[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-BrainBlend-AI-create-atomic-agent-en":3,"guides-for-BrainBlend-AI-create-atomic-agent":508,"similar-k1707nd2dxdw44brdnq5djf38d86mksy-en":509},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":242,"isFallback":237,"parentExtension":248,"providers":305,"relations":309,"repo":310,"tags":505,"workflow":506},1778683220959.325,"k1707nd2dxdw44brdnq5djf38d86mksy",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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`.",{"claudeCode":12},"BrainBlend-AI/atomic-agents","Create Atomic Agent","https://github.com/BrainBlend-AI/atomic-agents",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":240},1778683299108.9292,"kn7am7f78042m10r6s7ckj0qzh86m2b5","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":216,"tier":217,"useCases":218},[21,26,29,32,36,39,43,46,50,54,58,61,64,68,72,76,79,82,85,88,92,96,99,103,106,109,112,115,118,121,125,128,132,136,140,143,146,149,153,156,159,162,165,168,171,175,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of building and wiring `AtomicAgent` components and provides specific user intents and a CLI command for when to use it.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a structured approach to agent creation, defining schemas, system prompts, and provider clients, which goes beyond default LLM behavior and provides significant value over manual implementation.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a complete lifecycle for agent creation, from clarification to implementation and running, including provider-specific configurations and error handling guidance.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill is focused on the specific task of creating and wiring an `AtomicAgent`, with clear instructions and delegation to related skills for specific sub-tasks like schema creation or context providers.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's functionality, clearly outlining what it does and when to use it, including specific trigger phrases and a CLI command.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The description clearly identifies the artifact (`AtomicAgent`) and the user intent ('create an agent', 'build an `AtomicAgent`') and specifies trigger phrases and boundaries.",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and provides clear trigger phrases within the recommended character limit.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The skill body is well-structured, uses progressive disclosure for deeper material, and stays within a reasonable length, delegating extensive details to reference files.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","The skill appropriately links to external reference files for in-depth material on agents, providers, prompts, and memory, adhering to progressive disclosure principles.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","The skill's primary function is agent creation, not deep exploration or code review, so `context: fork` is not applicable.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","The README provides multiple runnable quickstart and complete examples covering various aspects of agent creation and usage, demonstrating concrete inputs and expected outputs.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The skill instruction addresses edge cases and limitations, such as provider-specific gotchas and common anti-patterns, with observable symptoms and recovery steps.",{"category":65,"check":66,"severity":56,"summary":67},"Code Execution","Tool Fallback","The skill does not appear to rely on external custom MCPs or tools that would require a fallback mechanism; it focuses on building agents within the Atomic Agents framework.",{"category":69,"check":70,"severity":24,"summary":71},"Safety","Halt on unexpected state","The skill's instructions detail how to handle pre-state conditions and potential failure modes, implicitly guiding the user to halt if unexpected states occur.",{"category":73,"check":74,"severity":24,"summary":75},"Portability","Cross-skill coupling","The skill is self-contained for agent creation and explicitly cross-references other skills (`create-atomic-schema`, `create-atomic-context-provider`) for related tasks, promoting standalone