi":225,"hasTests":233},{"updatedAt":241},1778696809347,{"basePath":243,"githubOwner":244,"githubRepo":245,"locale":18,"slug":13,"type":246},"skills/learn-rule","rohitg00","pro-workflow","skill",{"_creationTime":248,"_id":249,"community":250,"display":251,"identity":257,"parentExtension":260,"providers":292,"relations":306,"tags":307,"workflow":308},1778696595410.5615,"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv",{"reviewCount":8},{"description":252,"installMethods":253,"name":256,"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":245,"cursor":254,"npm":245,"skillkit":255},"/add-plugin pro-workflow","npx skillkit install pro-workflow","Pro Workflow",{"basePath":258,"githubOwner":244,"githubRepo":245,"locale":18,"slug":245,"type":259},"","plugin",{"_creationTime":261,"_id":262,"community":263,"display":264,"identity":267,"providers":269,"relations":286,"tags":288,"workflow":289},1778696595410.5613,"k1741gyqaf0tj1ffq65gjpsm6x86mfhx",{"reviewCount":8},{"description":265,"installMethods":266,"name":256,"sourceUrl":14},"Battle-tested Claude Code workflows from power users",{"claudeCode":12},{"basePath":258,"githubOwner":244,"githubRepo":245,"locale":18,"slug":245,"type":268},"marketplace",{"evaluate":270,"extract":279},{"promptVersionExtension":271,"promptVersionScoring":205,"score":272,"tags":273,"targetMarket":216,"tier":217},"3.1.0",99,[274,275,276,277,278],"workflow","productivity","ai-assistance","developer-tools","knowledge-management",{"commitSha":280,"license":281,"marketplace":282,"plugin":284},"HEAD","MIT",{"name":245,"pluginCount":283},1,{"mcpCount":8,"provider":285,"skillCount":8},"classify",{"repoId":287},"kd7am4e918eq98hrd9s31jm4vs86nn0b",[276,277,278,275,274],{"evaluatedAt":290,"extractAt":291,"updatedAt":290},1778696611346,1778696595410,{"evaluate":293,"extract":303},{"promptVersionExtension":204,"promptVersionScoring":205,"score":294,"tags":295,"targetMarket":216,"tier":302},96,[274,275,296,297,298,299,300,301],"ai-coding","self-correction","knowledge-base","sqlite","hooks","agents","community",{"commitSha":280,"license":281,"plugin":304},{"mcpCount":8,"provider":285,"skillCount":305},34,{"parentExtensionId":262,"repoId":287},[301,296,300,298,275,297,299,274],{"evaluatedAt":309,"extractAt":291,"updatedAt":309},1778696621396,{"evaluate":311,"extract":313},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":312,"targetMarket":216,"tier":217},[211,212,213,214,215],{"commitSha":280},{"parentExtensionId":249,"repoId":287},{"_creationTime":316,"_id":287,"identity":317,"providers":318,"workflow":805},1778696588306.821,{"githubOwner":244,"githubRepo":245,"sourceUrl":14},{"classify":319,"discover":784,"extract":787,"github":788,"npm":804},{"commitSha":280,"extensions":320},[321,331,472,481,489,497,505,513,521,529,537,545,553,561,566,577,585,593,601,609,617,625,633,640,648,656,664,672,680,692,700,708,740,750,766,776],{"basePath":258,"description":265,"displayName":245,"installMethods":322,"rationale":323,"selectedPaths":324,"source":330,"sourceLanguage":18,"type":268},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[325,328],{"path":326,"priority":327},".claude-plugin/marketplace.json","mandatory",{"path":329,"priority":327},"README.md","rule",{"basePath":258,"description":252,"displayName":245,"installMethods":332,"license":281,"rationale":333,"selectedPaths":334,"source":330,"sourceLanguage":18,"type":259},{"claudeCode":245},"plugin manifest at .claude-plugin/plugin.json",[335,337,338,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470],{"path":336,"priority":327},".claude-plugin/plugin.json",{"path":329,"priority":327},{"path":339,"priority":340},"skills/agent-teams/SKILL.md","medium",{"path":342,"priority":340},"skills/auto-setup/SKILL.md",{"path":344,"priority":340},"skills/batch-orchestration/SKILL.md",{"path":346,"priority":340},"skills/bug-capture/SKILL.md",{"path":348,"priority":340},"skills/compact-guard/SKILL.md",{"path":350,"priority":340},"skills/context-engineering/SKILL.md",{"path":352,"priority":340},"skills/context-optimizer/SKILL.md",{"path":354,"priority":340},"skills/cost-tracker/SKILL.md",{"path":356,"priority":340},"skills/deslop/SKILL.md",{"path":358,"priority":340},"skills/file-watcher/SKILL.md",{"path":360,"priority":340},"skills/insights/SKILL.md",{"path":362,"priority":340},"skills/learn-rule/SKILL.md",{"path":364,"priority":340},"skills/llm-council/SKILL.md",{"path":366,"priority":340},"skills/llm-gate/SKILL.md",{"path":368,"priority":340},"skills/mcp-audit/SKILL.md",{"path":370,"priority":340},"skills/module-map/SKILL.md",{"path":372,"priority":340},"skills/orchestrate/SKILL.md",{"path":374,"priority":340},"skills/parallel-worktrees/SKILL.md",{"path":376,"priority":340},"skills/permission-tuner/SKILL.md",{"path":378,"priority":340},"skills/plan-interrogate/SKILL.md",{"path":380,"priority":340},"skills/pro-workflow/SKILL.md",{"path":382,"priority":340},"skills/replay-learnings/SKILL.md",{"path":384,"priority":340},"skills/safe-mode/SKILL.md",{"path":386,"priority":340},"skills/session-handoff/SKILL.md",{"path":388,"priority":340},"skills/smart-commit/SKILL.md",{"path":390,"priority":340},"skills/sprint-status/SKILL.md",{"path":392,"priority":340},"skills/survey-generator/SKILL.md",{"path":394,"priority":340},"skills/thoroughness-scoring/SKILL.md",{"path":396,"priority":340},"skills/token-efficiency/SKILL.md",{"path":398,"priority":340},"skills/wiki-builder/SKILL.md",{"path":400,"priority":340},"skills/wiki-query/SKILL.md",{"path":402,"priority":340},"skills/wiki-research-loop/SKILL.md",{"path":404,"priority":340},"skills/wiki-viewer/SKILL.md",{"path":406,"priority":340},"skills/wrap-up/SKILL.md",{"path":408,"priority":409},"agents/context-engineer.md","high",{"path":411,"priority":409},"agents/cost-analyst.md",{"path":413,"priority":409},"agents/debugger.md",{"path":415,"priority":409},"agents/orchestrator.md",{"path":417,"priority":409},"agents/permission-analyst.md",{"path":419,"priority":409},"agents/planner.md",{"path":421,"priority":409},"agents/reviewer.md",{"path":423,"priority":409},"agents/scout.md",{"path":425,"priority":409},"commands/auto-setup.md",{"path":427,"priority":409},"commands/commit.md",{"path":429,"priority":409},"commands/compact-guard.md",{"path":431,"priority":409},"commands/context-optimizer.md",{"path":433,"priority":409},"commands/cost-tracker.md",{"path":435,"priority":409},"commands/deslop.md",{"path":437,"priority":409},"commands/develop.md",{"path":439,"priority":409},"commands/doctor.md",{"path":441,"priority":409},"commands/handoff.md",{"path":443,"priority":409},"commands/insights.md",{"path":445,"priority":409},"commands/learn-rule.md",{"path":447,"priority":409},"commands/learn.md",{"path":449,"priority":409},"commands/list.md",{"path":451,"priority":409},"commands/mcp-audit.md",{"path":453,"priority":409},"commands/parallel.md",{"path":455,"priority":409},"commands/permission-tuner.md",{"path":457,"priority":409},"commands/replay.md",{"path":459,"priority":409},"commands/safe-mode.md",{"path":461,"priority":409},"commands/search.md",{"path":463,"priority":409},"commands/sprint-status.md",{"path":465,"priority":409},"commands/wiki.md",{"path":467,"priority":409},"commands/wrap-up.md",{"path":469,"priority":409},"hooks/hooks.json",{"path":471,"priority":409},".cursor-plugin/plugin.json",{"basePath":473,"description":474,"displayName":475,"installMethods":476,"rationale":477,"selectedPaths":478,"source":330,"sourceLanguage":18,"type":246},"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",[479],{"path":480,"priority":327},"SKILL.md",{"basePath":482,"description":483,"displayName":484,"installMethods":485,"rationale":486,"selectedPaths":487,"source":330,"sourceLanguage":18,"type":246},"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",[488],{"path":480,"priority":327},{"basePath":490,"description":491,"displayName":492,"installMethods":493,"rationale":494,"selectedPaths":495,"source":330,"sourceLanguage":18,"type":246},"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",[496],{"path":480,"priority":327},{"basePath":498,"description":499,"displayName":500,"installMethods":501,"rationale":502,"selectedPaths":503,"source":330,"sourceLanguage":18,"type":246