[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-yvgude-lean-ctx-en":3,"guides-for-yvgude-lean-ctx":512,"similar-k170fxxh22hdspg4vr94whgj1986mpr9-en":513},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":242,"isFallback":234,"parentExtension":246,"providers":247,"relations":252,"repo":254,"tags":508,"workflow":509},1778699438912.8826,"k170fxxh22hdspg4vr94whgj1986mpr9",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.",{"claudeCode":12},"yvgude/lean-ctx","lean-ctx","https://github.com/yvgude/lean-ctx",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":240},1778699456179.6384,"kn7as55n1jmcyb8vj5gqk6dca186msac","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":217,"tier":218,"useCases":219},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,112,115,119,122,125,128,131,134,137,141,145,149,152,156,159,162,165,168,172,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of reducing LLM context waste and names the artifacts (files, shell output) and user intents (reading, running commands, searching code, exploring directories) that the extension addresses.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","LeanCTX offers significant value over direct LLM interaction by compressing context through various modes and patterns, providing a unique solution for token reduction and efficient AI agent operation.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a complete lifecycle, from installation and setup to various integration modes and advanced features like session continuity and knowledge management, making it ready for production workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses on optimizing LLM context through file reading and shell command compression, maintaining a coherent domain without silently extending into unrelated areas.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The provided description accurately and concisely reflects the extension's capabilities, including its compression techniques, supported languages, and primary use cases.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The extension primarily uses narrowly scoped tools for specific actions like file reading modes and command execution wrappers, rather than a single generalist tool.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All parameters for commands and read modes are documented in the SKILL.md and README, including default behaviors and usage instructions.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool names like 'read', 'knowledge', 'session', and commands wrapped by '-c' are descriptive and align with the extension's domain.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Inputs for commands and read modes are generally well-defined flags or structured arguments, and outputs are focused on compressed or structured information relevant to the task.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The project is licensed under Apache-2.0, as indicated by the LICENSE file and badges, which is a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows recent activity with a commit on 2026-05-13, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses Cargo for Rust dependencies and mentions npm for a related package, and has CI, suggesting dependency management practices are in place.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The extension focuses on local context compression and command execution, and its documentation and scripts do not indicate handling or echoing of sensitive secrets.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The installation script uses `curl | bash` which is generally safe when piped from a trusted source, and the tool itself appears to treat file content as data, not instructions, based on its purpose.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The installation uses `curl | bash` from a trusted URL, and the tool's core functionality focuses on local file and command processing, not remote code execution or dynamic content interpretation as instructions.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The tool operates locally on user files and shell commands, and its installation script targets standard user bin directories, not outside project folders or system-wide configuration outside of intended hooks.