functionality.",{"category":40,"check":77,"severity":56,"summary":78},"Scoped tools","This skill primarily provides instructions and code generation, rather than exposing discrete tools that would be subject to scope evaluation.",{"category":47,"check":80,"severity":24,"summary":81},"Configuration & parameter reference","All relevant configurations, parameters, and provider-specific settings are detailed within the SKILL.md and referenced documentation, including default values and required environment variables.",{"category":33,"check":83,"severity":56,"summary":84},"Tool naming","This skill does not expose user-facing tools; its primary output is code and instructions.",{"category":33,"check":86,"severity":56,"summary":87},"Minimal I/O surface","As this skill is instructional and generates code rather than operating as a tool with defined input/output schemas, this check is not applicable.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","The project is licensed under the MIT License, as indicated by the LICENSE file and the README badge, which is a permissive open-source license.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","The last commit was on April 29, 2026, which is within the last 3 months, indicating active maintenance.",{"category":93,"check":97,"severity":24,"summary":98},"Dependency Management","The project uses pip and specifies dependencies, and the README mentions installing provider SDKs, suggesting a standard Python dependency management approach.",{"category":100,"check":101,"severity":24,"summary":102},"Security","Secret Management","The skill explicitly instructs users to read API keys from environment variables (e.g., `os.environ[\"OPENAI_API_KEY\"]`) and avoids hardcoding secrets in the source code.",{"category":100,"check":104,"severity":24,"summary":105},"Injection","The skill focuses on generating code and instructions based on user input, and does not appear to load or execute arbitrary third-party data as instructions.",{"category":100,"check":107,"severity":24,"summary":108},"Transitive Supply-Chain Grenades","The skill generates Python code and instructions; it does not fetch remote scripts or markdown to execute at runtime, mitigating transitive supply-chain risks.",{"category":100,"check":110,"severity":24,"summary":111},"Sandbox Isolation","The skill's output is Python code and instructions; it does not directly interact with the file system or perform operations outside of generating code snippets.",{"category":100,"check":113,"severity":24,"summary":114},"Sandbox escape primitives","The skill generates code and instructions, and there are no indications of detached-process spawns or deny-retry loops within the skill's logic.",{"category":100,"check":116,"severity":24,"summary":117},"Data Exfiltration","The skill instructs users to use environment variables for secrets and does not contain any logic to read or submit confidential data to third parties.",{"category":100,"check":119,"severity":24,"summary":120},"Hidden Text Tricks","The bundled content, including SKILL.md and README.md, appears to be free of hidden-steering tricks, control characters, or invisible Unicode characters.",{"category":122,"check":123,"severity":24,"summary":124},"Hooks","Opaque code execution","The skill generates standard Python code and does not employ obfuscation techniques like base64 encoding, eval, or runtime script fetching.",{"category":73,"check":126,"severity":24,"summary":127},"Structural Assumption","The skill suggests standard project structures like `\u003Cproject>/agents/\u003Cagent_name>.py` and mentions using environment variables, which are common and adaptable practices.",{"category":129,"check":130,"severity":24,"summary":131},"Trust","Issues Attention","With 6 issues opened and 7 closed in the last 90 days, the closure rate is high, indicating good maintainer engagement.",{"category":133,"check":134,"severity":24,"summary":135},"Version","Release Management","The project has a clear versioning signal through PyPI package versioning and GitHub release tags, and the `pushedAt` date indicates recent activity.",{"category":137,"check":138,"severity":24,"summary":139},"Execution","Validation","The generated Python code utilizes Pydantic for schema validation, ensuring that inputs and outputs conform to defined structures.",{"category":100,"check":141,"severity":24,"summary":142},"Unguarded