[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-rohitg00-thoroughness-scoring-en":3,"guides-for-rohitg00-thoroughness-scoring":821,"similar-k174rw8p1gfxs56b7dpp0sqfas86n35s-en":822},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":256,"isFallback":247,"parentExtension":262,"providers":320,"relations":324,"repo":325,"tags":819,"workflow":820},1778696595410.5684,"k174rw8p1gfxs56b7dpp0sqfas86n35s",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"rohitg00/pro-workflow","Pro Workflow","https://github.com/rohitg00/pro-workflow",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":237,"workflow":254},1778697053970.2969,"kn7cq5y0tbs8sp1ynjs84k0cth86meb1","en",{"checks":20,"evaluatedAt":189,"extensionSummary":190,"features":191,"nonGoals":198,"practices":202,"prerequisites":207,"promptVersionExtension":210,"promptVersionScoring":211,"purpose":212,"rationale":213,"score":214,"summary":215,"tags":216,"targetMarket":224,"tier":225,"useCases":226,"workflow":231},[21,26,29,32,36,39,43,46,50,54,58,61,64,67,71,75,78,81,84,88,92,95,99,102,105,108,111,114,117,121,124,128,132,136,139,143,146,150,153,156,159,162,165,168,172,175,179,182,186],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly articulates the problem of repetitive corrections and knowledge loss with AI agents, framing the solution as a way to improve AI reliability and knowledge persistence.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers a significant value proposition over basic prompting by introducing a persistent, searchable SQLite-backed store for corrections, wikis, and research, along with intelligent auto-research loops and multi-LLM deliberation.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a comprehensive suite of skills and agents for managing AI workflows, including persistent memory, knowledge bases, quality gates, and observational tools, covering a complete lifecycle for AI-assisted development.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension consolidates a coherent set of capabilities around enhancing AI agent workflow, memory, and knowledge management, with clear sub-skills and agents supporting this central theme.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the extension's core purpose of improving AI session reliability and knowledge persistence through structured storage and advanced features.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The SKILL.md and README clearly define the purpose of enhancing AI agent reliability and knowledge management, specifying artifacts like SQLite store, wikis, and research loops, and the user intent of reducing repetitive corrections and improving knowledge persistence.",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter in SKILL.md is concise and self-contained, effectively summarizing the core capability of a persistent knowledge and memory layer for AI agents.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The SKILL.md body is well-structured and delegates extensive material to separate files like README and documentation guides, maintaining conciseness.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","Extensive material is delegated to the README and separate documentation guides, adhering to progressive disclosure principles.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","The extension focuses on workflow management and knowledge persistence rather than deep exploration or code review that would necessitate `context: fork`.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","The README provides a '60-second tour' with clear, copy-pasteable command examples demonstrating core functionalities like wiki management and research.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The documentation, particularly the README and philosophy sections, implicitly handles edge cases by emphasizing robustness, verification, and persistent storage, with clear patterns for managing complex workflows.",{"category":40,"check":65,"severity":56,"summary":66},"Tool Fallback","The extension primarily relies on internal Claude Code tools and does not appear to have external MCP dependencies that would require fallback mechanisms.",{"category":68,"check":69,"severity":24,"summary":70},"Safety","Halt on unexpected state","The extension's design emphasizes robust state management and atomic operations (e.g., file-watcher, pre-compact scripts), implying a halt on unexpected states to maintain integrity.",{"category":72,"check":73,"severity":24,"summary":74},"Portability","Cross-skill coupling","The extension is designed as a cohesive suite of skills and agents that work together, with clear documentation on patterns and architecture, suggesting self-containment within its own ecosystem.",{"category":33,"check":76,"severity":24,"summary":77},"Scoped