[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-BrainBlend-AI-framework-en":3,"guides-for-BrainBlend-AI-framework":485,"similar-k174y23pqen81g4psrdx7ejtf186nw0j-en":486},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":219,"isFallback":214,"parentExtension":224,"providers":281,"relations":285,"repo":286,"tags":482,"workflow":483},1778683220959.326,"k174y23pqen81g4psrdx7ejtf186nw0j",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Guide for the Atomic Agents Python framework — schemas, agents, tools, context providers, prompts, orchestration, and provider configuration. Use when code imports from `atomic_agents`, defines an `AtomicAgent`, `BaseTool`, or `BaseIOSchema`, or the user asks about multi-agent orchestration or LLM-provider wiring in an atomic-agents project.",{"claudeCode":12},"BrainBlend-AI/atomic-agents","Atomic Agents Framework Guide","https://github.com/BrainBlend-AI/atomic-agents",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":200,"workflow":217},1778683372619.575,"kn7fpbh2gvnem97fqqbdg11vzn86m17c","en",{"checks":20,"evaluatedAt":158,"extensionSummary":159,"features":160,"nonGoals":166,"practices":170,"prerequisites":174,"promptVersionExtension":176,"promptVersionScoring":177,"purpose":178,"rationale":179,"score":180,"summary":181,"tags":182,"targetMarket":188,"tier":189,"useCases":190,"workflow":195},[21,26,29,32,36,39,44,48,50,52,56,60,63,67,70,73,76,79,82,85,88,92,96,100,104,107,111,114,117,121,125,128,131,134,138,141,144,147,151,155],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly identifies the problem space: guiding users on the Atomic Agents Python framework, specifically for tasks involving its core abstractions, and lists concrete usage triggers.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The framework offers a distinct value proposition by emphasizing modularity, predictability, and control through structured schemas and Python best practices, differentiating it from other agentic AI frameworks.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a complete lifecycle for building LLM applications, covering core abstractions, tooling, and integration patterns with clear examples and documentation, indicating readiness for real-world workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on guiding users through the Atomic Agents Python framework and its components, without extending into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description is accurate, concise, and effectively communicates the skill's purpose and intended use cases, including specific import statements and user intents.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This check is not applicable as the extension is a skill that guides users on a framework, rather than exposing specific callable tools.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","Configuration details, environment variables for API keys, and model parameters are clearly documented within the referenced files, with default values and precedence explained.",{"category":33,"check":49,"severity":42,"summary":43},"Tool naming",{"category":33,"check":51,"severity":42,"summary":43},"Minimal I/O surface",{"category":53,"check":54,"severity":24,"summary":55},"License","License usability","The project is licensed under the MIT License, as indicated by the LICENSE file and README, which is a permissive open-source license.",{"category":57,"check":58,"severity":24,"summary":59},"Maintenance","Commit recency","The repository shows recent commits within the last 12 months, indicating active maintenance.",{"category":57,"check":61,"severity":24,"summary":62},"Dependency Management","The pyproject.toml file specifies dependencies, and the project structure includes development dependencies for testing, suggesting a managed approach to dependencies.",{"category":64,"check":65,"severity":24,"summary":66},"Security","Secret Management","The documentation and examples emphasize using environment variables for API keys and avoiding hardcoding secrets, adhering