Destructive Operations","The skill generates code for agent creation, which is not inherently destructive and does not involve operations like file deletion or system modification without user control.",{"category":65,"check":144,"severity":24,"summary":145},"Error Handling","The skill provides guidance on error handling, referencing hooks for parse errors and outlining common anti-patterns and provider-specific issues that lead to errors.",{"category":65,"check":147,"severity":56,"summary":148},"Logging","This skill's primary function is code generation and instruction; it does not perform destructive actions or outbound calls that would necessitate local audit logging.",{"category":150,"check":151,"severity":56,"summary":152},"Compliance","GDPR","The skill focuses on agent creation and does not process personal data; it instructs users to handle API keys via environment variables.",{"category":150,"check":154,"severity":24,"summary":155},"Target market","The skill is language-agnostic and provider-agnostic (supporting multiple LLM providers), with no regional or jurisdictional logic detected, making it globally applicable.",{"category":73,"check":157,"severity":24,"summary":158},"Runtime stability","The skill generates Python code compatible with standard Python environments and specifies dependencies through pip, ensuring cross-platform compatibility.",{"category":47,"check":160,"severity":24,"summary":161},"README","The README file is comprehensive, clearly states the project's purpose, and provides installation and usage instructions.",{"category":33,"check":163,"severity":56,"summary":164},"Tool surface size","This extension is a skill that generates code and instructions, rather than exposing multiple distinct tools.",{"category":40,"check":166,"severity":56,"summary":167},"Overlapping near-synonym tools","The skill itself does not expose tools, so there are no overlapping near-synonym tools to evaluate.",{"category":47,"check":169,"severity":24,"summary":170},"Phantom features","All features and capabilities described in the README and SKILL.md, such as agent creation, schema definition, and provider integration, are supported by the framework's implementation.",{"category":172,"check":173,"severity":24,"summary":174},"Install","Installation instruction","The README provides clear installation instructions using pip and includes runnable code examples for agent creation and usage.",{"category":176,"check":177,"severity":24,"summary":178},"Errors","Actionable error messages","The skill's documentation and examples guide users on how to interpret and address errors, particularly related to provider configurations and common anti-patterns.",{"category":137,"check":180,"severity":24,"summary":181},"Pinned dependencies","The project uses pip for dependency management, and the README indicates installation via pip, implying standard Python dependency resolution which can include pinning.",{"category":33,"check":183,"severity":56,"summary":184},"Dry-run preview","This skill generates code and instructions; it does not perform state-changing operations or outbound calls that would require a dry-run mode.",{"category":186,"check":187,"severity":56,"summary":188},"Protocol","Idempotent retry & timeouts","The skill itself does not make direct API calls; it generates code that will handle retries and timeouts via the underlying Instructor library and LLM provider.",{"category":150,"check":190,"severity":24,"summary":191},"Telemetry opt-in","The project's README and SKILL.md do not mention any telemetry collection; therefore, it is assumed to be either non-existent or opt-in by default.",1778683298988,"This skill, part of the Atomic Agents framework, provides instructions and code generation for building custom `AtomicAgent` instances. It guides users through defining schemas, system prompts, selecting LLM providers, and configuring agent behavior, with clear examples and documentation.",[195,196,197,198,199],"Build and wire `AtomicAgent` instances","Define input/output schemas using Pydantic","Configure LLM providers and models","Generate system prompts with background, steps, and output instructions","Integrate chat history and context providers",[201,202,203],"Authoring complex multi-agent orchestration logic (delegated to framework