},"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",[504],{"path":480,"priority":327},{"basePath":506,"description":507,"displayName":508,"installMethods":509,"rationale":510,"selectedPaths":511,"source":330,"sourceLanguage":18,"type":246},"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",[512],{"path":480,"priority":327},{"basePath":514,"description":515,"displayName":516,"installMethods":517,"rationale":518,"selectedPaths":519,"source":330,"sourceLanguage":18,"type":246},"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",[520],{"path":480,"priority":327},{"basePath":522,"description":523,"displayName":524,"installMethods":525,"rationale":526,"selectedPaths":527,"source":330,"sourceLanguage":18,"type":246},"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",[528],{"path":480,"priority":327},{"basePath":530,"description":531,"displayName":532,"installMethods":533,"rationale":534,"selectedPaths":535,"source":330,"sourceLanguage":18,"type":246},"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",[536],{"path":480,"priority":327},{"basePath":538,"description":539,"displayName":540,"installMethods":541,"rationale":542,"selectedPaths":543,"source":330,"sourceLanguage":18,"type":246},"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",[544],{"path":480,"priority":327},{"basePath":546,"description":547,"displayName":548,"installMethods":549,"rationale":550,"selectedPaths":551,"source":330,"sourceLanguage":18,"type":246},"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",[552],{"path":480,"priority":327},{"basePath":554,"description":555,"displayName":556,"installMethods":557,"rationale":558,"selectedPaths":559,"source":330,"sourceLanguage":18,"type":246},"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",[560],{"path":480,"priority":327},{"basePath":243,"description":10,"displayName":13,"installMethods":562,"rationale":563,"selectedPaths":564,"source":330,"sourceLanguage":18,"type":246},{"claudeCode":12},"SKILL.md frontmatter at skills/learn-rule/SKILL.md",[565],{"path":480,"priority":327},{"basePath":567,"description":568,"displayName":569,"installMethods":570,"rationale":571,"selectedPaths":572,"source":330,"sourceLanguage":18,"type":246},"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",[573,574],{"path":480,"priority":327},{"path":575,"priority":576},"scripts/council.js","low",{"basePath":578,"description":579,"displayName":580,"installMethods":581,"rationale":582,"selectedPaths":583,"source":330,"sourceLanguage":18,"type":246},"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",[584],{"path":480,"priority":327},{"basePath":586,"description":587,"displayName":588,"installMethods":589,"rationale":590,"selectedPaths":591,"source":330,"sourceLanguage":18,"type":246},"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",[592],{"path":480,"priority":327},{"basePath":594,"description":595,"displayName":596,"installMethods":597,"rationale":598,"selectedPaths":599,"source":330,"sourceLanguage":18,"type":246},"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",[600],{"path":480,"priority":327},{"basePath":602,"description":603,"displayName":604,"installMethods":605,"rationale":606,"selectedPaths":607,"source":330,"sourceLanguage":18,"type":246},"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",[608],{"path":480,"priority":327},{"basePath":610,"description":611,"displayName":612,"installMethods":613,"rationale":614,"selectedPaths":615,"source":330,"sourceLanguage":18,"type":246},"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",[616],{"path":480,"priority":327},{"basePath":618,"description":619,"displayName":620,"installMethods":621,"rationale":622,"selectedPaths":623,"source":330,"sourceLanguage":18,"type":246},"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",[624],{"path":480,"priority":327},{"basePath":626,"description":627,"displayName":628,"installMethods":629,"rationale":630,"selectedPaths":631,"source":330,"sourceLanguage":18,"type":246},"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",[632],{"path":480,"priority":327},{"basePath":634,"description":635,"displayName":245,"installMethods":636,"rationale":637,"selectedPaths":638,"source":330,"sourceLanguage":18,"type":246},"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",[639],{"path":480,"priority":327},{"basePath":641,"description":642,"displayName":643,"installMethods":644,"rationale":645,"selectedPaths":646,"source":330,"sourceLanguage":18,"type":246},"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",[647],{"path":480,"priority":327},{"basePath":649,"description":650,"displayName":651,"installMethods":652,"rationale":653,"selectedPaths":654,"source":330,"sourceLanguage":18,"type":246},"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",[655],{"path":480,"priority":327},{"basePath":657,"description":658,"displayName":659,"installMethods":660,"rationale":661,"selectedPaths":662,"source":330,"sourceLanguage":18,"type":246},"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",[663],{"path":480,"priority":327},{"basePath":665,"description":666,"displayName":667,"installMethods":668,"rationale":669,"selectedPaths":670,"source":330,"sourceLanguage":18,"type":246},"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",[671],{"path":480,"priority":327},{"basePath":673,"description":674,"displayName":675,"installMethods":676,"rationale":677,"selectedPaths":678,"source":330,"sourceLanguage":18,"type":246},"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",[679],{"path":480,"priority":327},{"basePath":681,"description":682,"displayName":683,"installMethods":684,"rationale":685,"selectedPaths":686,"source":330,"sourceLanguage":18,"type":246},"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",[687,688,690],{"path":480,"priority":327},{"path":689,"priority":576},"scripts/build-survey.js",{"path":691,"priority":576},"templates/research_bundle.template.json",{"basePath":693,"description":694,"displayName":695,"installMethods":696,"rationale":697,"selectedPaths":698,"source":330,"sourceLanguage":18,"type":246},"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",[699],{"path":480,"priority":327},{"basePath":701,"description":702,"displayName":703,"installMethods":704,"rationale":705,"selectedPaths":706,"source":330,"sourceLanguage":18,"type":246},"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",[707],{"path":480,"priority":327},{"basePath":709,"description":710,"displayName":711,"installMethods":712,"rationale":713,"selectedPaths":714,"source":330,"sourceLanguage":18,"type":246},"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",[715,716,718,720,722,724,726,728,730,732,734,736,738],{"path":480,"priority":327},{"path":717,"priority":340},"references/wiki-flavors.md",{"path":719,"priority":576},"scripts/init_wiki.sh",{"path":721,"priority":576},"scripts/wiki-cli.js",{"path":723,"priority":576},"templates/index.md",{"path":725,"priority":576},"templates/maintenance-log.md",{"path":727,"priority":576},"templates/prompts/compile-concept-page.md",{"path":729,"priority":576},"templates/prompts/compile-index.md",{"path":731,"priority":576},"templates/prompts/compile-source-page.md",{"path":733,"priority":576},"templates/prompts/lint-wiki.md",{"path":735,"priority":576},"templates/prompts/query-and-file.md",{"path":737,"priority":576},"templates/sources.md",{"path":739,"priority":576},"templates/wiki.config.md",{"basePath":741,"description":742,"displayName":743,"installMethods":744,"rationale":745,"selectedPaths":746,"source":330,"sourceLanguage":18,"type":246},"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",[747,748],{"path":480,"priority":327},{"path":749,"priority":576},"scripts/query.js",{"basePath":751,"description":752,"displayName":753,"installMethods":754,"rationale":755,"selectedPaths":756,"source":330,"sourceLanguage":18,"type":246},"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",[757,758,760,762,764],{"path":480,"priority":327},{"path":759,"priority":576},"scripts/research-loop.js",{"path":761,"priority":576},"scripts/source-fetchers/arxiv.js",{"path":763,"priority":576},"scripts/source-fetchers/github.js",{"path":765,"priority":576},"scripts/source-fetchers/web.js",{"basePath":767,"description