to secure practices.",{"category":64,"check":68,"severity":24,"summary":69},"Injection","The framework's design, leveraging Pydantic and Instructor, inherently treats LLM-generated content as data, mitigating injection risks. Documentation warns against common anti-patterns.",{"category":64,"check":71,"severity":24,"summary":72},"Transitive Supply-Chain Grenades","The framework focuses on bundled code and structured data, and the documentation warns against runtime fetches that could introduce external risks.",{"category":64,"check":74,"severity":24,"summary":75},"Sandbox Isolation","The framework and its components are designed to operate within their defined scopes, with no indication of attempts to modify files outside the project or bundle.",{"category":64,"check":77,"severity":24,"summary":78},"Sandbox escape primitives","No evidence of detached process spawns or deny-retry loops in the provided skill code or referenced patterns.",{"category":64,"check":80,"severity":24,"summary":81},"Data Exfiltration","The framework emphasizes structured data and warns against submitting secrets or PII, aligning with data exfiltration prevention principles.",{"category":64,"check":83,"severity":24,"summary":84},"Hidden Text Tricks","The documentation and code examples appear free of hidden text tricks or obfuscation techniques.",{"category":64,"check":86,"severity":24,"summary":87},"Opaque code execution","The codebase and examples utilize clear, readable Python code, avoiding obfuscation techniques like base64 payloads or runtime script fetching.",{"category":89,"check":90,"severity":24,"summary":91},"Portability","Structural Assumption","The project structure guidelines promote modularity and clear organization, and the framework's design avoids rigid assumptions about external project layouts.",{"category":93,"check":94,"severity":24,"summary":95},"Trust","Issues Attention","With 6 open issues and 7 closed issues in the last 90 days, the maintainers appear engaged and responsive.",{"category":97,"check":98,"severity":24,"summary":99},"Versioning","Release Management","The project has a clear versioning scheme indicated by PyPI version badges and release information in the README, with a `pyproject.toml` file likely managing versions.",{"category":101,"check":102,"severity":24,"summary":103},"Execution","Validation","The framework heavily relies on Pydantic for schema validation of inputs and outputs, ensuring data integrity.",{"category":64,"check":105,"severity":24,"summary":106},"Unguarded Destructive Operations","The framework focuses on building agents and tools, and the provided examples and documentation do not indicate the presence of unguarded destructive operations.",{"category":108,"check":109,"severity":24,"summary":110},"Errors","Error Handling","The framework utilizes Instructor's robust error handling mechanisms, including hooks for parse errors and completion errors, promoting structured error reporting.",{"category":101,"check":112,"severity":24,"summary":113},"Pinned dependencies","The `pyproject.toml` and `poetry.lock` (implied by `uv sync`) files indicate pinned dependencies, ensuring reproducible builds.",{"category":33,"check":115,"severity":42,"summary":116},"Dry-run preview","This check is not applicable as the extension is a skill that guides users on a framework, rather than executing state-changing commands.",{"category":118,"check":119,"severity":24,"summary":120},"Protocol","Idempotent retry & timeouts","The framework integrates with Instructor, which provides retry mechanisms, and the documentation encourages implementing timeouts for external calls, promoting robust protocols.",{"category":122,"check":123,"severity":24,"summary":124},"Compliance","Telemetry opt-in","The documentation and examples do not indicate any telemetry collection by default, aligning with opt-in principles.",{"category":40,"check":126,"severity":24,"summary":127},"Precise Purpose","The skill's description clearly states its purpose as a guide for the Atomic Agents