[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-rohitg00-context-optimizer-en":3,"guides-for-rohitg00-context-optimizer":810,"similar-k176qp395ndj2ctj6qqf9q028s86ndey-en":811},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":241,"isFallback":232,"parentExtension":246,"providers":309,"relations":313,"repo":314,"tags":808,"workflow":809},1778696595410.5632,"k176qp395ndj2ctj6qqf9q028s86ndey",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.",{"claudeCode":12},"rohitg00/pro-workflow","context-optimizer","https://github.com/rohitg00/pro-workflow",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":222,"workflow":239},1778696732992.839,"kn79n75r0hphqmj89ffcffmcts86mje7","en",{"checks":20,"evaluatedAt":190,"extensionSummary":191,"features":192,"nonGoals":198,"promptVersionExtension":203,"promptVersionScoring":204,"purpose":205,"rationale":206,"score":207,"summary":208,"tags":209,"targetMarket":215,"tier":216,"useCases":217},[21,26,29,33,37,41,45,48,52,56,59,62,65,69,72,75,79,82,85,89,93,96,100,103,106,109,112,115,118,122,126,130,134,138,141,144,147,151,154,157,160,163,166,169,173,177,180,183,187],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","The description clearly states the artifact (token usage, context management) and the user intent (optimize, manage) with specific triggers (slow sessions, degraded context, budget) and implicit boundaries (when sessions are fast and context is good).",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","The SKILL.md frontmatter is concise, self-contained, and provides a clear summary of the core capability and trigger phrases within the character limit.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","The SKILL.md body is well under the line limit and effectively uses progressive disclosure by deferring detailed procedures and configuration to tables and code blocks within the main file, rather than relying on external files for core functionality.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","The SKILL.md effectively uses tables and code blocks for procedures and configurations, keeping the main instruction concise while providing necessary detail inline.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","This skill is focused on direct command execution and optimization strategies rather than deep exploration or code review, so forked context is not applicable.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","The SKILL.md provides clear, ready-to-use examples for core functionalities like setting auto-compaction and general usage, demonstrating expected outcomes.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","The SKILL.md addresses edge cases and limitations, such as degraded context, and suggests recovery steps like manual compaction or starting a fresh session.",{"category":49,"check":50,"severity":39,"summary":51},"Code Execution","Tool Fallback","This skill does not appear to rely on external MCP servers or tools that would require a fallback mechanism.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","The SKILL.md implicitly handles unexpected state by suggesting actions like a fresh session when context is degraded, effectively halting problematic workflows.",{"category":42,"check":57,"severity":24,"summary":58},"Problem relevance","The description clearly names the problem of token usage and context management, relevant to users experiencing slow sessions, degraded context, or budget concerns.",{"category":42,"check":60,"severity":24,"summary":61},"Unique selling proposition","The skill offers distinct value over simple prompting by providing structured strategies for context optimization, MCP auditing, and token efficiency, going beyond default LLM behavior.",{"category":42,"check":63,"severity":24,"summary":64},"Production readiness","The skill provides actionable strategies and configuration examples, making it suitable for immediate use in real workflows to manage token usage and context.",{"category":66,"check":67,"severity":24,"summary":68},"Scope","Single responsibility principle","The skill focuses solely on token usage and context management, with no indication of extending into unrelated domains.",{"category":66,"check":70,"severity":24,"summary":71},"Description quality","The displayed description accurately reflects the skill's purpose of optimizing token usage and context management and provides relevant use cases.",{"category":22,"check":73,"severity":39,"summary":74},"Scoped tools","This skill does not expose tools directly; it provides instructions and configuration for managing context, making the 'scoped tools' check not applicable.",{"category":30,"check":76,"severity":77,"summary":78},"Configuration & parameter reference","info","While configuration via environment variables is mentioned, specific parameters and their default values are not exhaustively documented.",{"category":66,"check":80,"severity":39,"summary":81},"Tool