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","The provided installation script and tool description do not contain evidence of detached processes or retry loops around denied calls, suggesting no sandbox escape primitives are used.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension's purpose is local context compression and command execution; there's no indication of it reading or submitting confidential data to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled files and descriptions appear to be free of hidden steering tricks, control characters, or invisible Unicode characters designed to manipulate the AI.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The installation script is a clear bash script, and the tool itself is described as a Rust binary, with no evidence of obfuscated code or runtime script fetching for core logic.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The installation script uses standard user-local bin paths, and the tool's documentation implies it adapts to project structures rather than enforcing rigid ones.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The trust signals show 0 open issues and 150 closed issues in the last 90 days, indicating very active maintenance and issue resolution.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project uses Cargo with crates.io for versioning and has clear versioning indicated by GitHub releases and npm package, with recent activity.",{"category":103,"check":104,"severity":24,"summary":105},"Code Execution","Validation","While explicit schema validation libraries aren't detailed in the source, the nature of the tool (local file/command processing) and its Rust implementation suggest internal validation is likely robust. Documentation focuses on the command/file wrapping aspect.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The tool primarily manipulates context and shells commands, with no indication of destructive operations (like `rm -rf` or data deletion) being performed without user interaction or explicit command.",{"category":103,"check":110,"severity":24,"summary":111},"Error Handling","The Rust implementation likely includes robust error handling, and the tool's focus on wrapping commands and files suggests errors would be reported back clearly rather than silently swallowed.",{"category":103,"check":113,"severity":24,"summary":114},"Logging","The tool features 'gain' and 'dashboard' commands for visualizing token savings, implying local logging or state capture for analytics, and the `setup` command mentions configuration, suggesting audit trails are possible.",{"category":116,"check":117,"severity":24,"summary":118},"Compliance","GDPR","The tool operates locally on user files and commands and does not appear to process or submit personal data to third parties.",{"category":116,"check":120,"severity":24,"summary":121},"Target market","The extension's functionality is universally applicable to code development workflows and does not exhibit any language, legal, or regional restrictions, making it global.",{"category":91,"check":123,"severity":24,"summary":124},"Runtime stability","The installation script targets standard user locations and the tool itself is a single Rust binary, suggesting good cross-platform compatibility (Linux, macOS) as indicated by platform detection.",{"category":44,"check":126,"severity":24,"summary":127},"README","The README file is comprehensive, well-formatted with clear sections, and effectively communicates the extension's purpose and capabilities.",{"category":33,"check":129,"severity":24,"summary":130},"Tool surface size","The extension exposes a focused set of commands and MCP tools related to context management and shell integration, well within the target range.",{"category":40,"check":132,"severity":24,"summary":133},"Overlapping near-synonym tools","The tool names and commands are distinct and cover specific functionalities (e.g., 'read' modes, 'knowledge', 'session', command wrapping) without significant overlap.",{"category":44,"check":135,"severity":24,"summary":136},"Phantom