framework and specifies when to use it, including import statements and user intents.",{"category":40,"check":129,"severity":24,"summary":130},"Concise Frontmatter","The frontmatter is dense and effectively summarizes the core capability within the character limit, followed by relevant trigger phrases.",{"category":45,"check":132,"severity":24,"summary":133},"Concise Body","The SKILL.md content is well-structured and uses progressive disclosure by referencing separate files for deeper material, keeping the main document concise.",{"category":135,"check":136,"severity":24,"summary":137},"Context","Progressive Disclosure","The skill effectively uses progressive disclosure by referencing detailed explanations for specific concepts (schemas, agents, tools, etc.) in separate Markdown files.",{"category":135,"check":139,"severity":42,"summary":140},"Forked exploration","This check is not applicable as the skill itself is a guide and does not perform deep exploration requiring forked context.",{"category":22,"check":142,"severity":24,"summary":143},"Usage examples","The skill links to numerous examples in the README and SKILL.md, covering quickstarts, complete examples, and specific patterns, which are ready-to-use.",{"category":22,"check":145,"severity":24,"summary":146},"Edge cases","The referenced documentation files (agents.md, tools.md, schemas.md, etc.) address common mistakes, anti-patterns, and potential failure modes, offering guidance on handling them.",{"category":148,"check":149,"severity":42,"summary":150},"Code Execution","Tool Fallback","This check is not applicable as the extension is a skill guiding users on a framework, not a tool that requires external dependencies with fallbacks.",{"category":152,"check":153,"severity":24,"summary":154},"Safety","Halt on unexpected state","The framework's design, with strict schema validation and error handling through hooks, encourages halting on unexpected states rather than proceeding silently.",{"category":89,"check":156,"severity":24,"summary":157},"Cross-skill coupling","The skill focuses on guiding the user through the Atomic Agents framework itself and directs users to specific skills or references for related tasks, promoting standalone capabilities.",1778683371515,"This skill serves as a central guide for the Atomic Agents Python framework, detailing its core abstractions like schemas, agents, tools, and context providers. It provides canonical import paths, minimum viable agent examples, and directs users to specialized skills for common authoring tasks.",[161,162,163,164,165],"Guides on core Atomic Agents abstractions (schemas, agents, tools, context providers)","Provides canonical import paths and minimum viable agent examples","Directs users to specialized skills for schema, agent, tool, and context provider creation","Details system prompt structure and LLM provider integration","References files for deeper dives into specific concepts like memory, orchestration, and testing",[167,168,169],"This skill does not provide direct execution capabilities.","It does not replace the need to read the official Atomic Agents documentation for in-depth information.","It does not offer a GUI or interactive interface; interaction is through Claude's chat.",[171,172,173],"Framework Guidance","LLM Application Development","Agent Design Patterns",[175],"Claude Code environment","3.0.0","4.4.0","To guide developers in understanding and utilizing the Atomic Agents Python framework for building structured, modular, and predictable LLM applications.","The skill is exceptionally well-documented, follows best practices, and provides clear guidance on using the Atomic Agents framework. It achieves a high score due to comprehensive documentation, robust error handling, and clear structure, with no significant issues identified.",99,"A comprehensive guide to the Atomic Agents Python framework, promoting best practices for building LLM applications.",[183,184,185,186,187],"llm","python","framework","agent","developer-tools","global","verified",[191,192,193,194],"Use