naming","This skill does not expose user-facing tools or commands directly, so this check is not applicable.",{"category":66,"check":83,"severity":39,"summary":84},"Minimal I/O surface","The skill provides instructions and configuration, not tools with input/output schemas, making this check not applicable.",{"category":86,"check":87,"severity":24,"summary":88},"License","License usability","The license is MIT, clearly indicated by a badge in the README and implied by the permissive nature of the project's OSS focus.",{"category":90,"check":91,"severity":24,"summary":92},"Maintenance","Commit recency","The repository shows recent commits within the last 90 days, indicating active maintenance.",{"category":90,"check":94,"severity":24,"summary":95},"Dependency Management","The project includes a lockfile (`package-lock.json` or similar implied by `npm install`) and CI, suggesting dependency management practices are in place.",{"category":97,"check":98,"severity":39,"summary":99},"Security","Secret Management","The skill focuses on context management and does not appear to handle or expose secrets.",{"category":97,"check":101,"severity":39,"summary":102},"Injection","The skill does not load or include external data or files that could be subject to injection attacks.",{"category":97,"check":104,"severity":39,"summary":105},"Transitive Supply-Chain Grenades","The skill does not fetch remote content at runtime or include untrusted third-party data.",{"category":97,"check":107,"severity":39,"summary":108},"Sandbox Isolation","This skill provides instructions and configuration, not executable code that would require sandbox isolation checks.",{"category":97,"check":110,"severity":39,"summary":111},"Sandbox escape primitives","No scripts or executable code are present that could contain sandbox escape primitives.",{"category":97,"check":113,"severity":39,"summary":114},"Data Exfiltration","The skill does not handle or submit confidential data; its focus is on managing the LLM's context.",{"category":97,"check":116,"severity":24,"summary":117},"Hidden Text Tricks","The bundled content, including the SKILL.md and README.md, appears free of hidden-steering tricks and uses standard character sets.",{"category":119,"check":120,"severity":39,"summary":121},"Hooks","Opaque code execution","The skill does not contain any opaque code execution mechanisms like base64 payloads or minified scripts.",{"category":123,"check":124,"severity":24,"summary":125},"Portability","Structural Assumption","The skill provides configuration examples that use standard environment variables and paths, avoiding assumptions about specific user project structures.",{"category":127,"check":128,"severity":24,"summary":129},"Trust","Issues Attention","There are 0 open issues and 5 closed issues in the last 90 days, indicating a healthy ratio of closed to open issues and active maintenance.",{"category":131,"check":132,"severity":24,"summary":133},"Versioning","Release Management","The project has a meaningful npm version declared in the README and suggests use of specific versions via install commands.",{"category":135,"check":136,"severity":39,"summary":137},"Execution","Validation","This skill does not expose tools with complex input schemas or structured output requiring validation libraries.",{"category":97,"check":139,"severity":39,"summary":140},"Unguarded Destructive Operations","The skill does not perform any destructive operations on the file system or external services.",{"category":49,"check":142,"severity":39,"summary":143},"Error Handling","The skill provides instructions rather than executable code, so standard error handling checks are not applicable.",{"category":49,"check":145,"severity":39,"summary":146},"Logging","As this skill does not perform destructive actions or outbound calls, local audit logging is not applicable.",{"category":148,"check":149,"severity":39,"summary":150},"Compliance","GDPR","The skill does not operate on personal data; it focuses on managing LLM context and token usage.",{"category":148,"check":152,"severity":24,"summary":153},"Target market","The skill's functionality is language-agnostic and does not depend on specific regional regulations or data formats, making its target market global.",{"category":123,"check":155,"severity":24,"summary":156},"Runtime stability","The skill's instructions and configuration are based on standard environment variables and JSON, ensuring portability across different runtime environments.",{"category":30,"check":158,"severity":24,"summary":159},"README","The README file exists and clearly states the extension's purpose, providing comprehensive information about its features and usage.",{"category":66,"check":161,"severity":39,"summary":162},"Tool surface size","This skill does not expose multiple tools or commands; it is a single-purpose skill, making this check not