features","All advertised features, such as MCP tools, read modes, shell patterns, and AI tool integrations, are described and have corresponding implementations or setup instructions.",{"category":138,"check":139,"severity":24,"summary":140},"Install","Installation instruction","The README provides clear, multi-option installation instructions (curl, brew, npm, cargo, pi) and a step-by-step setup guide with verification commands.",{"category":142,"check":143,"severity":24,"summary":144},"Errors","Actionable error messages","The tool's CLI and documentation suggest clear reporting of issues, with `lean-ctx doctor --fix` and troubleshooting sections indicating an effort towards actionable error guidance.",{"category":146,"check":147,"severity":24,"summary":148},"Execution","Pinned dependencies","The Rust project likely uses Cargo.toml with version pinning, and the installation script focuses on fetching a specific release, indicating dependency management practices.",{"category":33,"check":150,"severity":24,"summary":151},"Dry-run preview","The `lean-ctx knowledge import` command includes a `--dry-run` flag, and the tool's core function is context manipulation, suggesting a focus on previewing effects where applicable.",{"category":153,"check":154,"severity":24,"summary":155},"Protocol","Idempotent retry & timeouts","The tool focuses on local operations and context manipulation. While not explicitly detailing idempotency for all operations, its Rust implementation and focus on wrapping CLI/reads suggest robust handling of state and potential timeouts would be incorporated.",{"category":116,"check":157,"severity":24,"summary":158},"Telemetry opt-in","The README explicitly states 'Telemetry-Opt--in Only' and mentions optional anonymous stats sharing during setup, aligning with best practices.",{"category":40,"check":160,"severity":24,"summary":161},"Precise Purpose","The extension clearly defines its purpose as compressing LLM context for AI agents and specifies usage scenarios like reading files and running shell commands, alongside clear non-goals implicitly through its focused functionality.",{"category":40,"check":163,"severity":24,"summary":164},"Concise Frontmatter","The frontmatter in SKILL.md is concise and self-contained, providing a clear summary of the core capability and relevant trigger phrases.",{"category":44,"check":166,"severity":24,"summary":167},"Concise Body","The SKILL.md and README are well-structured and avoid unnecessary verbosity, deferring deeper material to linked files where appropriate.",{"category":169,"check":170,"severity":24,"summary":171},"Context","Progressive Disclosure","The documentation and README link to separate files like BENCHMARKS.md, CHANGELOG.md, and COOKBOOK/README.md, demonstrating progressive disclosure of information.",{"category":169,"check":173,"severity":174,"summary":175},"Forked exploration","not_applicable","The extension's primary function is context compression and command wrapping, not deep exploration or code review that would necessitate a forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README and SKILL.md provide numerous clear, end-to-end examples for various commands and read modes, with instructions on how to reproduce GIF demos and benchmarks.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation addresses troubleshooting, safety concerns, and provides a `doctor --fix` command, indicating handling of potential failure modes and providing recovery steps.",{"category":103,"check":183,"severity":24,"summary":184},"Tool Fallback","The tool is designed to be largely self-contained, with installation scripts providing direct binaries. While it integrates with AI tools, it doesn't appear to require specific external MCP servers as a hard fallback.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The `lean-ctx doctor --fix` command and general troubleshooting advice suggest the tool aims to report and correct unexpected states rather than proceeding destructively.