when writing Python code that imports from `atomic_agents`.","Use when defining an `AtomicAgent`, `BaseTool`, or `BaseIOSchema`.","Use when asking about multi-agent orchestration or LLM-provider wiring in an atomic-agents project.","Use when needing guidance on project structure, testing, or error handling within the framework.",[196,197,198,199],"User asks about Atomic Agents framework, specific components, or common tasks.","Skill identifies relevant sections within SKILL.md or linked reference files.","Skill provides concise explanations, code snippets, and directs users to deeper documentation or specialized skills.","User follows guidance to understand and implement Atomic Agents components.",{"codeQuality":201,"collectedAt":203,"documentation":204,"maintenance":207,"security":213,"testCoverage":216},{"hasLockfile":202},true,1778683348878,{"descriptionLength":205,"readmeSize":206},343,20431,{"closedIssues90d":208,"forks":209,"hasChangelog":202,"openIssues90d":210,"pushedAt":211,"stars":212},7,506,6,1777460217000,5909,{"hasNpmPackage":214,"license":215,"smitheryVerified":214},false,"MIT",{"hasCi":202,"hasTests":202},{"updatedAt":218},1778683372619,{"basePath":220,"githubOwner":221,"githubRepo":222,"locale":18,"slug":185,"type":223},"claude-plugin/atomic-agents/skills/framework","BrainBlend-AI","atomic-agents","skill",{"_creationTime":225,"_id":226,"community":227,"display":228,"identity":231,"parentExtension":234,"providers":267,"relations":276,"tags":277,"workflow":278},1778683220959.3245,"k17bm61p7zr993vt7thb45838h86mrjy",{"reviewCount":8},{"description":229,"installMethods":230,"name":222,"sourceUrl":14},"Skills plus explorer and reviewer subagents for building, scaffolding, understanding, and auditing applications with the Atomic Agents Python framework. Includes the umbrella `framework` skill, action-oriented `create-atomic-schema` / `create-atomic-agent` / `create-atomic-tool` / `create-atomic-context-provider` skills, the `new-app` scaffolder, progressive-disclosure reference material for prompts, orchestration, memory, hooks, providers, project structure, and testing, and isolated-context subagents for codebase mapping and code review.",{"claudeCode":222},{"basePath":232,"githubOwner":221,"githubRepo":222,"locale":18,"slug":222,"type":233},"claude-plugin/atomic-agents","plugin",{"_creationTime":235,"_id":236,"community":237,"display":238,"identity":242,"providers":245,"relations":260,"tags":262,"workflow":263},1778683220959.3242,"k173812k7d1b2wh2bze2r2cdjn86mzva",{"reviewCount":8},{"description":239,"installMethods":240,"name":241,"sourceUrl":14},"Official plugins for the Atomic Agents framework - a lightweight, modular system for building AI agents with Pydantic and Instructor",{"claudeCode":12},"Atomic Agents",{"basePath":243,"githubOwner":221,"githubRepo":222,"locale":18,"slug":222,"type":244},"","marketplace",{"evaluate":246,"extract":253},{"promptVersionExtension":247,"promptVersionScoring":177,"score":248,"tags":249,"targetMarket":188,"tier":189},"3.1.0",95,[250,183,251,252,184,185],"ai-agents","pydantic","instructor",{"commitSha":254,"license":215,"marketplace":255,"plugin":258},"HEAD",{"name":256,"pluginCount":257},"brainblend-plugins",1,{"mcpCount":8,"provider":259,"skillCount":8},"classify",{"repoId":261},"kd7038dvhwk39adrnvedmx8x3s86mqpq",[250,185,252,183,251,184],{"evaluatedAt":264,"extractAt":265,"updatedAt":266},1778683239491,1778683220959,1778683666542,{"evaluate":268,"extract":274},{"promptVersionExtension":176,"promptVersionScoring":177,"score":269,"tags":270,"targetMarket":188,"tier":189},98,[184,186,185,271,272,273],"code-generation","development-tools","llm-application-development",{"commitSha":254,"license":215,"plugin":275},{"mcpCount":8,"provider":259,"skillCount":210},{"parentExtensionId":236,"repoId":261},[186,271,272,185,273,184],{"evaluatedAt":279,"extractAt":265,"updatedAt":280},1778683257368,1778683666777,{"evaluate":282,"extract":284},{"promptVersionExtension":176,"promptVersionScoring