applicable.",{"category":22,"check":164,"severity":39,"summary":165},"Overlapping near-synonym tools","This skill does not expose multiple tools, therefore there are no overlapping near-synonym tools to evaluate.",{"category":30,"check":167,"severity":24,"summary":168},"Phantom features","All features mentioned in the README and SKILL.md, such as context optimization strategies and configuration, have corresponding implementations or clear instructions.",{"category":170,"check":171,"severity":24,"summary":172},"Install","Installation instruction","The README provides clear installation instructions for multiple methods (marketplace, Cursor, SkillKit, manual) and includes copy-pasteable commands.",{"category":174,"check":175,"severity":39,"summary":176},"Errors","Actionable error messages","The skill provides instructional guidance rather than executable code with user-facing error paths.",{"category":135,"check":178,"severity":24,"summary":179},"Pinned dependencies","The project's `package.json` and lockfile indicate pinned dependencies and interpreter declarations (e.g., shebangs for scripts).",{"category":66,"check":181,"severity":39,"summary":182},"Dry-run preview","The skill does not perform state-changing operations or outbound calls that would require a dry-run mode.",{"category":184,"check":185,"severity":39,"summary":186},"Protocol","Idempotent retry & timeouts","This skill does not involve remote calls or state-changing operations that require idempotency or timeouts.",{"category":148,"check":188,"severity":24,"summary":189},"Telemetry opt-in","The project's structure and README do not indicate any telemetry collection, implying no opt-out telemetry and thus satisfying the opt-in requirement by default.",1778696732891,"This skill provides strategies and configuration for optimizing token usage and managing context window limitations within an LLM environment. It offers guidance on immediate actions, configuration settings, prompt engineering, and subagent delegation to maintain performance and control costs.",[193,194,195,196,197],"Token usage optimization","Context window management","Performance degradation mitigation","Budget control strategies","Configuration for auto-compaction",[199,200,201,202],"Replacing core LLM functionality","Managing specific project code logic","Directly interacting with external services","Providing general AI assistance unrelated to context management","3.0.0","4.4.0","Optimize token usage and context management to prevent sessions from feeling slow, context from degrading, or budget from being exceeded.","The skill is highly polished with excellent documentation, clear purpose, and strong production readiness. The primary finding is minor documentation incompleteness regarding environment variable parameters.",97,"A high-quality skill for optimizing token usage and context management with clear documentation and actionable strategies.",[210,211,212,213,214],"context-management","token-optimization","llm","claude-code","workflow-optimization","global","verified",[218,219,220,221],"When LLM sessions feel slow or unresponsive","When context window is degraded or losing information","When running out of budget or concerned about token costs","To proactively manage context before performance issues arise",{"codeQuality":223,"collectedAt":225,"documentation":226,"maintenance":229,"popularity":235,"security":237,"testCoverage":238},{"hasLockfile":224},true,1778696717915,{"descriptionLength":227,"readmeSize":228},127,22012,{"closedIssues90d":230,"forks":231,"hasChangelog":232,"openIssues90d":8,"pushedAt":233,"stars":234},5,203,false,1778554780000,2113,{"npmDownloads":236},611,{"hasNpmPackage":224,"smitheryVerified":232},{"hasCi":224,"hasTests":232},{"updatedAt":240},1778696732992,{"basePath":242,"githubOwner":243,"githubRepo":244,"locale":18,"slug":13,"type":245},"skills/context-optimizer","rohitg00","pro-workflow","skill",{"_creationTime":247,"_id":248,"community":249,"display":250,"identity":256,"parentExtension":259,"providers":291,"relations":305,"tags":306,"workflow":307},1778696595410.5615,"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv",{"reviewCount":8},{"description":251,"installMethods":252,"name":255,"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":244,"cursor":253,"npm":244,"skillkit":254},"/add-plugin pro-workflow","npx skillkit install pro-workflow","Pro Workflow",{"basePath":257,"githubOwner":243,"githubRepo":244,"locale":18,"slug":244,"type":258},"","plugin",{"_creationTime":260,"_id":261,"community":262,"display":263,"identity":266,"providers":268,"relations":285,"tags":287,"workflow":288},1778696595410.5613,"k1741gyqaf0tj1ffq65gjpsm6x86mfhx",{"reviewCount":8},{"description":264,"installMethods":265,"name":255,"sourceUrl":14},"Battle-tested Claude Code workflows from power