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The extension operates as a standalone utility and context compressor; there's no indication of implicit reliance on other specific skills.",1778699456062,"LeanCTX is a local-first context runtime that compresses file reads and shell command output for AI agents, reducing token usage by up to 99%. It offers various read modes, shell command patterns, and integrates with multiple AI tools via CLI-redirect or MCP protocols.",[195,196,197,198,199],"Context compression for LLM interactions","Advanced file reading modes","Shell command output compression","Integration with AI agents via CLI/MCP","Local-first operation with opt-in telemetry",[201,202,203],"Processing personal data without user consent.","Executing arbitrary remote code as instructions.","Replacing core development tools, but rather enhancing their output for LLMs.","3.0.0","4.4.0","To significantly reduce LLM token consumption and improve the efficiency of AI coding agents by intelligently compressing file content and shell command outputs.","All checks passed with positive evidence. The extension is well-documented, secure, actively maintained, and provides significant utility.",100,"A high-quality, secure, and actively maintained tool for optimizing LLM context for AI agents.",[211,212,213,214,215,216],"context-compression","ai-agent","cli-tools","developer-tools","rust","code-analysis","global","verified",[220,221,222,223],"When working with large codebases where AI agents need to read many files.","When AI agents frequently execute verbose shell commands (e.g., git, build logs).","To reduce LLM API costs by minimizing token usage.","For long-running AI agent tasks requiring efficient context management.",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"security":237,"testCoverage":239},{"hasLockfile":226},true,1778699440342,{"descriptionLength":229,"readmeSize":230},271,12393,{"closedIssues90d":232,"forks":233,"hasChangelog":234,"openIssues90d":8,"pushedAt":235,"stars":236},150,165,false,1778695353000,1629,{"hasNpmPackage":234,"license":238,"smitheryVerified":234},"Apache-2.0",{"hasCi":226,"hasTests":226},{"updatedAt":241},1778699456179,{"basePath":243,"githubOwner":244,"githubRepo":13,"locale":18,"slug":13,"type":245},"skills/lean-ctx","yvgude","skill",null,{"evaluate":248,"extract":250},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":249,"targetMarket":217,"tier":218},[211,212,213,214,215,216],{"commitSha":251},"HEAD",{"repoId":253},"kd7dxtfr9j3z54hs3bz0218e1n86may0",{"_creationTime":255,"_id":253,"identity":256,"providers":257,"workflow":504},1778699432853.3982,{"githubOwner":244,"githubRepo":13,"sourceUrl":14},{"classify":258,"discover":485,"github":488},{"commitSha":251,"extensions":259},[260,271,286],{"basePath":243,"description":10,"displayName":13,"installMethods":261,"rationale":262,"selectedPaths":263,"source":270,"sourceLanguage":18,"type":245},{"claudeCode":12},"SKILL.md frontmatter at skills/lean-ctx/SKILL.md (coalesced with duplicate skill at rust/src/templates)",[264,267],{"path":265,"priority":266},"SKILL.md","mandatory",{"path":268,"priority":269},"scripts/install.sh","low","rule",{"basePath":272,"description":273,"displayName":274,"installMethods":275,"license":238,"rationale":276,"selectedPaths":277,"source":270,"sourceLanguage":18,"type":285},"packages/lean-ctx-bin","lean-ctx — the token-efficient context tool for LLM coding agents. Installs a pre-built binary, no Rust required.","lean-ctx-bin",{"npm":274},"cli ecosystem detected at packages/lean-ctx-bin",[278,280,282],{"path":279,"priority":266},"package.json",{"path":281,"priority":266},"README.md",{"path":283,"priority":284},"bin/lean-ctx.js","medium","cli",{"basePath":215,"installMethods":287,"rationale":288,"selectedPaths":289,"source":270,"sourceLanguage":18,"type":484},{"cargo":13},"Cargo.toml with MCP SDK dependency + [[bin]] at