":177,"score":180,"tags":283,"targetMarket":188,"tier":189},[183,184,185,186,187],{"commitSha":254,"license":215},{"parentExtensionId":226,"repoId":261},{"_creationTime":287,"_id":261,"identity":288,"providers":289,"workflow":478},1778683214161.1255,{"githubOwner":221,"githubRepo":222,"sourceUrl":14},{"classify":290,"discover":465,"github":468},{"commitSha":254,"extensions":291},[292,305,330,339,347,355,363,371,398,406,431,440,449,458],{"basePath":243,"description":239,"displayName":256,"installMethods":293,"rationale":294,"selectedPaths":295,"source":304,"sourceLanguage":18,"type":244},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[296,299,301],{"path":297,"priority":298},".claude-plugin/marketplace.json","mandatory",{"path":300,"priority":298},"README.md",{"path":302,"priority":303},"LICENSE","high","rule",{"basePath":232,"description":229,"displayName":222,"installMethods":306,"license":215,"rationale":307,"selectedPaths":308,"source":304,"sourceLanguage":18,"type":233},{"claudeCode":222},"plugin manifest at claude-plugin/atomic-agents/.claude-plugin/plugin.json",[309,311,312,313,316,318,320,322,324,326,328],{"path":310,"priority":298},".claude-plugin/plugin.json",{"path":300,"priority":298},{"path":302,"priority":303},{"path":314,"priority":315},"skills/create-atomic-agent/SKILL.md","medium",{"path":317,"priority":315},"skills/create-atomic-context-provider/SKILL.md",{"path":319,"priority":315},"skills/create-atomic-schema/SKILL.md",{"path":321,"priority":315},"skills/create-atomic-tool/SKILL.md",{"path":323,"priority":315},"skills/framework/SKILL.md",{"path":325,"priority":315},"skills/new-app/SKILL.md",{"path":327,"priority":303},"agents/atomic-explorer.md",{"path":329,"priority":303},"agents/atomic-reviewer.md",{"basePath":331,"description":332,"displayName":333,"installMethods":334,"rationale":335,"selectedPaths":336,"source":304,"sourceLanguage":18,"type":223},".claude/skills/release","Release a new version of atomic-agents to PyPI and GitHub. Use when the user asks to \"release\", \"publish\", \"deploy\", or \"bump version\" for atomic-agents.","release",{"claudeCode":12},"SKILL.md frontmatter at .claude/skills/release/SKILL.md",[337],{"path":338,"priority":298},"SKILL.md",{"basePath":340,"description":341,"displayName":342,"installMethods":343,"rationale":344,"selectedPaths":345,"source":304,"sourceLanguage":18,"type":223},"claude-plugin/atomic-agents/skills/create-atomic-agent","Build and wire an `AtomicAgent[InSchema, OutSchema]` — schemas, `AgentConfig`, `SystemPromptGenerator`, provider client, history, hooks, optional context providers. Use when the user asks to \"create an agent\", \"add another agent\", \"build an `AtomicAgent`\", \"wire up an agent\", \"make a planner/router/extractor agent\", or runs `/atomic-agents:create-atomic-agent`.","create-atomic-agent",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-agent/SKILL.md",[346],{"path":338,"priority":298},{"basePath":348,"description":349,"displayName":350,"installMethods":351,"rationale":352,"selectedPaths":353,"source":304,"sourceLanguage":18,"type":223},"claude-plugin/atomic-agents/skills/create-atomic-context-provider","Build a `BaseDynamicContextProvider` that injects a named, titled block into an agent's system prompt at every `run()` — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to \"add a context provider\", \"inject X into the prompt\", \"give the agent dynamic context\", \"wire up RAG\", \"make a `BaseDynamicContextProvider`\", or runs `/atomic-agents:create-atomic-context-provider`.","create-atomic-context-provider",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-context-provider/SKILL.md",[354],{"path":338,"priority":298},{"basePath":356,"description":357,"displayName":358,"installMethods":359,"rationale":360,"selectedPaths":361,"source":304,"sourceLanguage":18,"type":223},"claude-plugin/atomic-agents/skills/create-atomic-schema","Design and write a `BaseIOSchema` input/output pair for an Atomic Agents agent or tool — docstrings, field