":768,"displayName":769,"installMethods":770,"rationale":771,"selectedPaths":772,"source":330,"sourceLanguage":18,"type":246},"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",[773,774],{"path":480,"priority":327},{"path":775,"priority":576},"scripts/render.js",{"basePath":777,"description":778,"displayName":779,"installMethods":780,"rationale":781,"selectedPaths":782,"source":330,"sourceLanguage":18,"type":246},"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",[783],{"path":480,"priority":327},{"sources":785},[786],"manual",{"npmPackage":245},{"closedIssues90d":231,"description":789,"forks":232,"homepage":790,"openIssues90d":8,"pushedAt":234,"readmeSize":229,"stars":235,"topics":791},"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",[792,793,794,274,795,796,296,797,798,799,800,801,516,277,802,300,275,297,803],"claude","claude-code","cursor","agent-orchestration","ai-agents","ai-workflow","claude-code-plugin","claude-code-skills","claude-skills","codex","gemini-cli","worktrees",{"downloads":237},{"classifiedAt":806,"discoverAt":807,"extractAt":808,"githubAt":808,"npmAt":809,"updatedAt":806},1778696594915,1778696588306,1778696590961,1778696593284,[211,215,212,214,213],{"evaluatedAt":241,"extractAt":291,"updatedAt":241},[],[814,832,863,891,919,945],{"_creationTime":815,"_id":816,"community":817,"display":818,"identity":821,"providers":822,"relations":828,"tags":829,"workflow":830},1778696595410.5698,"k171sdysmt658g1cdd7hgt8p8h86nms7",{"reviewCount":8},{"description":778,"installMethods":819,"name":820,"sourceUrl":14},{"claudeCode":12},"Wrap-Up Ritual",{"basePath":777,"githubOwner":244,"githubRepo":245,"locale":18,"slug":779,"type":246},{"evaluate":823,"extract":827},{"promptVersionExtension":204,"promptVersionScoring":205,"score":824,"tags":825,"targetMarket":216,"tier":217},100,[274,215,275,212,298,826],"code-quality",{"commitSha":280,"license":281},{"parentExtensionId":249,"repoId":287},[826,298,215,212,275,274],{"evaluatedAt":831,"extractAt":291,"updatedAt":831},1778697164619,{"_creationTime":833,"_id":834,"community":835,"display":836,"identity":842,"providers":847,"relations":855,"tags":858,"workflow":859},1778693539593.1858,"k171p5pgbfbm5g4k5sa3y4cj9s86m6hk",{"reviewCount":8},{"description":837,"installMethods":838,"name":840,"sourceUrl":841},"Domain knowledge for the Evolution Engine — LLM-powered autonomous strategy discovery from raw OHLCV data. Covers the generate-backtest-select-evolve loop, vectorized backtesting, out-of-sample validation, and strategy graduation. Use when discovering trading patterns, running backtests, evolving strategies, or reviewing evolution logs. Triggers on \"evolve\", \"discover patterns\", \"backtest\", \"evolution\", \"strategy generation\", \"candidate strategy\".",{"claudeCode":839},"mnemox-ai/tradememory-protocol","TradeMemory Protocol","https://github.com/mnemox-ai/tradememory-protocol",{"basePath":843,"githubOwner":844,"githubRepo":845,"locale":18,"slug":846,"type":246},"tradememory-plugin/skills/evolution-engine","mnemox-ai","tradememory-protocol","evolution-engine",{"evaluate":848,"extract":854},{"promptVersionExtension":204,"promptVersionScoring":205,"score":824,"tags":849,"targetMarket":216,"tier":217},[850,851,212,852,853,215],"trading","ai","audit","compliance",{"commitSha":280,"license":281},{"parentExtensionId":856,"repoId":857},"k170vxkqee48k2xq1v55a025nh86nzn7","kd73z11kfekksxyrs8ds0snacs86ncdy",[851,852,853,215,212,850],{"evaluatedAt":860,"extractAt":861,"updatedAt":862},1778693678813,1778693539593,1778693832942,{"_creationTime":864,"_id":865,"community":866,"display":867,"identity":873,"providers":877,"relations":884,"tags":887,"workflow":888},1778683562157.8755,"k170hhfkx545yd99mvxa5xqamd86m4sv",{"reviewCount":8},{"description":868,"installMethods":869,"name":871,"sourceUrl":872},"Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to automate memory behavior based on