references).","Deep dives into LLM provider specifics beyond configuration needs.","Directly managing LLM API calls outside the agent instantiation process.","3.0.0","4.4.0","To streamline the creation and wiring of custom AI agents by providing a structured, code-generative approach that emphasizes modularity, predictability, and developer experience.","High quality across all checks, with a focus on clear documentation, practical utility, and adherence to best practices for agent development. No significant issues found.",98,"A well-documented and robust framework for building modular and predictable AI agents with strong developer experience.",[211,212,213,214,215],"agent-development","llm-framework","python","code-generation","pydantic","global","verified",[219,220,221,222],"When the user asks to 'create an agent' or 'build an `AtomicAgent`'.","When a user wants to 'add another agent' to an existing pipeline.","To 'wire up an agent' with specific schemas, prompts, and providers.","To 'make a planner/router/extractor agent' for specialized tasks.",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"security":236,"testCoverage":239},{"hasLockfile":225},true,1778683276726,{"descriptionLength":228,"readmeSize":229},363,20431,{"closedIssues90d":231,"forks":232,"hasChangelog":225,"openIssues90d":233,"pushedAt":234,"stars":235},7,506,6,1777460217000,5909,{"hasNpmPackage":237,"license":238,"smitheryVerified":237},false,"MIT",{"hasCi":225,"hasTests":225},{"updatedAt":241},1778683299108,{"basePath":243,"githubOwner":244,"githubRepo":245,"locale":18,"slug":246,"type":247},"claude-plugin/atomic-agents/skills/create-atomic-agent","BrainBlend-AI","atomic-agents","create-atomic-agent","skill",{"_creationTime":249,"_id":250,"community":251,"display":252,"identity":255,"parentExtension":258,"providers":292,"relations":300,"tags":301,"workflow":302},1778683220959.3245,"k17bm61p7zr993vt7thb45838h86mrjy",{"reviewCount":8},{"description":253,"installMethods":254,"name":245,"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":245},{"basePath":256,"githubOwner":244,"githubRepo":245,"locale":18,"slug":245,"type":257},"claude-plugin/atomic-agents","plugin",{"_creationTime":259,"_id":260,"community":261,"display":262,"identity":266,"providers":269,"relations":285,"tags":287,"workflow":288},1778683220959.3242,"k173812k7d1b2wh2bze2r2cdjn86mzva",{"reviewCount":8},{"description":263,"installMethods":264,"name":265,"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":267,"githubOwner":244,"githubRepo":245,"locale":18,"slug":245,"type":268},"","marketplace",{"evaluate":270,"extract":278},{"promptVersionExtension":271,"promptVersionScoring":205,"score":272,"tags":273,"targetMarket":216,"tier":217},"3.1.0",95,[274,275,215,276,213,277],"ai-agents","llm","instructor","framework",{"commitSha":279,"license":238,"marketplace":280,"plugin":283},"HEAD",{"name":281,"pluginCount":282},"brainblend-plugins",1,{"mcpCount":8,"provider":284,"skillCount":8},"classify",{"repoId":286},"kd7038dvhwk39adrnvedmx8x3s86mqpq",[274,277,276,275,215,213],{"evaluatedAt":289,"extractAt":290,"updatedAt":291},1778683239491,1778683220959,1778683666542,{"evaluate":293,"extract":298},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":294,"targetMarket":216,"tier":217},[213,295,277,214,296,297],"agent","development-tools","llm-application-development",{"commitSha":279,"license":238,"plugin":299},{"mcpCount":8,"provider":284,"skillCount":233},{"parentExtensionId":260,"repoId":286},[295,214,296,277,297,213],{"evaluatedAt":303,"extractAt":290,"updatedAt":304},1778683257368,1778683666777,{"evaluate":306,"extract":308},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":307,"targetMarket":216,"tier":217},[211,212,213,214,215],{"commitSha":279,"license":238},{"parentExtensionId":250,"repoId":286},{"_creationTime":311,"_id":286,"identity":312,"providers":313,"workflow":501},1778683214161.1255,{"githubOwner":244,"githubRepo":245,"sourceUrl":14},{"classify":314,"discover":488,"github":491},{"commitSha":279,"extensions":315},[316,329,354,363,368,376,384,392,421,429,454,463,472,481],{"basePath":267,"description":263,"displayName":281,"installMethods":317,"rationale":318,"selectedPaths":319,"source":328,"sourceLanguage":18,"type":268},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[320,323,325],{"path":321,"priority":322},".claude-plugin/marketplace.json","mandatory",{"path":324,"priority":322},"README.md",{"path":326,"priority":327},"LICENSE","high","rule",{"basePath":256,"description":253,"displayName":245,"installMethods":330,"license":238,"rationale":331,"selectedPaths":332,"source":328,"sourceLanguage":18,"type":257},{"claudeCode":245},"plugin