rust/Cargo.toml",[290,292,293,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482],{"path":291,"priority":266},"Cargo.toml",{"path":281,"priority":266},{"path":294,"priority":295},"LICENSE","high",{"path":297,"priority":284},"src/main.rs",{"path":299,"priority":284},"src/cloud_server_main.rs",{"path":301,"priority":269},"src/lib.rs",{"path":303,"priority":269},"src/tools/autonomy.rs",{"path":305,"priority":269},"src/tools/ctx_agent.rs",{"path":307,"priority":269},"src/tools/ctx_analyze.rs",{"path":309,"priority":269},"src/tools/ctx_architecture.rs",{"path":311,"priority":269},"src/tools/ctx_artifacts.rs",{"path":313,"priority":269},"src/tools/ctx_benchmark.rs",{"path":315,"priority":269},"src/tools/ctx_callees.rs",{"path":317,"priority":269},"src/tools/ctx_callers.rs",{"path":319,"priority":269},"src/tools/ctx_callgraph.rs",{"path":321,"priority":269},"src/tools/ctx_compile.rs",{"path":323,"priority":269},"src/tools/ctx_compress.rs",{"path":325,"priority":269},"src/tools/ctx_compress_memory.rs",{"path":327,"priority":269},"src/tools/ctx_context.rs",{"path":329,"priority":269},"src/tools/ctx_control.rs",{"path":331,"priority":269},"src/tools/ctx_cost.rs",{"path":333,"priority":269},"src/tools/ctx_dedup.rs",{"path":335,"priority":269},"src/tools/ctx_delta.rs",{"path":337,"priority":269},"src/tools/ctx_discover.rs",{"path":339,"priority":269},"src/tools/ctx_edit.rs",{"path":341,"priority":269},"src/tools/ctx_execute.rs",{"path":343,"priority":269},"src/tools/ctx_expand.rs",{"path":345,"priority":269},"src/tools/ctx_feedback.rs",{"path":347,"priority":269},"src/tools/ctx_fill.rs",{"path":349,"priority":269},"src/tools/ctx_gain.rs",{"path":351,"priority":269},"src/tools/ctx_graph.rs",{"path":353,"priority":269},"src/tools/ctx_graph_diagram.rs",{"path":355,"priority":269},"src/tools/ctx_handoff.rs",{"path":357,"priority":269},"src/tools/ctx_heatmap.rs",{"path":359,"priority":269},"src/tools/ctx_impact.rs",{"path":361,"priority":269},"src/tools/ctx_index.rs",{"path":363,"priority":269},"src/tools/ctx_intent.rs",{"path":365,"priority":269},"src/tools/ctx_knowledge.rs",{"path":367,"priority":269},"src/tools/ctx_knowledge_relations.rs",{"path":369,"priority":269},"src/tools/ctx_metrics.rs",{"path":371,"priority":269},"src/tools/ctx_multi_read.rs",{"path":373,"priority":269},"src/tools/ctx_outline.rs",{"path":375,"priority":269},"src/tools/ctx_overview.rs",{"path":377,"priority":269},"src/tools/ctx_pack.rs",{"path":379,"priority":269},"src/tools/ctx_plan.rs",{"path":381,"priority":269},"src/tools/ctx_prefetch.rs",{"path":383,"priority":269},"src/tools/ctx_preload.rs",{"path":385,"priority":269},"src/tools/ctx_proof.rs",{"path":387,"priority":269},"src/tools/ctx_provider.rs",{"path":389,"priority":269},"src/tools/ctx_read.rs",{"path":391,"priority":269},"src/tools/ctx_response.rs",{"path":393,"priority":269},"src/tools/ctx_review.rs",{"path":395,"priority":269},"src/tools/ctx_routes.rs",{"path":397,"priority":269},"src/tools/ctx_search.rs",{"path":399,"priority":269},"src/tools/ctx_semantic_search.rs",{"path":401,"priority":269},"src/tools/ctx_session.rs",{"path":403,"priority":269},"src/tools/ctx_share.rs",{"path":405,"priority":269},"src/tools/ctx_shell.rs",{"path":407,"priority":269},"src/tools/ctx_smart_read.rs",{"path":409,"priority":269},"src/tools/ctx_smells.rs",{"path":411,"priority":269},"src/tools/ctx_symbol.rs",{"path":413,"priority":269},"src/tools/ctx_task.rs",{"path":415,"priority":269},"src/tools/ctx_tree.rs",{"path":417,"priority":269},"src/tools/ctx_verify.rs",{"path":419,"priority":269},"src/tools/ctx_workflow.rs",{"path":421,"priority":269},"src/tools/ctx_wrapped.rs",{"path":423,"priority":269},"src/tools/knowledge_shared.rs",{"path":425,"priority":269},"src/tools/mod.rs",{"path":427,"priority":269},"src/tools/registered/ctx_analyze.rs",{"path":429,"priority":269},"src/tools/registered/ctx_architecture.rs",{"path":431,"priority":269},"src/tools/registered/ctx_artifacts.rs",{"path":433,"priority":269},"src/tools/registered/ctx_benchmark.rs",{"path":435,"priority":269},"src/tools/registered/ctx_callees.rs",{"path":437,"priority":269},"src/tools/registered/ctx_callers.rs",{"path":439,"priority":269},"src/tools/registered/ctx_callgraph.rs",{"path":441,"priority":269},"src/tools/registered/ctx_compress_memory.rs",{"path":443,"priority":269},"src/tools/registered/ctx_cost.rs",{"path":445,"priority":269},"src/tools/registered/ctx_discover.rs",{"path":447,"priority":269},"src/tools/registered/ctx_discover_tools.rs",{"path":449,"priority":269},"src/tools/registered/ctx_expand.rs",{"path":451,"priority":269},"src/tools/registered/ctx_gain.rs",{"path":453,"priority":269},"src/tools/registered/ctx_graph_diagram.rs",{"path":455,"priority":269},"src/tools/registered/ctx_heatmap.rs",{"path":457,"priority":269},"src/tools/registered/ctx_impact.rs",{"path":459,"priority":269},"src/tools/registered/ctx_index.rs",{"path":461,"priority":269},"src/tools/registered/ctx_outline.rs",{"path":463,"priority":269},"src/tools/registered/ctx_pack.rs",{"path":465,"priority":269},"src/tools/registered/ctx_provider.rs",{"path":467,"priority":269},"src/tools/registered/ctx_response.rs",{"path":469,"priority":269},"src/tools/registered/ctx_review.rs",{"path":471,"priority":269},"src/tools/registered/ctx_routes.rs",{"path":473,"priority":269},"src/tools/registered/ctx_smells.rs",{"path":475,"priority":269},"src/tools/registered/ctx_symbol.rs",{"path":477,"priority":269},"src/tools/registered/ctx_tree.rs",{"path":479,"priority":269},"src/tools/registered/ctx_verify.rs",{"path":481,"priority":269},"src/tools/registered/ctx_wrapped.rs",{"path":483,"priority":269},"src/tools/registered/mod.rs","mcp",{"sources":486},[487],"manual",{"closedIssues90d":232,"description":489,"forks":233,"homepage":490,"license":238,"openIssues90d":8,"pushedAt":235,"readmeSize":230,"stars":236,"topics":491},"The Context OS for AI Development. Reduce token waste in Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini & more by 60–95% (up to 99% on cached reads) Shell Hook + MCP Server · 49 tools · 10 read modes · 90+ patterns · Single Rust binary ","https://leanctx.com",[492,493,494,484,215,495,496,497,498,214,499,500,501,502,503],"ai","cursor","llm","token-optimization","agentic-coding","claude-code","copilot","ai-coding","context-engineering","gemini-cli","mcp-server","reduce-token-costs",{"classifiedAt":505,"discoverAt":506,"extractAt":507,"githubAt":507,"updatedAt":505},1778699438683,1778699432853,1778699436480,[212,213,216,211,214,215],{"evaluatedAt":241,"extractAt":510,"updatedAt":511},1778699438912,1778699517795,[],[514,543,574,600,629,659],{"_creationTime":515,"_id":516,"community":517,"display":518,"identity":524,"providers":528,"relations":536,"tags":539,"workflow":540},1778696833339.6243,"k174g80xa9zxhydbncvpf0xzy986nvx5",{"reviewCount":8},{"description":519,"installMethods":520,"name":522,"sourceUrl":523},"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":521},"sanjay3290/ai-skills","manus","https://github.com/sanjay3290/ai-skills",{"basePath":525,"githubOwner":526,"githubRepo":527,"locale":18,"slug":522,"type":245},"skills/manus","sanjay3290","ai-skills",{"evaluate":529,"extract":535},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":530,"targetMarket":217,"tier":218},[212,531,532,533,534],"autonomous-execution","research","automation","api-integration",{"commitSha":251},{"parentExtensionId":537,"repoId":538},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[212,534,533,531,532],{"evaluatedAt":541,"extractAt":542,"updatedAt":541},1778697107270,1778696833339,{"_creationTime":544,"_id":545,"community":546,"display":547,"identity":553,"providers":558,"relations":566,"tags":569,"workflow":570},1778693539593.186,"k17bgwvhb6h29py715de1cm9xd86msq6",{"reviewCount":8},{"description":548,"installMethods":549,"name":551,"sourceUrl":552},"Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on \"risk\", \"drawdown\", \"tilt\", \"position size\", \"lot size\", \"confidence\", \"revenge trading\", \"overtrading\", \"discipline\".",{"claudeCode":550},"mnemox-ai/tradememory-protocol","Risk Management","https://github.com/mnemox-ai/tradememory-protocol",{"basePath":554,"githubOwner":555,"githubRepo":556,"locale":18,"slug":557,"type":245},"tradememory-plugin/skills/risk-management","mnemox-ai","tradememory-protocol","risk-management",{"evaluate":559,"extract":564},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":560,"targetMarket":217,"tier":218},[561,557,212,562,563],"trading","behavioral-analysis","finance",{"commitSha":251,"license":565},"MIT",{"parentExtensionId":567,"repoId":568},"k170vxkqee48k2xq1v55a025nh86nzn7","kd73z11kfekksxyrs8ds0snacs86ncdy",[212,562,563,557,561],{"evaluatedAt":571,"extractAt":572,"updatedAt":573},1778693700524,1778693539593,1778693833120,{"_creationTime":575,"_id":576,"community":577,"display":578,"identity":584,"providers":587,"relations":594,"tags":596,"workflow":597},1778687183932.1943,"k1728svzyq5wfc93gjyntemgnh86m6d9",{"reviewCount":8},{"description":579,"installMethods":580,"name":582,"sourceUrl":583},"Set up gbrain for this coding agent: install the CLI, initialize a\nlocal PGLite or Supabase brain, register MCP, capture per-remote trust\npolicy. One command from zero to \"gbrain is running, and this agent\ncan call it.\" Use when: \"setup gbrain\", \"connect gbrain\", \"start\ngbrain\", \"install gbrain\", \"configure gbrain for this machine\". (gstack)\n",{"claudeCode":581},"garrytan/gstack","setup-gbrain","https://github.com/garrytan/gstack",{"basePath":582,"githubOwner":585,"githubRepo":586,"locale":18,"slug":582,"type":245},"garrytan","gstack",{"evaluate":588,"extract":593},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":589,"targetMarket":217,"tier":218},[590,591,592,212,285,484],"gbrain","setup","configuration",{"commitSha":251},{"repoId":595},"kd73s35xh97m9mmc5nz3pb1f3n86m0an",[212,285,592,590,484,591],{"evaluatedAt":598,"extractAt":599,"updatedAt":598},1778688428238,1778687183932,{"_creationTime":601,"_id":602,"community":603,"display":604,"identity":610,"providers":615,"relations":623,"tags":625,"workflow":626},1778683190010.286,"k17bhh6s25qm1c5w7g2rfaknyd86nysv",{"reviewCount":8},{"description":605,"installMethods":606,"name":608,"sourceUrl":609},"Guide for creating effective skills",{"claudeCode":607},"bobmatnyc/claude-mpm-skills","Skill Creator","https://github.com/bobmatnyc/claude-mpm-skills",{"basePath":611,"githubOwner":612,"githubRepo":613,"locale":18,"slug":614,"type":245},"universal/main/skill-creator","bobmatnyc","claude-mpm-skills","skill-creator",{"evaluate":616,"extract":622},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":617,"targetMarket":217,"tier":218},[618,619,212,620,621],"documentation","skill-creation","developer-tool","framework",{"commitSha":251,"license":565},{"repoId":624},"kd72g55e5qeqs90bk1bvkt8wbx86nkn3",[212,620,618,621,619],{"evaluatedAt":627,"extractAt":628,"updatedAt":627},1778686498077,1778683190010,{"_creationTime":630,"_id":631,"community":632,"display":633,"identity":639,"providers":644,"relations":652,"tags":655,"workflow":656},1778695548458.377,"k17esa27yncbsd0bz8hcg2crg986mjqk",{"reviewCount":8},{"description":634,"installMethods":635,"name":637,"sourceUrl":638},"Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.\n",{"claudeCode":636},"pjt222/agent-almanac","Metal","https://github.com/pjt222/agent-almanac",{"basePath":640,"githubOwner":641,"githubRepo":642,"locale":18,"slug":643,"type":245},"skills/metal","pjt222","agent-almanac","metal",{"evaluate":645,"extract":651},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":646,"targetMarket":217,"tier":218},[216,647,648,649,650],"conceptualization","agent-definition","repository-structure","software-architecture",{"commitSha":251,"license":565},{"parentExtensionId":653,"repoId":654},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[648,216,647,649,650],{"evaluatedAt":657,"extractAt":658,"updatedAt":657},1778699463464,1778695548458,{"_creationTime":660,"_id":661,"community":662,"display":663,"identity":669,"providers":674,"relations":681,"tags":683,"workflow":684},1778698056313.1528,"k176pxdjxvnyex7jv6abt3myd586n5vv",{"reviewCount":8},{"description":664,"installMethods":665,"name":667,"sourceUrl":668},"Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to \"find the ideal path,\" unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.",{"claudeCode":666},"thedotmack/claude-mem","Pathfinder","https://github.com/thedotmack/claude-mem",{"basePath":670,"githubOwner":671,"githubRepo":672,"locale":18,"slug":673,"type":245},"plugin/skills/pathfinder","thedotmack","claude-mem","pathfinder",{"evaluate":675,"extract":680},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":676,"targetMarket":217,"tier":218},[216,677,618,678,679],"architecture","refactoring","flowchart",{"commitSha":251,"license":238},{"repoId":682},"kd70jnxgm695az2wtf37zbqdj986mp7k",[677,216,618,679,678],{"evaluatedAt":685,"extractAt":686,"updatedAt":687},1778698228002,1778698056313,1778698443446]