descriptions, validators, error variants. Use when the user asks to \"create a schema\", \"design the input/output schema\", \"define an `IOSchema`\", \"write a `BaseIOSchema`\", \"model the agent's output\", or runs `/atomic-agents:create-atomic-schema`.","create-atomic-schema",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-schema/SKILL.md",[362],{"path":338,"priority":298},{"basePath":364,"description":365,"displayName":366,"installMethods":367,"rationale":368,"selectedPaths":369,"source":304,"sourceLanguage":18,"type":223},"claude-plugin/atomic-agents/skills/create-atomic-tool","Build a `BaseTool[InSchema, OutSchema]` subclass — input/output schemas, `BaseToolConfig`, `run()` (and optional `run_async()`), env-driven secrets, typed failure outputs. Use when the user asks to \"add a tool\", \"create a tool\", \"wrap an API as a tool\", \"build a `BaseTool`\", \"make a calculator/search/weather tool\", or runs `/atomic-agents:create-atomic-tool`.","create-atomic-tool",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-tool/SKILL.md",[370],{"path":338,"priority":298},{"basePath":220,"description":10,"displayName":185,"installMethods":372,"rationale":373,"selectedPaths":374,"source":304,"sourceLanguage":18,"type":223},{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/framework/SKILL.md",[375,376,378,380,382,384,386,388,390,392,394,396],{"path":338,"priority":298},{"path":377,"priority":315},"references/agents.md",{"path":379,"priority":315},"references/context-providers.md",{"path":381,"priority":315},"references/hooks.md",{"path":383,"priority":315},"references/memory.md",{"path":385,"priority":315},"references/orchestration.md",{"path":387,"priority":315},"references/project-structure.md",{"path":389,"priority":315},"references/prompts.md",{"path":391,"priority":315},"references/providers.md",{"path":393,"priority":315},"references/schemas.md",{"path":395,"priority":315},"references/testing.md",{"path":397,"priority":315},"references/tools.md",{"basePath":399,"description":400,"displayName":401,"installMethods":402,"rationale":403,"selectedPaths":404,"source":304,"sourceLanguage":18,"type":223},"claude-plugin/atomic-agents/skills/new-app","Scaffold a new Atomic Agents project from scratch — create the directory, `pyproject.toml`, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says \"scaffold\" / \"new project\" / \"start from zero\", or runs `/atomic-agents:new-app`.","new-app",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/new-app/SKILL.md",[405],{"path":338,"priority":298},{"basePath":407,"displayName":408,"installMethods":409,"rationale":410,"selectedPaths":411,"source":304,"sourceLanguage":18,"type":430},"atomic-examples/mcp-agent/example-mcp-server","example-mcp-server",{"pypi":408},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/mcp-agent/example-mcp-server/pyproject.toml",[412,414,415,417,420,422,424,426,428],{"path":413,"priority":298},"pyproject.toml",{"path":300,"priority":298},{"path":416,"priority":315},"example_mcp_server/server.py",{"path":418,"priority":419},"example_mcp_server/tools/__init__.py","low",{"path":421,"priority":419},"example_mcp_server/tools/add_numbers.py",{"path":423,"priority":419},"example_mcp_server/tools/batch_operations.py",{"path":425,"priority":419},"example_mcp_server/tools/divide_numbers.py",{"path":427,"priority":419},"example_mcp_server/tools/multiply_numbers.py",{"path":429,"priority":419},"example_mcp_server/tools/subtract_numbers.py","mcp",{"basePath":432,"displayName":433,"installMethods":434,"rationale":435,"selectedPaths":436,"source":304,"sourceLanguage":18,"type":430},"atomic-examples/progressive-disclosure/servers/data_server","pd-data-server",{"pypi":433},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/data_server/pyproject.toml",[437,438],{"path":413,"priority":298},{"path":439,"priority":315},"data_server/server.py",{"basePath":441,"displayName":442,"installMethods":443,"rationale":444,"selectedPaths":445,"source":304,"sourceLanguage":18,"type":430},"atomic-examples/progressive-disclosure/servers/math_server","pd-math-server",{"pypi":442},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/math_server/pyproject.toml",[446,447],{"path":413,"priority":298},{"path":448,"priority":315},"math_server/server.py",{"basePath":450,"displayName":451,"installMethods":452,"rationale":453,"selectedPaths":454,"source":304,"sourceLanguage":18,"type":430},"atomic-examples/progressive-disclosure/servers/text_server","pd-text-server",{"pypi":451},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/text_server/pyproject.toml",[455,456],{"path":413,"priority":298},{"path":457,"priority":315},"text_server/server.py",{"basePath":243,"displayName":222,"installMethods":459,"rationale":460,"selectedPaths":461,"source":304,"sourceLanguage":18,"type":430},{"pypi":222},"pyproject.toml with mcp/fastmcp dependency + scripts at pyproject.toml",[462,463,464],{"path":413,"priority":298},{"path":300,"priority":298},{"path":302,"priority":303},{"sources":466},[467],"manual",{"closedIssues90d":208,"description":469,"forks":209,"license":215,"openIssues90d":210,"pushedAt":211,"readmeSize":206,"stars":212,"topics":470},"Building AI agents, atomically",[471,472,473,474,475,476,477],"ai","artificial-intelligence","large-language-model","large-language-models","llms","openai","openai-api",{"classifiedAt":479,"discoverAt":480,"extractAt":481,"githubAt":481,"updatedAt":479},1778683220596,1778683214161,1778683218333,[186,187,185,183,184],{"evaluatedAt":218,"extractAt":265,"updatedAt":484},1778683669063,[],[487,518,546,568,596,625],{"_creationTime":488,"_id":489,"community":490,"display":491,"identity":497,"providers":502,"relations":511,"tags":514,"workflow":515},1778694269038.6682,"k1752cypc448mke749yjbkc65186mg6f",{"reviewCount":8},{"description":492,"installMethods":493,"name":495,"sourceUrl":496},"This skill should be used when the user asks to \"compress context\", \"summarize conversation history\", \"implement compaction\", \"reduce token usage\", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.",{"claudeCode":494},"muratcankoylan/Agent-Skills-for-Context-Engineering","Context Compression","https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",{"basePath":498,"githubOwner":499,"githubRepo":500,"locale":18,"slug":501,"type":223},"skills/context-compression","muratcankoylan","Agent-Skills-for-Context-Engineering","context-compression",{"evaluate":503,"extract":510},{"promptVersionExtension":176,"promptVersionScoring":177,"score":504,"tags":505,"targetMarket":188,"tier":189},100,[506,183,186,507,508,509],"context-engineering","summarization","compression","evaluation",{"commitSha":254,"license":215},{"parentExtensionId":512,"repoId":513},"k1754dy3wbsv2a5gr1a983zzs586njca","kd7f12maf5nxmx5xttjx7scfnx86m1tv",[186,508,506,509,183,507],{"evaluatedAt":516,"extractAt":517,"updatedAt":516},1778694410149,1778694269038,{"_creationTime":519,"_id":520,"community":521,"display":522,"identity":528,"providers":532,"relations":539,"tags":542,"workflow":543},1778699234184.6143,"k17cnx0m6a27fw52yvt4zsbsxh86nd1c",{"reviewCount":8},{"description":523,"installMethods":524,"name":526,"sourceUrl":527},"Configure popular MCP servers for enhanced agent capabilities",{"claudeCode":525},"Yeachan-Heo/oh-my-claudecode","mcp-setup","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":529,"githubOwner":530,"githubRepo":531,"locale":18,"slug":526,"type":223},"skills/mcp-setup","Yeachan-Heo","oh-my-claudecode",{"evaluate":533,"extract":538},{"promptVersionExtension":176,"promptVersionScoring":177,"score":504,"tags":534,"targetMarket":188,"tier":189},[430,535,536,186,537],"configuration","cli","tooling",{"commitSha":254},{"parentExtensionId":540,"repoId":541},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[186,536,535,430,537],{"evaluatedAt":544,"extractAt":545,"updatedAt":544},1778699492025,1778699234184,{"_creationTime":547,"_id":548,"community":549,"display":550,"identity":554,"providers":556,"relations":564,"tags":565,"workflow":566},1778699234184.6133,"k170q6m14w6ah5ygc0jr5sa54986mpx7",{"reviewCount":8},{"description":551,"installMethods":552,"name":553,"sourceUrl":527},"Deep