manifest at claude-plugin/atomic-agents/.claude-plugin/plugin.json",[333,335,336,337,340,342,344,346,348,350,352],{"path":334,"priority":322},".claude-plugin/plugin.json",{"path":324,"priority":322},{"path":326,"priority":327},{"path":338,"priority":339},"skills/create-atomic-agent/SKILL.md","medium",{"path":341,"priority":339},"skills/create-atomic-context-provider/SKILL.md",{"path":343,"priority":339},"skills/create-atomic-schema/SKILL.md",{"path":345,"priority":339},"skills/create-atomic-tool/SKILL.md",{"path":347,"priority":339},"skills/framework/SKILL.md",{"path":349,"priority":339},"skills/new-app/SKILL.md",{"path":351,"priority":327},"agents/atomic-explorer.md",{"path":353,"priority":327},"agents/atomic-reviewer.md",{"basePath":355,"description":356,"displayName":357,"installMethods":358,"rationale":359,"selectedPaths":360,"source":328,"sourceLanguage":18,"type":247},".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",[361],{"path":362,"priority":322},"SKILL.md",{"basePath":243,"description":10,"displayName":246,"installMethods":364,"rationale":365,"selectedPaths":366,"source":328,"sourceLanguage":18,"type":247},{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-agent/SKILL.md",[367],{"path":362,"priority":322},{"basePath":369,"description":370,"displayName":371,"installMethods":372,"rationale":373,"selectedPaths":374,"source":328,"sourceLanguage":18,"type":247},"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",[375],{"path":362,"priority":322},{"basePath":377,"description":378,"displayName":379,"installMethods":380,"rationale":381,"selectedPaths":382,"source":328,"sourceLanguage":18,"type":247},"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",[383],{"path":362,"priority":322},{"basePath":385,"description":386,"displayName":387,"installMethods":388,"rationale":389,"selectedPaths":390,"source":328,"sourceLanguage":18,"type":247},"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",[391],{"path":362,"priority":322},{"basePath":393,"description":394,"displayName":277,"installMethods":395,"rationale":396,"selectedPaths":397,"source":328,"sourceLanguage":18,"type":247},"claude-plugin/atomic-agents/skills/framework","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},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/framework/SKILL.md",[398,399,401,403,405,407,409,411,413,415,417,419],{"path":362,"priority":322},{"path":400,"priority":339},"references/agents.md",{"path":402,"priority":339},"references/context-providers.md",{"path":404,"priority":339},"references/hooks.md",{"path":406,"priority":339},"references/memory.md",{"path":408,"priority":339},"references/orchestration.md",{"path":410,"priority":339},"references/project-structure.md",{"path":412,"priority":339},"references/prompts.md",{"path":414,"priority":339},"references/providers.md",{"path":416,"priority":339},"references/schemas.md",{"path":418,"priority":339},"references/testing.md",{"path":420,"priority":339},"references/tools.md",{"basePath":422,"description":423,"displayName":424,"installMethods":425,"rationale":426,"selectedPaths":427,"source":328,"sourceLanguage":18,"type":247},"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",[428],{"path":362,"priority":322},{"basePath":430,"displayName":431,"installMethods":432,"rationale":433,"selectedPaths":434,"source":328,"sourceLanguage":18,"type":453},"atomic-examples/mcp-agent/example-mcp-server","example-mcp-server",{"pypi":431},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/mcp-agent/example-mcp-server/pyproject.toml",[435,437,438,440,443,445,447,449,451],{"path":436,"priority":322},"pyproject.toml",{"path":324,"priority":322},{"path":439,"priority":339},"example_mcp_server/server.py",{"path":441,"priority":442},"example_mcp_server/tools/__init__.py","low",{"path":444,"priority":442},"example_mcp_server/tools/add_numbers.py",{"path":446,"priority":442},"example_mcp_server/tools/batch_operations.py",{"path":448,"priority":442},"example_mcp_server/tools/divide_numbers.py",{"path