users",{"claudeCode":12},{"basePath":257,"githubOwner":243,"githubRepo":244,"locale":18,"slug":244,"type":267},"marketplace",{"evaluate":269,"extract":278},{"promptVersionExtension":270,"promptVersionScoring":204,"score":271,"tags":272,"targetMarket":215,"tier":216},"3.1.0",99,[273,274,275,276,277],"workflow","productivity","ai-assistance","developer-tools","knowledge-management",{"commitSha":279,"license":280,"marketplace":281,"plugin":283},"HEAD","MIT",{"name":244,"pluginCount":282},1,{"mcpCount":8,"provider":284,"skillCount":8},"classify",{"repoId":286},"kd7am4e918eq98hrd9s31jm4vs86nn0b",[275,276,277,274,273],{"evaluatedAt":289,"extractAt":290,"updatedAt":289},1778696611346,1778696595410,{"evaluate":292,"extract":302},{"promptVersionExtension":203,"promptVersionScoring":204,"score":293,"tags":294,"targetMarket":215,"tier":301},96,[273,274,295,296,297,298,299,300],"ai-coding","self-correction","knowledge-base","sqlite","hooks","agents","community",{"commitSha":279,"license":280,"plugin":303},{"mcpCount":8,"provider":284,"skillCount":304},34,{"parentExtensionId":261,"repoId":286},[300,295,299,297,274,296,298,273],{"evaluatedAt":308,"extractAt":290,"updatedAt":308},1778696621396,{"evaluate":310,"extract":312},{"promptVersionExtension":203,"promptVersionScoring":204,"score":207,"tags":311,"targetMarket":215,"tier":216},[210,211,212,213,214],{"commitSha":279},{"parentExtensionId":248,"repoId":286},{"_creationTime":315,"_id":286,"identity":316,"providers":317,"workflow":803},1778696588306.821,{"githubOwner":243,"githubRepo":244,"sourceUrl":14},{"classify":318,"discover":783,"extract":786,"github":787,"npm":802},{"commitSha":279,"extensions":319},[320,330,471,480,488,496,504,512,520,525,533,541,549,557,565,576,584,592,600,608,616,624,632,639,647,655,663,671,679,691,699,707,739,749,765,775],{"basePath":257,"description":264,"displayName":244,"installMethods":321,"rationale":322,"selectedPaths":323,"source":329,"sourceLanguage":18,"type":267},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[324,327],{"path":325,"priority":326},".claude-plugin/marketplace.json","mandatory",{"path":328,"priority":326},"README.md","rule",{"basePath":257,"description":251,"displayName":244,"installMethods":331,"license":280,"rationale":332,"selectedPaths":333,"source":329,"sourceLanguage":18,"type":258},{"claudeCode":244},"plugin manifest at .claude-plugin/plugin.json",[334,336,337,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469],{"path":335,"priority":326},".claude-plugin/plugin.json",{"path":328,"priority":326},{"path":338,"priority":339},"skills/agent-teams/SKILL.md","medium",{"path":341,"priority":339},"skills/auto-setup/SKILL.md",{"path":343,"priority":339},"skills/batch-orchestration/SKILL.md",{"path":345,"priority":339},"skills/bug-capture/SKILL.md",{"path":347,"priority":339},"skills/compact-guard/SKILL.md",{"path":349,"priority":339},"skills/context-engineering/SKILL.md",{"path":351,"priority":339},"skills/context-optimizer/SKILL.md",{"path":353,"priority":339},"skills/cost-tracker/SKILL.md",{"path":355,"priority":339},"skills/deslop/SKILL.md",{"path":357,"priority":339},"skills/file-watcher/SKILL.md",{"path":359,"priority":339},"skills/insights/SKILL.md",{"path":361,"priority":339},"skills/learn-rule/SKILL.md",{"path":363,"priority":339},"skills/llm-council/SKILL.md",{"path":365,"priority":339},"skills/llm-gate/SKILL.md",{"path":367,"priority":339},"skills/mcp-audit/SKILL.md",{"path":369,"priority":339},"skills/module-map/SKILL.md",{"path":371,"priority":339},"skills/orchestrate/SKILL.md",{"path":373,"priority":339},"skills/parallel-worktrees/SKILL.md",{"path":375,"priority":339},"skills/permission-tuner/SKILL.md",{"path":377,"priority":339},"skills/plan-interrogate/SKILL.md",{"path":379,"priority":339},"skills/pro-workflow/SKILL.md",{"path":381,"priority":339},"skills/replay-learnings/SKILL.md",{"path":383,"priority":339},"skills/safe-mode/SKILL.md",{"path":385,"priority":339},"skills/session-handoff/SKILL.md",{"path":387,"priority":339},"skills/smart-commit/SKILL.md",{"path":389,"priority":339},"skills/sprint-status/SKILL.md",{"path":391,"priority":339},"skills/survey-generator/SKILL.md",{"path":393,"priority":339},"skills/thoroughness-scoring/SKILL.md",{"path":395,"priority":339},"skills/token-efficiency/SKILL.md",{"path":397,"priority":339},"skills/wiki-builder/SKILL.md",{"path":399,"priority":339},"skills/wiki-query/SKILL.md",{"path":401,"priority":339},"skills/wiki-research-loop/SKILL.md",{"path":403,"priority":339},"skills/wiki-viewer/SKILL.md",{"path":405,"priority":339},"skills/wrap-up/SKILL.md",{"path":407,"priority":408},"agents/context-engineer.md","high",{"path":410,"priority":408},"agents/cost-analyst.md",{"path":412,"priority":408},"agents/debugger.md",{"path":414,"priority":408},"agents/orchestrator.md",{"path":416,"priority":408},"agents/permission-analyst.md",{"path":418,"priority":408},"agents/planner.md",{"path":420,"priority":408},"agents/reviewer.md",{"path":422,"priority":408},"agents/scout.md",{"path":424,"priority":408},"commands/auto-setup.md",{"path":426,"priority":408},"commands/commit.md",{"path":428,"priority":408},"commands/compact-guard.md",{"path":430,"priority":408},"commands/context-optimizer.md",{"path":432,"priority":408},"commands/cost-tracker.md",{"path":434,"priority":408},"commands/deslop.md",{"path":436,"priority":408},"commands/develop.md",{"path":438,"priority":408},"commands/doctor.md",{"path":440,"priority":408},"commands/handoff.md",{"path":442,"priority":408},"commands/insights.md",{"path":444,"priority":408},"commands/learn-rule.md",{"path":446,"priority":408},"commands/learn.md",{"path":448,"priority":408},"commands/list.md",{"path":450,"priority":408},"commands/mcp-audit.md",{"path":452,"priority":408},"commands/parallel.md",{"path":454,"priority":408},"commands/permission-tuner.md",{"path":456,"priority":408},"commands/replay.md",{"path":458,"priority":408},"commands/safe-mode.md",{"path":460,"priority":408},"commands/search.md",{"path":462,"priority":408},"commands/sprint-status.md",{"path":464,"priority":408},"commands/wiki.md",{"path":466,"priority":408},"commands/wrap-up.md",{"path":468,"priority":408},"hooks/hooks.json",{"path":470,"priority":408},".cursor-plugin/plugin.json",{"basePath":472,"description":473,"displayName":474,"installMethods":475,"rationale":476,"selectedPaths":477,"source":329,"sourceLanguage":18,"type":245},"skills/agent-teams","Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.","agent-teams",{"claudeCode":12},"SKILL.md frontmatter at skills/agent-teams/SKILL.md",[478],{"path":479,"priority":326},"SKILL.md",{"basePath":481,"description":482,"displayName":483,"installMethods":484,"rationale":485,"selectedPaths":486,"source":329,"sourceLanguage":18,"type":245},"skills/auto-setup","Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.","auto-setup",{"claudeCode":12},"SKILL.md frontmatter at skills/auto-setup/SKILL.md",[487],{"path":479,"priority":326},{"basePath":489,"description":490,"displayName":491,"installMethods":492,"rationale":493,"selectedPaths":494,"source":329,"sourceLanguage":18,"type":245},"skills/batch-orchestration","Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.","batch-orchestration",{"claudeCode":12},"SKILL.md frontmatter at skills/batch-orchestration/SKILL.md",[495],{"path":479,"priority":326},{"basePath":497,"description":498,"displayName":499,"installMethods":500,"rationale":501,"selectedPaths":502,"source":329,"sourceLanguage":18,"type":245},"skills/bug-capture","Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says \"file an issue\", \"log this as a bug\", \"capture this\".","bug-capture",{"claudeCode":12},"SKILL.md frontmatter at skills/bug-capture/SKILL.md",[503],{"path":479,"priority":326},{"basePath":505,"description":506,"displayName":507,"installMethods":508,"rationale":509,"selectedPaths":510,"source":329,"sourceLanguage":18,"type":245},"skills/compact-guard","Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.","compact-guard",{"claudeCode":12},"SKILL.md frontmatter at skills/compact-guard/SKILL.md",[511],{"path":479,"priority":326},{"basePath":513,"description":514,"displayName":515,"installMethods":516,"rationale":517,"selectedPaths":518,"source":329,"sourceLanguage":18,"type":245},"skills/context-engineering","Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.","context-engineering",{"claudeCode":12},"SKILL.md frontmatter at skills/context-engineering/SKILL.md",[519],{"path":479,"priority":326},{"basePath":242,"description":10,"displayName":13,"installMethods":521,"rationale":522,"selectedPaths":523,"source":329,"sourceLanguage":18,"type":245},{"claudeCode":12},"SKILL.md frontmatter at skills/context-optimizer/SKILL.md",[524],{"path":479,"priority":326},{"basePath":526,"description":527,"displayName":528,"installMethods":529,"rationale":530,"selectedPaths":531,"source":329,"sourceLanguage":18,"type":245},"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",[532],{"path":479,"priority":326},{"basePath":534,"description":535,"displayName":536,"installMethods":537,"rationale":538,"selectedPaths":539,"source":329,"sourceLanguage":18,"type":245},"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",[540],{"path":479,"priority":326},{"basePath":542,"description":543,"displayName":544,"installMethods":545,"rationale":546,"selectedPaths":547,"source":329,"sourceLanguage":18,"type":245},"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",[548],{"path":479,"priority":326},{"basePath":550,"description":551,"displayName":552,"installMethods":553,"rationale":554,"selectedPaths":555,"source":329,"sourceLanguage":18,"type":245},"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",[556],{"path":479,"priority":326},{"basePath":558,"description":559,"displayName":560,"installMethods":561,"rationale":562,"selectedPaths":563,"source":329,"sourceLanguage":18,"type":245},"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",[564],{"path":479,"priority":326},{"basePath":566