tools","The extension exposes well-defined skills and commands (e.g., `/wiki init`, `/develop`, `/commit`) that are specific to its domain of AI workflow enhancement.",{"category":33,"check":79,"severity":24,"summary":80},"Tool naming","Tool and command names are descriptive and follow a consistent kebab-case format (e.g., `thoroughness-scoring`, `/wiki init`).",{"category":33,"check":82,"severity":24,"summary":83},"Minimal I/O surface","Skills and commands appear to have well-defined inputs and outputs as demonstrated in the usage examples and command descriptions.",{"category":85,"check":86,"severity":24,"summary":87},"License","License usability","The MIT license is clearly declared via a badge in the README and is likely sourced from a LICENSE file or manifest.",{"category":89,"check":90,"severity":24,"summary":91},"Maintenance","Commit recency","The repository shows a recent commit on May 12, 2026, indicating active maintenance.",{"category":89,"check":93,"severity":24,"summary":94},"Dependency Management","The presence of `package.json` and `npm install` commands suggests standard Node.js dependency management, and `hasLockfile: true` indicates pinned dependencies.",{"category":96,"check":97,"severity":24,"summary":98},"Security","Secret Management","The README mentions LLM-powered secret hooks and implies robust guards, suggesting secrets are handled appropriately.",{"category":96,"check":100,"severity":24,"summary":101},"Injection","The extension's focus on structured data and workflows, along with documented CLI commands, suggests a low risk of executing untrusted code or data.",{"category":96,"check":103,"severity":24,"summary":104},"Transitive Supply-Chain Grenades","The installation instructions use standard package managers and Git cloning, without evidence of runtime script execution from untrusted remote sources.",{"category":96,"check":106,"severity":24,"summary":107},"Sandbox Isolation","The extension operates within the Claude Code environment and does not appear to manipulate files outside its designated project or data scopes.",{"category":96,"check":109,"severity":24,"summary":110},"Sandbox escape primitives","No evidence of detached-process spawns or deny-retry loops is present in the documentation or provided file structure.",{"category":96,"check":112,"severity":24,"summary":113},"Data Exfiltration","The extension focuses on local state and knowledge management, with no documented outbound calls for telemetry or data submission.",{"category":96,"check":115,"severity":24,"summary":116},"Hidden Text Tricks","The bundled content appears to be standard markdown and code, with no indication of hidden steering tricks or obfuscation.",{"category":118,"check":119,"severity":24,"summary":120},"Hooks","Opaque code execution","The extension's source code is described as TypeScript, implying readable and non-obfuscated code.",{"category":72,"check":122,"severity":24,"summary":123},"Structural Assumption","The extension's CLI commands and internal structure seem designed to be general and not rely on specific user project layouts outside of its own configuration directories.",{"category":125,"check":126,"severity":24,"summary":127},"Trust","Issues Attention","With 0 open issues and 5 closed issues in the last 90 days, the maintenance team is highly responsive.",{"category":129,"check":130,"severity":24,"summary":131},"Versioning","Release Management","The README includes an npm version badge, indicating proper versioning, and the recent commit history suggests active development.",{"category":133,"check":134,"severity":24,"summary":135},"Code Execution","Validation","The use of TypeScript and standard Node.js practices suggests input validation is likely implemented, though specific schema libraries aren't detailed.",{"category":96,"check":137,"severity":24,"summary":138},"Unguarded Destructive Operations","The extension's features like 'safe-mode' and 'permission-tuner' suggest that destructive operations are guarded or analyzed.",{"category":140,"check":141,"severity":24,"summary":142},"Errors","Error Handling","The extension's use of TypeScript and focus on robust workflow management implies a strong emphasis on error handling and meaningful reporting.",{"category":133,"check":144,"severity":24,"summary":145},"Logging","The presence of `tick.log` and the focus on audit trails (e.g., 'wrap-up' ritual) suggest that logging and auditing are considered.",{"category":147,"check":148,"severity":56,"summary":149},"Compliance","GDPR","The extension primarily manages local data and AI workflows, with no indication of handling personal data directly or submitting it to third parties.",{"category":147,"check":151,"severity":24,"summary":152},"Target market","The extension is designed for general AI development workflows and has no apparent regional limitations, making it globally applicable.",{"category":72,"check":154,"severity":24,"summary":155},"Runtime stability","Built with TypeScript and Node.js, the extension should be cross-platform compatible on systems with Node.js installed.",{"category":47,"check":157,"severity":24,"summary":158},"README","The README is comprehensive, well-organized, and clearly states the extension's purpose and capabilities.",{"category":33,"check":160,"severity":24,"summary":161},"Tool surface size","The extension exposes 34 skills, 8 agents, and 22 commands, which is within the recommended range for a feature-rich tool.",{"category":40,"check":163,"severity":24,"summary":164},"Overlapping near-synonym tools","The commands and skills appear to have distinct responsibilities, avoiding direct synonym overlap that would confuse the model.",{"category":47,"check":166,"severity":24,"summary":167},"Phantom features","All advertised features, such as the knowledge plane and self-correction memory, have corresponding implementations described in the documentation and structure.",{"category":169,"check":170,"severity":24,"summary":171},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for various environments (Claude Code, Cursor, SkillKit, manual) and includes command examples.",{"category":140,"check":173,"severity":24,"summary":174},"Actionable error messages","The extension's focus on developer productivity and robust error handling suggests that error messages are actionable and informative.",{"category":176,"check":177,"severity":24,"summary":178},"Execution","Pinned dependencies","The presence of `hasLockfile: true` indicates that dependencies are pinned, ensuring reproducible builds.",{"category":33,"check":180,"severity":56,"summary":181},"Dry-run preview","The extension's core functionality involves managing local data and AI workflows, without directly performing state-changing operations that would typically require a dry-run mode.",{"category":183,"check":184,"severity":24,"summary":185},"Protocol","Idempotent retry & timeouts","The focus on robust state management and local operations suggests that retries are likely handled appropriately where mutations occur, and timeouts are implicitly managed by the Claude Code environment.",{"category":147,"check":187,"severity":24,"summary":188},"Telemetry opt-in","The documentation emphasizes local storage and user control, with no mention of telemetry, suggesting it is either absent or strictly opt-in.",1778697053863,"This extension enhances AI agent capabilities by providing a persistent, SQLite-backed store for self-correction memory, research wikis, and advanced workflow management tools. It includes features for quality gates, cost tracking, and multi-LLM deliberation.",[192,193,194,195,196,197],"Persistent self-correction memory via SQLite","FTS5-indexed research wikis with auto-research loops","Budget-capped AI research capabilities","Multi-LLM deliberation and planning","Quality gates for commits and destructive operations","Session analytics and cost tracking",[199,200,201],"Replacing the core AI agent's reasoning capabilities","Directly managing cloud infrastructure deployments","Providing generic task management outside of AI workflow enhancement",[203,204,205,206],"AI Workflow Enhancement","Knowledge Management","Developer Productivity","Code Quality",[208,209],"Node.js runtime","Claude Code or compatible agent environment","3.0.0","4.4.0","To significantly improve AI agent reliability and knowledge persistence by allowing users to capture corrections, build research wikis, and manage complex workflows effectively.","The extension is exceptionally well-documented, feature-rich, and actively maintained, with a clear focus on practical utility and robust design, indicated by numerous 'pass' findings across all categories.",96,"A comprehensive and robust suite for enhancing AI agent workflows with persistent memory, knowledge management, and quality gates.",[217,218,219,220,221,222,223],"ai-workflow","memory","knowledge-management","sqlite","research","automation","developer-tools","global","verified",[227,228,229,230],"Reducing repetitive AI corrections by storing learnings persistently","Building and querying personal or project-specific knowledge bases","Automating research and literature review on specific topics","Managing complex AI-assisted development workflows with validation gates",[232,233,234,235,236],"Install the extension and its dependencies.","Configure settings and API keys as needed.","Utilize commands like `/wiki` to manage knowledge bases.","Leverage skills for developing features, committing code, and analyzing sessions.","Benefit from persistent memory and automated research loops.",{"codeQuality":238,"collectedAt":240,"documentation":241,"maintenance":244,"popularity":250,"security":252,"testCoverage":253},{"hasLockfile":239},true,1778697038102,{"descriptionLength":242,"readmeSize":243},232,22012,{"closedIssues90d":245,"forks":246,"hasChangelog":247,"openIssues90d":8,"pushedAt":248,"stars":249},5,203,false,1778554780000,2113,{"npmDownloads":251},611,{"hasNpmPackage":239,"smitheryVerified":247},{"hasCi":239,"hasTests":247},{"updatedAt":255},1778697053970,{"basePath":257,"githubOwner":258,"githubRepo":259,"locale":18,"slug":260,"type":261},"skills/thoroughness-scoring","rohitg00","pro-workflow","thoroughness-scoring","skill",{"_creationTime":263,"_id":264,"community":265,"display":266,"identity":271,"parentExtension":274,"providers":304,"relations":316,"tags":317,"workflow":318},1778696595410.5615,"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv",{"reviewCount":8},{"description":267,"installMethods":268,"name":13,"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":259,"cursor":269,"npm":259,"skillkit":270},"/add-plugin pro-workflow","npx skillkit install pro-workflow",{"basePath":272,"githubOwner":258,"githubRepo":259,"locale":18,"slug":259,"type":273},"","plugin",{"_creationTime":275,"_id":276,"community":277,"display":278,"identity":281,"providers":283,"relations":298,"tags":300,"workflow":301},1778696595410.5613,"k1741gyqaf0tj1ffq65gjpsm6x86mfhx",{"reviewCount":8},{"description":279,"installMethods":280,"name":13,"sourceUrl":14},"Battle-tested Claude Code workflows from power users",{"claudeCode":12},{"basePath":272,"githubOwner":258,"githubRepo":259,"locale":18,"slug":259,"type":282},"marketplace",{"evaluate":284,"extract":291},{"promptVersionExtension":285,"promptVersionScoring":211,"score":286,"tags":287,"targetMarket":224,"tier":225},"3.1.0",99,[288,289,290,223,219],"workflow","productivity","ai-assistance",{"commitSha":292,"license":293,"marketplace":294,"plugin":296},"HEAD","MIT",{"name":259,"pluginCount":295},1,{"mcpCount":8,"provider":297,"skillCount":8},"classify",{"repoId":299},"kd7am4e918eq98hrd9s31jm4vs86nn0b",[290,223,219,289,288],{"evaluatedAt":302,"extractAt":303,"updatedAt":302},1778696611346,1778696595410,{"evaluate":305,"extract":313},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":306,"targetMarket":224,"tier":312},[288,289,307,308,309,220,310,311],"ai-coding","self-correction","knowledge-base","hooks","agents","community",{"commitSha":292,"license":293,"plugin":314},{"mcpCount":8,"provider":297,"skillCount":315},34,{"parentExtensionId":276,"repoId":299},[311,307,310,309,289,308,220,288],{"evaluatedAt":319,"extractAt":303,"updatedAt":319},1778696621396,{"evaluate":321,"extract":323},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":322,"targetMarket":224,"tier":225},[217,218,219,220,221,222,223],{"commitSha":292,"license":293},{"parentExtensionId":264,"repoId":299},{"_creationTime":326,"_id":299,"identity":327,"providers":328,"workflow":814},1778696588306.821,{"githubOwner":258,"githubRepo":259,"sourceUrl":14},{"classify":329,"discover":794,"extract":797,"github":798,"npm":813},{"commitSha":292,"extensions":330},[331,341,482,491,499,507,515,523,531,539,547,555,563,571,579,590,598,606,614,622,630,638,646,653,661,669,677,685,693,705,710,718,750,760,776,786],{"basePath":272,"description":279,"displayName":259,"installMethods":332,"rationale":333,"selectedPaths":334,"source":340,"sourceLanguage":18,"type":282},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[335,338],{"path":336,"priority":337},".claude-plugin/marketplace.json","mandatory",{"path":339,"priority":337},"README.md","rule",{"basePath":272,"description":267,"displayName":259,"installMethods":342,"license":293,"rationale":343,"selectedPaths":344,"source":340,"sourceLanguage":18,"type":273},{"claudeCode":259},"plugin manifest at .claude-plugin/plugin.json",[345,347,348,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,409,411,413,415,417,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480],{"path":346,"priority":337},".claude-plugin/plugin.json",{"path":339,"priority":337},{"path":349,"priority":350},"skills/agent-teams/SKILL.md","medium",{"path":352,"priority":350},"skills/auto-setup/SKILL.md",{"path":354,"priority":350},"skills/batch-orchestration/SKILL.md",{"path":356,"priority":350},"skills/bug-capture/SKILL.md",{"path":358,"priority":350},"skills/compact-guard/SKILL.md",{"path":360,"priority":350},"skills/context-engineering/SKILL.md",{"path":362,"priority":350},"skills/context-optimizer/SKILL.md",{"path":364,"priority":350},"skills/cost-tracker/SKILL.md",{"path":366,"priority":350},"skills/deslop/SKILL.md",{"path":368,"priority":350},"skills/file-watcher/SKILL.md",{"path":370,"priority":350},"skills/insights/SKILL.md",{"path":372,"priority":350},"skills/learn-rule/SKILL.md",{"path":374,"priority