":450,"priority":442},"example_mcp_server/tools/multiply_numbers.py",{"path":452,"priority":442},"example_mcp_server/tools/subtract_numbers.py","mcp",{"basePath":455,"displayName":456,"installMethods":457,"rationale":458,"selectedPaths":459,"source":328,"sourceLanguage":18,"type":453},"atomic-examples/progressive-disclosure/servers/data_server","pd-data-server",{"pypi":456},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/data_server/pyproject.toml",[460,461],{"path":436,"priority":322},{"path":462,"priority":339},"data_server/server.py",{"basePath":464,"displayName":465,"installMethods":466,"rationale":467,"selectedPaths":468,"source":328,"sourceLanguage":18,"type":453},"atomic-examples/progressive-disclosure/servers/math_server","pd-math-server",{"pypi":465},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/math_server/pyproject.toml",[469,470],{"path":436,"priority":322},{"path":471,"priority":339},"math_server/server.py",{"basePath":473,"displayName":474,"installMethods":475,"rationale":476,"selectedPaths":477,"source":328,"sourceLanguage":18,"type":453},"atomic-examples/progressive-disclosure/servers/text_server","pd-text-server",{"pypi":474},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/text_server/pyproject.toml",[478,479],{"path":436,"priority":322},{"path":480,"priority":339},"text_server/server.py",{"basePath":267,"displayName":245,"installMethods":482,"rationale":483,"selectedPaths":484,"source":328,"sourceLanguage":18,"type":453},{"pypi":245},"pyproject.toml with mcp/fastmcp dependency + scripts at pyproject.toml",[485,486,487],{"path":436,"priority":322},{"path":324,"priority":322},{"path":326,"priority":327},{"sources":489},[490],"manual",{"closedIssues90d":231,"description":492,"forks":232,"license":238,"openIssues90d":233,"pushedAt":234,"readmeSize":229,"stars":235,"topics":493},"Building AI agents, atomically",[494,495,496,497,498,499,500],"ai","artificial-intelligence","large-language-model","large-language-models","llms","openai","openai-api",{"classifiedAt":502,"discoverAt":503,"extractAt":504,"githubAt":504,"updatedAt":502},1778683220596,1778683214161,1778683218333,[211,214,212,215,213],{"evaluatedAt":241,"extractAt":290,"updatedAt":507},1778683668203,[],[510,539,567,596,624,649],{"_creationTime":511,"_id":512,"community":513,"display":514,"identity":520,"providers":524,"relations":532,"tags":535,"workflow":536},1778675056600.2441,"k171y80q0m602mftp477895w5s86n54t",{"reviewCount":8},{"description":515,"installMethods":516,"name":518,"sourceUrl":519},"Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.",{"claudeCode":517},"alirezarezvani/claude-skills","extract","https://github.com/alirezarezvani/claude-skills",{"basePath":521,"githubOwner":522,"githubRepo":523,"locale":18,"slug":518,"type":247},"engineering-team/self-improving-agent/skills/extract","alirezarezvani","claude-skills",{"evaluate":525,"extract":531},{"promptVersionExtension":204,"promptVersionScoring":205,"score":526,"tags":527,"targetMarket":216,"tier":217},100,[528,211,214,529,530],"skill-extraction","knowledge-management","developer-tools",{"commitSha":279},{"parentExtensionId":533,"repoId":534},"k171b5pw3erme9qy3334r4gbv586mzhf","kd7ff9s1w43mfyy1n7hf87816186m6px",[211,214,530,529,528],{"evaluatedAt":537,"extractAt":538,"updatedAt":537},1778682824392,1778675056600,{"_creationTime":540,"_id":541,"community":542,"display":543,"identity":549,"providers":553,"relations":560,"tags":563,"workflow":564},1778694480889.9487,"k17eg219cke0p45yfhh8n2t37986mgm4",{"reviewCount":8},{"description":544,"installMethods":545,"name":547,"sourceUrl":548},"Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration",{"claudeCode":546},"NeoLabHQ/context-engineering-kit","create-command","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":550,"githubOwner":551,"githubRepo":552,"locale":18,"slug":547,"type":247},"plugins/customaize-agent/skills/create-command","NeoLabHQ","context-engineering-kit",{"evaluate":554,"extract":559},{"promptVersionExtension":204,"promptVersionScoring":205,"score":526,"tags":555,"targetMarket":216,"tier":217},[556,211,557,453,558],"command-creation","prompt-engineering","claude-code",{"commitSha":279},{"parentExtensionId":561,"repoId":562},"k173g0c46wghgz5j9gn02wfydn86mkh8","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[211,558,556,453,557],{"evaluatedAt":565,"extractAt":566,"updatedAt":565},1778694773368,1778694480890,{"_creationTime":568,"_id":569,"community":570,"display":571,"identity":577,"providers":582,"relations":589,"tags":592,"workflow":593},1778694269038.6707,"k178ghjhvwyw1pv6vxnaqcwgyx86m2g7",{"reviewCount":8},{"description":572,"installMethods":573,"name":575,"sourceUrl":576},"This