,"description":567,"displayName":568,"installMethods":569,"rationale":570,"selectedPaths":571,"source":329,"sourceLanguage":18,"type":245},"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",[572,573],{"path":479,"priority":326},{"path":574,"priority":575},"scripts/council.js","low",{"basePath":577,"description":578,"displayName":579,"installMethods":580,"rationale":581,"selectedPaths":582,"source":329,"sourceLanguage":18,"type":245},"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",[583],{"path":479,"priority":326},{"basePath":585,"description":586,"displayName":587,"installMethods":588,"rationale":589,"selectedPaths":590,"source":329,"sourceLanguage":18,"type":245},"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",[591],{"path":479,"priority":326},{"basePath":593,"description":594,"displayName":595,"installMethods":596,"rationale":597,"selectedPaths":598,"source":329,"sourceLanguage":18,"type":245},"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",[599],{"path":479,"priority":326},{"basePath":601,"description":602,"displayName":603,"installMethods":604,"rationale":605,"selectedPaths":606,"source":329,"sourceLanguage":18,"type":245},"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",[607],{"path":479,"priority":326},{"basePath":609,"description":610,"displayName":611,"installMethods":612,"rationale":613,"selectedPaths":614,"source":329,"sourceLanguage":18,"type":245},"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",[615],{"path":479,"priority":326},{"basePath":617,"description":618,"displayName":619,"installMethods":620,"rationale":621,"selectedPaths":622,"source":329,"sourceLanguage":18,"type":245},"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",[623],{"path":479,"priority":326},{"basePath":625,"description":626,"displayName":627,"installMethods":628,"rationale":629,"selectedPaths":630,"source":329,"sourceLanguage":18,"type":245},"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",[631],{"path":479,"priority":326},{"basePath":633,"description":634,"displayName":244,"installMethods":635,"rationale":636,"selectedPaths":637,"source":329,"sourceLanguage":18,"type":245},"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",[638],{"path":479,"priority":326},{"basePath":640,"description":641,"displayName":642,"installMethods":643,"rationale":644,"selectedPaths":645,"source":329,"sourceLanguage":18,"type":245},"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",[646],{"path":479,"priority":326},{"basePath":648,"description":649,"displayName":650,"installMethods":651,"rationale":652,"selectedPaths":653,"source":329,"sourceLanguage":18,"type":245},"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",[654],{"path":479,"priority":326},{"basePath":656,"description":657,"displayName":658,"installMethods":659,"rationale":660,"selectedPaths":661,"source":329,"sourceLanguage":18,"type":245},"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",[662],{"path":479,"priority":326},{"basePath":664,"description":665,"displayName":666,"installMethods":667,"rationale":668,"selectedPaths":669,"source":329,"sourceLanguage":18,"type":245},"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",[670],{"path":479,"priority":326},{"basePath":672,"description":673,"displayName":674,"installMethods":675,"rationale":676,"selectedPaths":677,"source":329,"sourceLanguage":18,"type":245},"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",[678],{"path":479,"priority":326},{"basePath":680,"description":681,"displayName":682,"installMethods":683,"rationale":684,"selectedPaths":685,"source":329,"sourceLanguage":18,"type":245},"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",[686,687,689],{"path":479,"priority":326},{"path":688,"priority":575},"scripts/build-survey.js",{"path":690,"priority":575},"templates/research_bundle.template.json",{"basePath":692,"description":693,"displayName":694,"installMethods":695,"rationale":696,"selectedPaths":697,"source":329,"sourceLanguage":18,"type":245},"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",[698],{"path":479,"priority":326},{"basePath":700,"description":701,"displayName":702,"installMethods":703,"rationale":704,"selectedPaths":705,"source":329,"sourceLanguage":18,"type":245},"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",[706],{"path":479,"priority":326},{"basePath":708,"description":709,"displayName":710,"installMethods":711,"rationale":712,"selectedPaths":713,"source":329,"sourceLanguage":18,"type":245},"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",[714,715,717,719,721,723,725,727,729,731,733,735,737],{"path":479,"priority":326},{"path":716,"priority":339},"references/wiki-flavors.md",{"path":718,"priority":575},"scripts/init_wiki.sh",{"path":720,"priority":575},"scripts/wiki-cli.js",{"path":722,"priority":575},"templates/index.md",{"path":724,"priority":575},"templates/maintenance-log.md",{"path":726,"priority":575},"templates/prompts