conditions.",{"claudeCode":870},"cdeust/Cortex","cortex-automate","https://github.com/cdeust/Cortex",{"basePath":874,"githubOwner":875,"githubRepo":876,"locale":18,"slug":871,"type":246},"skills/cortex-automate","cdeust","Cortex",{"evaluate":878,"extract":883},{"promptVersionExtension":204,"promptVersionScoring":205,"score":824,"tags":879,"targetMarket":216,"tier":217},[880,212,881,213,882,274],"automation","triggers","sync",{"commitSha":280},{"parentExtensionId":885,"repoId":886},"k1739s9t9kj9bmjq1z4byk17g986mv7x","kd79gxpemvkr09a7zsb3h8kmah86nvgf",[880,212,213,882,881,274],{"evaluatedAt":889,"extractAt":890,"updatedAt":889},1778683620696,1778683562157,{"_creationTime":892,"_id":893,"community":894,"display":895,"identity":901,"providers":904,"relations":912,"tags":914,"workflow":915},1778691193352.519,"k17b92m937rpcpsdzk2tpkbx1186n7d4",{"reviewCount":8},{"description":896,"installMethods":897,"name":899,"sourceUrl":900},"Persistent correction system that captures mistakes from skills or Claude behavior and ensures they never repeat across sessions. Use whenever the user indicates something went wrong — \"that's wrong\", \"fix this\", \"not what I wanted\", \"learn from this\", \"don't do that again\", \"esto está mal\", \"aprende de esto\", \"no hagas eso otra vez\", or any correction, complaint, or teaching moment about Claude's output or a skill's behavior. Also use when the user asks to review, list, delete, or manage past corrections, or wants to create an improvement proposal for a skill author. Covers installed skills, general Claude behavior, and cross-session learning persistence.\n",{"claudeCode":898},"j4rk0r/claude-skills","skill-learner","https://github.com/j4rk0r/claude-skills",{"basePath":902,"githubOwner":903,"githubRepo":800,"locale":18,"slug":899,"type":246},"skills/skill-learner","j4rk0r",{"evaluate":905,"extract":911},{"promptVersionExtension":204,"promptVersionScoring":205,"score":272,"tags":906,"targetMarket":216,"tier":217},[211,907,214,908,909,910],"corrections","skills","behavioral-tuning","auditing",{"commitSha":280},{"repoId":913},"kd79shaph0e07035621cxd7x1n86m944",[910,909,907,211,214,908],{"evaluatedAt":916,"extractAt":917,"updatedAt":918},1778691334993,1778691193352,1778691485659,{"_creationTime":920,"_id":921,"community":922,"display":923,"identity":929,"providers":934,"relations":939,"tags":941,"workflow":942},1778698371743.7043,"k179rk9j081qefqrd7ebwnx9yx86msv2",{"reviewCount":8},{"description":924,"installMethods":925,"name":927,"sourceUrl":928},"Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user)",{"claudeCode":926},"vectorize-io/hindsight","Hindsight Memory Skill","https://github.com/vectorize-io/hindsight",{"basePath":930,"githubOwner":931,"githubRepo":932,"locale":18,"slug":933,"type":246},"skills/hindsight-local","vectorize-io","hindsight","hindsight-local",{"evaluate":935,"extract":938},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":936,"targetMarket":216,"tier":217},[212,937,211,214,215],"agent",{"commitSha":280,"license":281},{"repoId":940},"kd7etqyey7pjacrkp7wzfh4vts86nq1z",[937,211,215,212,214],{"evaluatedAt":943,"extractAt":944,"updatedAt":943},1778698529103,1778698371743,{"_creationTime":946,"_id":947,"community":948,"display":949,"identity":955,"providers":960,"relations":971,"tags":974,"workflow":975},1778696691708.3308,"k17d3c35ws96bb55ry97apwm5n86mqp2",{"reviewCount":8},{"description":950,"installMethods":951,"name":953,"sourceUrl":954},"Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval",{"claudeCode":952},"ruvnet/ruflo","Chat Format","https://github.com/ruvnet/ruflo",{"basePath":956,"githubOwner":957,"githubRepo":958,"locale":18,"slug":959,"type":246},"plugins/ruflo-ruvllm/skills/chat-format","ruvnet","ruflo","chat-format",{"evaluate":961,"extract":970},{"promptVersionExtension":204,"promptVersionScoring":205,"score":824,"tags":962,"targetMarket":216,"tier":217},[215,963,964,965,966,967,968,969],"prompting","rag","context-retrieval","openai","anthropic","gemini","ollama",{"commitSha":280,"license":281},{"parentExtensionId":972,"repoId":973},"k17ekc0sj70ms9kgkkgr2ypr4s86mz40","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[967,965,968,215,969,966,963,964],{"evaluatedAt":976,"extractAt":977,"updatedAt":976},1778701390930,1778696691708]