":350},"skills/llm-council/SKILL.md",{"path":376,"priority":350},"skills/llm-gate/SKILL.md",{"path":378,"priority":350},"skills/mcp-audit/SKILL.md",{"path":380,"priority":350},"skills/module-map/SKILL.md",{"path":382,"priority":350},"skills/orchestrate/SKILL.md",{"path":384,"priority":350},"skills/parallel-worktrees/SKILL.md",{"path":386,"priority":350},"skills/permission-tuner/SKILL.md",{"path":388,"priority":350},"skills/plan-interrogate/SKILL.md",{"path":390,"priority":350},"skills/pro-workflow/SKILL.md",{"path":392,"priority":350},"skills/replay-learnings/SKILL.md",{"path":394,"priority":350},"skills/safe-mode/SKILL.md",{"path":396,"priority":350},"skills/session-handoff/SKILL.md",{"path":398,"priority":350},"skills/smart-commit/SKILL.md",{"path":400,"priority":350},"skills/sprint-status/SKILL.md",{"path":402,"priority":350},"skills/survey-generator/SKILL.md",{"path":404,"priority":350},"skills/thoroughness-scoring/SKILL.md",{"path":406,"priority":350},"skills/token-efficiency/SKILL.md",{"path":408,"priority":350},"skills/wiki-builder/SKILL.md",{"path":410,"priority":350},"skills/wiki-query/SKILL.md",{"path":412,"priority":350},"skills/wiki-research-loop/SKILL.md",{"path":414,"priority":350},"skills/wiki-viewer/SKILL.md",{"path":416,"priority":350},"skills/wrap-up/SKILL.md",{"path":418,"priority":419},"agents/context-engineer.md","high",{"path":421,"priority":419},"agents/cost-analyst.md",{"path":423,"priority":419},"agents/debugger.md",{"path":425,"priority":419},"agents/orchestrator.md",{"path":427,"priority":419},"agents/permission-analyst.md",{"path":429,"priority":419},"agents/planner.md",{"path":431,"priority":419},"agents/reviewer.md",{"path":433,"priority":419},"agents/scout.md",{"path":435,"priority":419},"commands/auto-setup.md",{"path":437,"priority":419},"commands/commit.md",{"path":439,"priority":419},"commands/compact-guard.md",{"path":441,"priority":419},"commands/context-optimizer.md",{"path":443,"priority":419},"commands/cost-tracker.md",{"path":445,"priority":419},"commands/deslop.md",{"path":447,"priority":419},"commands/develop.md",{"path":449,"priority":419},"commands/doctor.md",{"path":451,"priority":419},"commands/handoff.md",{"path":453,"priority":419},"commands/insights.md",{"path":455,"priority":419},"commands/learn-rule.md",{"path":457,"priority":419},"commands/learn.md",{"path":459,"priority":419},"commands/list.md",{"path":461,"priority":419},"commands/mcp-audit.md",{"path":463,"priority":419},"commands/parallel.md",{"path":465,"priority":419},"commands/permission-tuner.md",{"path":467,"priority":419},"commands/replay.md",{"path":469,"priority":419},"commands/safe-mode.md",{"path":471,"priority":419},"commands/search.md",{"path":473,"priority":419},"commands/sprint-status.md",{"path":475,"priority":419},"commands/wiki.md",{"path":477,"priority":419},"commands/wrap-up.md",{"path":479,"priority":419},"hooks/hooks.json",{"path":481,"priority":419},".cursor-plugin/plugin.json",{"basePath":483,"description":484,"displayName":485,"installMethods":486,"rationale":487,"selectedPaths":488,"source":340,"sourceLanguage":18,"type":261},"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",[489],{"path":490,"priority":337},"SKILL.md",{"basePath":492,"description":493,"displayName":494,"installMethods":495,"rationale":496,"selectedPaths":497,"source":340,"sourceLanguage":18,"type":261},"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",[498],{"path":490,"priority":337},{"basePath":500,"description":501,"displayName":502,"installMethods":503,"rationale":504,"selectedPaths":505,"source":340,"sourceLanguage":18,"type":261},"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",[506],{"path":490,"priority":337},{"basePath":508,"description":509,"displayName":510,"installMethods":511,"rationale":512,"selectedPaths":513,"source":340,"sourceLanguage":18,"type":261},"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",[514],{"path":490,"priority":337},{"basePath":516,"description":517,"displayName":518,"installMethods":519,"rationale":520,"selectedPaths":521,"source":340,"sourceLanguage":18,"type":261},"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",[522],{"path":490,"priority":337},{"basePath":524,"description":525,"displayName":526,"installMethods":527,"rationale":528,"selectedPaths":529,"source":340,"sourceLanguage":18,"type":261},"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",[530],{"path":490,"priority":337},{"basePath":532,"description":533,"displayName":534,"installMethods":535,"rationale":536,"selectedPaths":537,"source":340,"sourceLanguage":18,"type":261},"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",[538],{"path":490,"priority":337},{"basePath":540,"description":541,"displayName":542,"installMethods":543,"rationale":544,"selectedPaths":545,"source":340,"sourceLanguage":18,"type":261},"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",[546],{"path":490,"priority":337},{"basePath":548,"description":549,"displayName":550,"installMethods":551,"rationale":552,"selectedPaths":553,"source":340,"sourceLanguage":18,"type":261},"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",[554],{"path":490,"priority":337},{"basePath":556,"description":557,"displayName":558,"installMethods":559,"rationale":560,"selectedPaths":561,"source":340,"sourceLanguage":18,"type":261},"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",[562],{"path":490,"priority":337},{"basePath":564,"description":565,"displayName":566,"installMethods":567,"rationale":568,"selectedPaths":569,"source":340,"sourceLanguage":18,"type":261},"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",[570],{"path":490,"priority":337},{"basePath":572,"description":573,"displayName":574,"installMethods":575,"rationale":576,"selectedPaths":577,"source":340,"sourceLanguage":18,"type":261},"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",[578],{"path":490,"priority":337},{"basePath":580,"description":581,"displayName":582,"installMethods":583,"rationale":584,"selectedPaths":585,"source":340,"sourceLanguage":18,"type":261},"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",[586,587],{"path":490,"priority":337},{"path":588,"priority":589},"scripts/council.js","low",{"basePath":591,"description":592,"displayName":593,"installMethods":594,"rationale":595,"selectedPaths":596,"source":340,"sourceLanguage":18,"type":261},"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",[597],{"path":490,"priority":337},{"basePath":599,"description":600,"displayName":601,"installMethods":602,"rationale":603,"selectedPaths":604,"source":340,"sourceLanguage":18,"type":261},"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",[605],{"path":490,"priority":337},{"basePath":607,"description":608,"displayName":609,"installMethods":610,"rationale":611,"selectedPaths":612,"source":340,"sourceLanguage":18,"type":261},"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",[613],{"path":490,"priority":337},{"basePath":615,"description":616,"displayName":617,"installMethods":618,"rationale":619,"selectedPaths":620,"source":340,"sourceLanguage":18,"type":261},"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",[621],{"path":490,"priority":337},{"basePath":623,"description":624,"displayName":625,"installMethods":626,"rationale":627,"selectedPaths":628,"source":340,"sourceLanguage":18,"type":261},"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",[629],{"path":490,"priority":337},{"basePath":631,"description":632,"displayName":633,"installMethods":634,"rationale":635,"selectedPaths":636,"source":340,"sourceLanguage":18,"type":261},"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",[637],{"path":490,"priority":337},{"basePath":639,"description":640,"displayName":641,"installMethods":642,"rationale":643,"selectedPaths":644,"source":340,"sourceLanguage":18,"type":261},"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",[645],{"path":490,"priority":337},{"basePath":647,"description":648,"displayName":259,"installMethods":649,"rationale":650,"selectedPaths":651,"source":340,"sourceLanguage":18,"type":261},"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",[652],{"path":490,"priority":337},{"basePath":654,"description":655,"displayName":656,"installMethods":657,"rationale":658,"selectedPaths":659,"source":340,"sourceLanguage":18,"type":261},"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",[660],{"path":490,"priority":337},{"basePath":662,"description":663,"displayName":664,"installMethods":665,"rationale":666,"selectedPaths":667,"source":340,"sourceLanguage":18,"type":261},"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",[668],{"path":490,"priority":337},{"basePath":670,"description":671,"displayName":672,"installMethods":673,"rationale":674,"selectedPaths":675,"source":340,"sourceLanguage":18,"type":261},"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",[676],{"path":490,"priority":337},{"basePath":678,"description":679,"displayName":680,"installMethods":681,"rationale":682,"selectedPaths":683,"source":340,"sourceLanguage":18,"type":261},"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",[684],{"path":490,"priority":337},{"basePath":686,"description":687,"displayName":688,"installMethods":689,"rationale":690,"selectedPaths":691,"source":340,"sourceLanguage":18,"type":261},"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",[692],{"path":490,"priority":337},{"basePath":694,"description":695,"displayName":696,"installMethods":697,"rationale":698,"selectedPaths":699,"source":340,"sourceLanguage":18,"type":261},"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",[700,701,703],{"path":490,"priority":337},{"path":702,"priority":589},"scripts/build-survey.js",{"path":704,"priority":589},"templates/research_bundle.template.json",{"basePath":257,"description":10,"displayName":260,"installMethods":706,"rationale":707,"selectedPaths":708,"source":340,"sourceLanguage":18,"type":261},{"claudeCode":12},"SKILL.md