/compile-concept-page.md",{"path":728,"priority":575},"templates/prompts/compile-index.md",{"path":730,"priority":575},"templates/prompts/compile-source-page.md",{"path":732,"priority":575},"templates/prompts/lint-wiki.md",{"path":734,"priority":575},"templates/prompts/query-and-file.md",{"path":736,"priority":575},"templates/sources.md",{"path":738,"priority":575},"templates/wiki.config.md",{"basePath":740,"description":741,"displayName":742,"installMethods":743,"rationale":744,"selectedPaths":745,"source":329,"sourceLanguage":18,"type":245},"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",[746,747],{"path":479,"priority":326},{"path":748,"priority":575},"scripts/query.js",{"basePath":750,"description":751,"displayName":752,"installMethods":753,"rationale":754,"selectedPaths":755,"source":329,"sourceLanguage":18,"type":245},"skills/wiki-research-loop","Auto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from the queue, fetches sources, drafts a wiki page, dedupes claims against existing pages, enqueues follow-up seeds. Halts on budget cap, depth cap, or convergence. Use when the user says \"research \u003Ctopic>\", \"grow the \u003Cslug> wiki\", \"auto-research\", or wants a knowledge base that builds itself overnight.","wiki-research-loop",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-research-loop/SKILL.md",[756,757,759,761,763],{"path":479,"priority":326},{"path":758,"priority":575},"scripts/research-loop.js",{"path":760,"priority":575},"scripts/source-fetchers/arxiv.js",{"path":762,"priority":575},"scripts/source-fetchers/github.js",{"path":764,"priority":575},"scripts/source-fetchers/web.js",{"basePath":766,"description":767,"displayName":768,"installMethods":769,"rationale":770,"selectedPaths":771,"source":329,"sourceLanguage":18,"type":245},"skills/wiki-viewer","Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's \"Unreasonable Effectiveness of HTML\" — favors information density and shareability over markdown-only outputs.","wiki-viewer",{"claudeCode":12},"SKILL.md frontmatter at skills/wiki-viewer/SKILL.md",[772,773],{"path":479,"priority":326},{"path":774,"priority":575},"scripts/render.js",{"basePath":776,"description":777,"displayName":778,"installMethods":779,"rationale":780,"selectedPaths":781,"source":329,"sourceLanguage":18,"type":245},"skills/wrap-up","End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying \"wrap up\", \"done for the day\", \"finish coding\", or ending a coding session.","wrap-up",{"claudeCode":12},"SKILL.md frontmatter at skills/wrap-up/SKILL.md",[782],{"path":479,"priority":326},{"sources":784},[785],"manual",{"npmPackage":244},{"closedIssues90d":230,"description":788,"forks":231,"homepage":789,"openIssues90d":8,"pushedAt":233,"readmeSize":228,"stars":234,"topics":790},"Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.","https://rohitg00.github.io/pro-workflow/infographic.html",[791,213,792,273,793,794,295,795,796,797,798,799,515,276,800,299,274,296,801],"claude","cursor","agent-orchestration","ai-agents","ai-workflow","claude-code-plugin","claude-code-skills","claude-skills","codex","gemini-cli","worktrees",{"downloads":236},{"classifiedAt":804,"discoverAt":805,"extractAt":806,"githubAt":806,"npmAt":807,"updatedAt":804},1778696594915,1778696588306,1778696590961,1778696593284,[213,210,212,211,214],{"evaluatedAt":240,"extractAt":290,"updatedAt":240},[],[812,841,871,901,929,958],{"_creationTime":813,"_id":814,"community":815,"display":816,"identity":822,"providers":827,"relations":834,"tags":837,"workflow":838},1778696691708.329,"k170yjw596k3cg892bq130jyd186mhyz",{"reviewCount":8},{"description":817,"installMethods":818,"name":820,"sourceUrl":821},"Validate a Claude Code plugin structure, frontmatter, and MCP tool references",{"claudeCode":819},"ruvnet/ruflo","Validate Plugin","https://github.com/ruvnet/ruflo",{"basePath":823,"githubOwner":824,"githubRepo":825,"locale":18,"slug":826,"type":245},"plugins/ruflo-plugin-creator/skills/validate-plugin","ruvnet","ruflo","validate-plugin",{"evaluate":828,"extract":833},{"promptVersionExtension":203,"promptVersionScoring":204,"score":829,"tags":830,"targetMarket":215,"tier":216},100,[831,258,276,213,832],"validation","mcp",{"commitSha":279,"license":280},{"parentExtensionId":835,"repoId":836},"k17f4y1y2y777p7zrxxhbnf03n86mr5j","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[213,276,832,258,831],{"evaluatedAt":839,"extractAt":840,"updatedAt":839},1778701241052,1778696691708,{"_creationTime":842,"_id":843,"community":844,"display":845,"identity":851,"providers":855,"relations":864,"tags":866,"workflow":867},1778699106670.4258,"k17c1n6dbde7qh2wemx78d13t986n7x2",{"reviewCount":8},{"description":846,"installMethods":847,"name":849,"sourceUrl":850},"Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.",{"claudeCode":848},"xixu-me/skills","running-claude-code-via-litellm-copilot","https://github.com/xixu-me/skills",{"basePath