codebase initialization with hierarchical AGENTS.md documentation",{"claudeCode":525},"deepinit",{"basePath":555,"githubOwner":530,"githubRepo":531,"locale":18,"slug":553,"type":223},"skills/deepinit",{"evaluate":557,"extract":563},{"promptVersionExtension":176,"promptVersionScoring":177,"score":504,"tags":558,"targetMarket":188,"tier":189},[559,560,186,561,562],"documentation","codebase","typescript","javascript",{"commitSha":254},{"parentExtensionId":540,"repoId":541},[186,560,559,562,561],{"evaluatedAt":567,"extractAt":545,"updatedAt":567},1778699437749,{"_creationTime":569,"_id":570,"community":571,"display":572,"identity":578,"providers":582,"relations":590,"tags":592,"workflow":593},1778696691708.297,"k174kx68t1r1znb9ws0ndvkpt586nx68",{"reviewCount":8},{"description":573,"installMethods":574,"name":576,"sourceUrl":577},"Agent skill for worker-specialist - invoke with $agent-worker-specialist",{"claudeCode":575},"ruvnet/ruflo","agent-worker-specialist","https://github.com/ruvnet/ruflo",{"basePath":579,"githubOwner":580,"githubRepo":581,"locale":18,"slug":576,"type":223},".agents/skills/agent-worker-specialist","ruvnet","ruflo",{"evaluate":583,"extract":589},{"promptVersionExtension":176,"promptVersionScoring":177,"score":504,"tags":584,"targetMarket":188,"tier":189},[186,585,586,587,588],"orchestration","task-execution","coordination","progress-reporting",{"commitSha":254},{"repoId":591},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[186,587,585,588,586],{"evaluatedAt":594,"extractAt":595,"updatedAt":594},1778698724168,1778696691708,{"_creationTime":597,"_id":598,"community":599,"display":600,"identity":606,"providers":610,"relations":618,"tags":621,"workflow":622},1778696595410.5657,"k17bk9m02r7jkbzzqapbzfvq8h86m6qn",{"reviewCount":8},{"description":601,"installMethods":602,"name":604,"sourceUrl":605},"Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.",{"claudeCode":603},"rohitg00/pro-workflow","orchestrate","https://github.com/rohitg00/pro-workflow",{"basePath":607,"githubOwner":608,"githubRepo":609,"locale":18,"slug":604,"type":223},"skills/orchestrate","rohitg00","pro-workflow",{"evaluate":611,"extract":617},{"promptVersionExtension":176,"promptVersionScoring":177,"score":504,"tags":612,"targetMarket":188,"tier":189},[613,186,614,615,616],"llm-ops","workflow","memory","knowledge-management",{"commitSha":254},{"parentExtensionId":619,"repoId":620},"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv","kd7am4e918eq98hrd9s31jm4vs86nn0b",[186,616,613,615,614],{"evaluatedAt":623,"extractAt":624,"updatedAt":623},1778696881233,1778696595410,{"_creationTime":626,"_id":627,"community":628,"display":629,"identity":635,"providers":639,"relations":645,"tags":648,"workflow":649},1778683790179.7805,"k175gdavh4ddb920rs1v4jc92586n0ke",{"reviewCount":8},{"description":630,"installMethods":631,"name":633,"sourceUrl":634},"Initializes an optional repo-local agent collaboration preference file at `.ai/swe.json` by running a short interview or a zero-question quick mode. Use when a user says `initialize agent settings for this repo`, `set up my local agent prefs here`, `run quick init for this project`, or `create .ai/swe.json for how I like to work`. Do NOT use for `npm init`, project scaffolding, dependency installation, or environment bootstrap.",{"claudeCode":632},"ckorhonen/swe-skills","init","https://github.com/ckorhonen/swe-skills",{"basePath":636,"githubOwner":637,"githubRepo":638,"locale":18,"slug":633,"type":223},"skills/init","ckorhonen","swe-skills",{"evaluate":640,"extract":644},{"promptVersionExtension":176,"promptVersionScoring":177,"score":504,"tags":641,"targetMarket":188,"tier":189},[535,642,186,643,187],"preferences","local",{"commitSha":254},{"parentExtensionId":646,"repoId":647},"k17d2yq229g61qvea0x8t60w1h86mgr8","kd7b5kvzw3q7dgvym5bdx3m53986mann",[186,535,187,643,642],{"evaluatedAt":650,"extractAt":651,"updatedAt":650},1778683991127,1778683790179]