frontmatter at skills/thoroughness-scoring/SKILL.md",[709],{"path":490,"priority":337},{"basePath":711,"description":712,"displayName":713,"installMethods":714,"rationale":715,"selectedPaths":716,"source":340,"sourceLanguage":18,"type":261},"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",[717],{"path":490,"priority":337},{"basePath":719,"description":720,"displayName":721,"installMethods":722,"rationale":723,"selectedPaths":724,"source":340,"sourceLanguage":18,"type":261},"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",[725,726,728,730,732,734,736,738,740,742,744,746,748],{"path":490,"priority":337},{"path":727,"priority":350},"references/wiki-flavors.md",{"path":729,"priority":589},"scripts/init_wiki.sh",{"path":731,"priority":589},"scripts/wiki-cli.js",{"path":733,"priority":589},"templates/index.md",{"path":735,"priority":589},"templates/maintenance-log.md",{"path":737,"priority":589},"templates/prompts/compile-concept-page.md",{"path":739,"priority":589},"templates/prompts/compile-index.md",{"path":741,"priority":589},"templates/prompts/compile-source-page.md",{"path":743,"priority":589},"templates/prompts/lint-wiki.md",{"path":745,"priority":589},"templates/prompts/query-and-file.md",{"path":747,"priority":589},"templates/sources.md",{"path":749,"priority":589},"templates/wiki.config.md",{"basePath":751,"description":752,"displayName":753,"installMethods":754,"rationale":755,"selectedPaths":756,"source":340,"sourceLanguage":18,"type":261},"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",[757,758],{"path":490,"priority":337},{"path":759,"priority":589},"scripts/query.js",{"basePath":761,"description":762,"displayName":763,"installMethods":764,"rationale":765,"selectedPaths":766,"source":340,"sourceLanguage":18,"type":261},"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",[767,768,770,772,774],{"path":490,"priority":337},{"path":769,"priority":589},"scripts/research-loop.js",{"path":771,"priority":589},"scripts/source-fetchers/arxiv.js",{"path":773,"priority":589},"scripts/source-fetchers/github.js",{"path":775,"priority":589},"scripts/source-fetchers/web.js",{"basePath":777,"description":778,"displayName":779,"installMethods":780,"rationale":781,"selectedPaths":782,"source":340,"sourceLanguage":18,"type":261},"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",[783,784],{"path":490,"priority":337},{"path":785,"priority":589},"scripts/render.js",{"basePath":787,"description":788,"displayName":789,"installMethods":790,"rationale":791,"selectedPaths":792,"source":340,"sourceLanguage":18,"type":261},"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",[793],{"path":490,"priority":337},{"sources":795},[796],"manual",{"npmPackage":259},{"closedIssues90d":245,"description":799,"forks":246,"homepage":800,"openIssues90d":8,"pushedAt":248,"readmeSize":243,"stars":249,"topics":801},"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",[802,803,804,288,805,806,307,217,807,808,809,810,526,223,811,310,289,308,812],"claude","claude-code","cursor","agent-orchestration","ai-agents","claude-code-plugin","claude-code-skills","claude-skills","codex","gemini-cli","worktrees",{"downloads":251},{"classifiedAt":815,"discoverAt":816,"extractAt":817,"githubAt":817,"npmAt":818,"updatedAt":815},1778696594915,1778696588306,1778696590961,1778696593284,[217,222,223,219,218,221,220],{"evaluatedAt":255,"extractAt":303,"updatedAt":255},[],[823,841,870,896,917,945],{"_creationTime":824,"_id":825,"community":826,"display":827,"identity":829,"providers":830,"relations":837,"tags":838,"workflow":839},1778696595410.5618,"k174h4yhwrcpcmdx62n2g2b88986mx17",{"reviewCount":8},{"description":484,"installMethods":828,"name":485,"sourceUrl":14},{"claudeCode":12},{"basePath":483,"githubOwner":258,"githubRepo":259,"locale":18,"slug":485,"type":261},{"evaluate":831,"extract":836},{"promptVersionExtension":210,"promptVersionScoring":211,"score":832,"tags":833,"targetMarket":224,"tier":225},100,[217,834,219,835,289,308],"collaboration","llm-ops",{"commitSha":292},{"parentExtensionId":264,"repoId":299},[217,834,219,835,289,308],{"evaluatedAt":840,"extractAt":303,"updatedAt":840},1778696637446,{"_creationTime":842,"_id":843,"community":844,"display":845,"identity":851,"providers":856,"relations":863,"tags":865,"workflow":866},1778699106670.4268,"k179cgk616p3xva37r5jqsfwvh86mcp2",{"reviewCount":8},{"description":846,"installMethods":847,"name":849,"sourceUrl":850},"Use when work depends on the user's live browser session or visible rendered state rather than static fetches, especially for browser debugging contexts or DevTools-selected elements or requests, logged-in dashboards or CMS flows, localhost apps, forms, uploads, downloads, media inspection, DOM or iframe inspection, Shadow DOM, or browser failures that look like soft 404s, auth walls, anti-bot checks, or rate limits.",{"claudeCode":848},"xixu-me/skills","Use My Browser","https://github.com/xixu-me/skills",{"basePath":852,"githubOwner":853,"githubRepo":854,"locale":18,"slug":855,"type":261},"skills/use-my-browser","xixu-me","skills","use-my-browser",{"evaluate":857,"extract":862},{"promptVersionExtension":210,"promptVersionScoring":211,"score":832,"tags":858,"targetMarket":224,"tier":225},[859,860,222,861,223],"browser","debugging","ux",{"commitSha":292,"license":293},{"repoId":864},"kd77r2vb42jmgam0qbr9f2c6kn86mebv",[222,859,860,223,861],{"evaluatedAt":867,"extractAt":868,"updatedAt":869},1778699261239,1778699106670,1778699384978,{"_creationTime":871,"_id":872,"community":873,"display":874,"identity":880,"providers":884,"relations":890,"tags":892,"workflow":893},1778697652123.8928,"k171pew5empzzrfghyg9nqrk6n86nqa9",{"reviewCount":8},{"description":875,"installMethods":876,"name":878,"sourceUrl":879},"Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.",{"claudeCode":877},"steipete/clawdis","github","https://github.com/steipete/clawdis",{"basePath":881,"githubOwner":882,"githubRepo":883,"locale":18,"slug":878,"type":261},"skills/github","steipete","clawdis",{"evaluate":885,"extract":889},{"promptVersionExtension":210,"promptVersionScoring":211,"score":832,"tags":886,"targetMarket":224,"tier":225},[878,887,888,223,222],"cli","api",{"commitSha":292},{"repoId":891},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[888,222,887,223,878],{"evaluatedAt":894,"extractAt":895,"updatedAt":894},1778698569289,1778697652123,{"_creationTime":897,"_id":898,"community":899,"display":900,"identity":904,"providers":906,"relations":913,"tags":914,"workflow":915},1778697652123.8845,"k17bexjjjsz81ysk7bd3ggdm8s86mt2t",{"reviewCount":8},{"description":901,"installMethods":902,"name":903,"sourceUrl":879},"Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.",{"claudeCode":877},"openclaw-testing",{"basePath":905,"githubOwner":882,"githubRepo":883,"locale":18,"slug":903,"type":261},".agents/skills/openclaw-testing",{"evaluate":907,"extract":912},{"promptVersionExtension":210,"promptVersionScoring":211,"score":832,"tags":908,"targetMarket":224,"tier":225},[909,910,911,222,223],"testing","ci","validation",{"commitSha":292},{"repoId":891},[222,910,223,909,911],{"evaluatedAt":916,"extractAt":895,"updatedAt":916},1778697962962,{"_creationTime":918,"_id":919,"community":920,"display":921,"identity":927,"providers":931,"relations":938,"tags":941,"workflow":942},1778696833339.6243,"k174g80xa9zxhydbncvpf0xzy986nvx5",{"reviewCount":8},{"description":922,"installMethods":923,"name":925,"sourceUrl":926},"Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.",{"claudeCode":924},"sanjay3290/ai-skills","manus","https://github.com/sanjay3290/ai-skills",{"basePath":928,"githubOwner":929,"githubRepo":930,"locale":18,"slug":925,"type":261},"skills/manus","sanjay3290","ai-skills",{"evaluate":932,"extract":937},{"promptVersionExtension":210,"promptVersionScoring":211,"score":832,"tags":933,"targetMarket":224,"tier":225},[934,935,221,222,936],"ai-agent","autonomous-execution","api-integration",{"commitSha":292},{"parentExtensionId":939,"repoId":940},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[934,936,222,935,221],{"evaluatedAt":943,"extractAt":944,"updatedAt":943},1778697107270,1778696833339,{"_creationTime":946,"_id":947,"community":948,"display":949,"identity":955,"providers":960,"relations":967,"tags":970,"workflow":971},1778695116697.199,"k17cex5hqwje7qgvts5evct1d186nd4m",{"reviewCount":8},{"description":950,"installMethods":951,"name":953,"sourceUrl":954},"Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.",{"claudeCode":952},"Orchestra-Research/AI-Research-SKILLs","ARA Research Manager","https://github.com/Orchestra-Research/AI-Research-SKILLs",{"basePath":956,"githubOwner":957,"githubRepo":958,"locale":18,"slug":959,"type":261},"22-agent-native-research-artifact/research-manager","Orchestra-Research","AI-Research-SKILLs","research-manager",{"evaluate":961,"extract":966},{"promptVersionExtension":210,"promptVersionScoring":211,"score":832,"tags":962,"targetMarket":224,"tier":225},[221,963,219,964,965],"provenance","session-logging","ara",{"commitSha":292,"license":293},{"parentExtensionId":968,"repoId":969},"k17155ws9qc0hw7a568bg79sfd86max8","kd70hj1y80mhra5xm5g188j5n586mg18",[965,219,963,221,964],{"evaluatedAt":972,"extractAt":973,"updatedAt":972},1778697541177,1778695116697]