":852,"githubOwner":853,"githubRepo":854,"locale":18,"slug":849,"type":245},"skills/running-claude-code-via-litellm-copilot","xixu-me","skills",{"evaluate":856,"extract":863},{"promptVersionExtension":203,"promptVersionScoring":204,"score":829,"tags":857,"targetMarket":215,"tier":216},[858,859,860,213,861,862],"copilot","litellm","proxy","configuration","troubleshooting",{"commitSha":279},{"repoId":865},"kd77r2vb42jmgam0qbr9f2c6kn86mebv",[213,861,858,859,860,862],{"evaluatedAt":868,"extractAt":869,"updatedAt":870},1778699196029,1778699106670,1778699384216,{"_creationTime":872,"_id":873,"community":874,"display":875,"identity":881,"providers":885,"relations":893,"tags":896,"workflow":897},1778696712851.9746,"k17ef0e0f693nd248cs3f63rys86ndy8",{"reviewCount":8},{"description":876,"installMethods":877,"name":879,"sourceUrl":880},"Protect Claude Code sessions from context overflow by running a background daemon that monitors session size and auto-prunes before compaction hits. Use when the user says \"guard\", \"protect session\", \"context getting long\", \"prevent compaction\", \"session management\", or is running agent teams that need continuous context protection.\n",{"claudeCode":878},"Ruya-AI/cozempic","guard","https://github.com/Ruya-AI/cozempic",{"basePath":882,"githubOwner":883,"githubRepo":884,"locale":18,"slug":879,"type":245},"plugin/skills/guard","Ruya-AI","cozempic",{"evaluate":886,"extract":892},{"promptVersionExtension":203,"promptVersionScoring":204,"score":829,"tags":887,"targetMarket":215,"tier":216},[888,889,213,890,891],"session-management","context-pruning","python","utility",{"commitSha":279},{"parentExtensionId":894,"repoId":895},"k176hd1j2vn0hpak7ds6v3eand86mfqh","kd79d77qmyh3826dwhk7ynx9xd86nmqm",[213,889,890,888,891],{"evaluatedAt":898,"extractAt":899,"updatedAt":900},1778696790816,1778696712852,1778696924761,{"_creationTime":902,"_id":903,"community":904,"display":905,"identity":911,"providers":915,"relations":922,"tags":925,"workflow":926},1778694480889.9487,"k17eg219cke0p45yfhh8n2t37986mgm4",{"reviewCount":8},{"description":906,"installMethods":907,"name":909,"sourceUrl":910},"Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration",{"claudeCode":908},"NeoLabHQ/context-engineering-kit","create-command","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":912,"githubOwner":913,"githubRepo":914,"locale":18,"slug":909,"type":245},"plugins/customaize-agent/skills/create-command","NeoLabHQ","context-engineering-kit",{"evaluate":916,"extract":921},{"promptVersionExtension":203,"promptVersionScoring":204,"score":829,"tags":917,"targetMarket":215,"tier":216},[918,919,920,832,213],"command-creation","agent-development","prompt-engineering",{"commitSha":279},{"parentExtensionId":923,"repoId":924},"k173g0c46wghgz5j9gn02wfydn86mkh8","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[919,213,918,832,920],{"evaluatedAt":927,"extractAt":928,"updatedAt":927},1778694773368,1778694480890,{"_creationTime":930,"_id":931,"community":932,"display":933,"identity":939,"providers":944,"relations":951,"tags":954,"workflow":955},1778692488329.0164,"k17d7dgccv6vnj9tcw0cehwnph86nryb",{"reviewCount":8},{"description":934,"installMethods":935,"name":937,"sourceUrl":938},"Analyze which rules are actively used vs inert. Detect coverage gaps. Recommend pruning to reduce token consumption.",{"claudeCode":936},"luiseiman/claude-kit","Rule Effectiveness Analysis","https://github.com/luiseiman/claude-kit",{"basePath":940,"githubOwner":941,"githubRepo":942,"locale":18,"slug":943,"type":245},"skills/rule-effectiveness","luiseiman","claude-kit","rule-effectiveness",{"evaluate":945,"extract":950},{"promptVersionExtension":203,"promptVersionScoring":204,"score":829,"tags":946,"targetMarket":215,"tier":216},[213,861,947,948,949],"analysis","optimization","git",{"commitSha":279,"license":280},{"parentExtensionId":952,"repoId":953},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[947,213,861,949,948],{"evaluatedAt":956,"extractAt":957,"updatedAt":956},1778693275143,1778692488329,{"_creationTime":959,"_id":960,"community":961,"display":962,"identity":966,"providers":968,"relations":975,"tags":976,"workflow":977},1778692488329.0137,"k172mwc9y507ztvq3eqqkqnhvh86n16s",{"reviewCount":8},{"description":963,"installMethods":964,"name":965,"sourceUrl":938},"Initializes the Claude Code configuration in a new or existing project using the dotforge template.",{"claudeCode":936},"bootstrap-project",{"basePath":967,"githubOwner":941,"githubRepo":942,"locale":18,"slug":965,"type":245},"skills/bootstrap-project",{"evaluate":969,"extract":974},{"promptVersionExtension":203,"promptVersionScoring":204,"score":829,"tags":970,"targetMarket":215,"tier":216},[861,971,972,973,213],"project-setup","automation","dotforge",{"commitSha":279},{"parentExtensionId":952,"repoId":953},[972,213,861,973,971],{"evaluatedAt":978,"extractAt":957,"updatedAt":978},1778692993130]