skill should be used when the user asks to \"start an LLM project\", \"design batch pipeline\", \"evaluate task-model fit\", \"structure agent project\", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.",{"claudeCode":574},"muratcankoylan/Agent-Skills-for-Context-Engineering","Project Development","https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",{"basePath":578,"githubOwner":579,"githubRepo":580,"locale":18,"slug":581,"type":247},"skills/project-development","muratcankoylan","Agent-Skills-for-Context-Engineering","project-development",{"evaluate":583,"extract":588},{"promptVersionExtension":204,"promptVersionScoring":205,"score":526,"tags":584,"targetMarket":216,"tier":217},[275,585,586,211,587],"project-management","pipeline-architecture","batch-processing",{"commitSha":279,"license":238},{"parentExtensionId":590,"repoId":591},"k1754dy3wbsv2a5gr1a983zzs586njca","kd7f12maf5nxmx5xttjx7scfnx86m1tv",[211,587,275,586,585],{"evaluatedAt":594,"extractAt":595,"updatedAt":594},1778694576171,1778694269038,{"_creationTime":597,"_id":598,"community":599,"display":600,"identity":606,"providers":610,"relations":617,"tags":620,"workflow":621},1778692846401.1536,"k17f8b769y9swjcqb91vq74zy986n2wf",{"reviewCount":8},{"description":601,"installMethods":602,"name":604,"sourceUrl":605},"Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.",{"claudeCode":603},"mattpocock/skills","write-a-skill","https://github.com/mattpocock/skills",{"basePath":607,"githubOwner":608,"githubRepo":609,"locale":18,"slug":604,"type":247},"skills/productivity/write-a-skill","mattpocock","skills",{"evaluate":611,"extract":616},{"promptVersionExtension":204,"promptVersionScoring":205,"score":526,"tags":612,"targetMarket":216,"tier":217},[613,211,614,557,615],"skill-creation","documentation","productivity",{"commitSha":279},{"parentExtensionId":618,"repoId":619},"k171mc92f05dc4v6jzgf6bng7d86mr9t","kd70nm2vazehgqc4j28ve6cwv986mv1s",[211,614,615,557,613],{"evaluatedAt":622,"extractAt":623,"updatedAt":622},1778693512400,1778692846401,{"_creationTime":625,"_id":626,"community":627,"display":628,"identity":634,"providers":636,"relations":643,"tags":645,"workflow":646},1778695021936.555,"k1715rn9402s29yge55y9nt0x986n2tf",{"reviewCount":8},{"description":629,"installMethods":630,"name":632,"sourceUrl":633},"Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.",{"claudeCode":631},"openai/skills","cli-creator","https://github.com/openai/skills",{"basePath":635,"githubOwner":499,"githubRepo":609,"locale":18,"slug":632,"type":247},"skills/.curated/cli-creator",{"evaluate":637,"extract":642},{"promptVersionExtension":204,"promptVersionScoring":205,"score":526,"tags":638,"targetMarket":216,"tier":217},[639,214,530,640,641],"cli","codex","automation",{"commitSha":279},{"repoId":644},"kd75n2zj3yh472p25zffgycved86mnpx",[641,639,214,640,530],{"evaluatedAt":647,"extractAt":648,"updatedAt":647},1778695068759,1778695021936,{"_creationTime":650,"_id":651,"community":652,"display":653,"identity":659,"providers":663,"relations":673,"tags":675,"workflow":676},1778693511416.365,"k1758b69g51wttzw4r6epd3jrs86mtk8",{"reviewCount":8},{"description":654,"installMethods":655,"name":657,"sourceUrl":658},"Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches.",{"claudeCode":656},"mksglu/context-mode","context-mode-ops","https://github.com/mksglu/context-mode",{"basePath":660,"githubOwner":661,"githubRepo":662,"locale":18,"slug":657,"type":247},".claude/skills/context-mode-ops","mksglu","context-mode",{"evaluate":664,"extract":672},{"promptVersionExtension":204,"promptVersionScoring":205,"score":526,"tags":665,"targetMarket":216,"tier":217},[666,667,668,214,669,615,670,671],"context-window","llm-optimization","session-continuity","developer-tool","security","compliance",{"commitSha":279},{"repoId":674},"kd764b2fctbqg4b8j8y6xvmkvs86m29m",[214,671,666,669,667,615,670,668],{"evaluatedAt":677,"extractAt":678,"updatedAt":679},1778693567505,1778693511416,1778693817147]