[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-BrainBlend-AI-create-atomic-tool-en":3,"guides-for-BrainBlend-AI-create-atomic-tool":509,"similar-k17etfv7gy0r843nssf7yy7em586nxja-en":510},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":243,"isFallback":238,"parentExtension":249,"providers":306,"relations":310,"repo":311,"tags":506,"workflow":507},1778683220959.3257,"k17etfv7gy0r843nssf7yy7em586nxja",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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`.",{"claudeCode":12},"BrainBlend-AI/atomic-agents","Create Atomic Tool","https://github.com/BrainBlend-AI/atomic-agents",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":241},1778683348543.446,"kn745wxb6q1ej0j3n5yhq1xn8586mt63","en",{"checks":20,"evaluatedAt":185,"extensionSummary":186,"features":187,"nonGoals":193,"practices":197,"prerequisites":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":217,"tier":218,"useCases":219},[21,26,29,32,36,39,43,46,50,54,58,61,64,68,72,76,79,82,86,90,93,97,100,103,106,109,112,115,119,122,126,130,133,136,139,142,146,149,152,155,158,160,163,167,171,175,178,182],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of building `BaseTool` subclasses with specific requirements like input/output schemas, configurations, and error handling.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value by providing a structured, guided process for creating tools, going beyond basic prompt engineering and offering a framework for robust tool development.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a complete lifecycle for tool creation, from clarification to implementation and verification, making it suitable for production workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on the creation of `BaseTool` subclasses, adhering to a single responsibility principle.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description is concise, accurate, and clearly outlines the purpose and use cases of the skill.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The skill clearly defines its purpose: building `BaseTool` subclasses, and its usage triggers are specific and actionable.",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and triggers.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The skill body is well-structured and delegates deeper material to references, adhering to progressive disclosure principles.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","The skill defers deeper material like MCP interop and packaging to a separate reference file (`../framework/references/tools.md`).",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","The skill is focused on code generation and does not involve deep exploration or code review that would necessitate `context: fork`.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","The skill provides clear, runnable skeleton examples for both local computation and HTTP-backed tools, demonstrating usage and expected output.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The skill documents hard rules and anti-patterns, addressing potential failure modes like incorrect schema usage and missing configurations.",{"category":65,"check":66,"severity":56,"summary":67},"Code Execution","Tool Fallback","This skill is a code-generation tool and does not rely on external tools like MCP servers with fallbacks.",{"category":69,"check":70,"severity":24,"summary":71},"Safety","Halt on unexpected state","The skill instructs users to clarify inputs and schemas upfront, implicitly halting workflows if pre-states are unexpected or missing.",{"category":73,"check":74,"severity":24,"summary":75},"Portability","Cross-skill coupling","The skill is self-contained and focuses on tool creation; it does not implicitly rely on other skills and cross-references related documentation clearly.",{"category":33,"check":77,"severity":56,"summary":78},"Tool naming","This skill does not expose tools directly; it generates code for tools.",{"category":33,"check":80,"severity":56,"summary":81},"Minimal I/O surface","This skill's primary function is code generation, not direct tool execution with I/O surfaces.",{"category":83,"check":84,"severity":24,"summary":85},"License","License usability","The extension is licensed under the MIT license, as indicated by the LICENSE file.",{"category":87,"check":88,"severity":24,"summary":89},"Maintenance","Commit recency","The last commit was on April 29, 2026, which is recent.",{"category":87,"check":91,"severity":24,"summary":92},"Dependency Management","The project uses a lockfile (`uv.lock`) and declares dependencies, suggesting good dependency management practices.",{"category":94,"check":95,"severity":24,"summary":96},"Security","Secret Management","The skill itself does not handle secrets; it generates code that guides users to handle secrets via environment variables or tool configurations.",{"category":94,"check":98,"severity":24,"summary":99},"Injection","The skill generates code that uses Pydantic for schema validation, treating inputs as data and not instructions.",{"category":94,"check":101,"severity":24,"summary":102},"Transitive Supply-Chain Grenades","The skill generates code; it does not fetch or execute external content at runtime.",{"category":94,"check":104,"severity":24,"summary":105},"Sandbox Isolation","The skill is a code generator and does not interact with the file system or execute code outside of its defined scope.",{"category":94,"check":107,"severity":24,"summary":108},"Sandbox escape primitives","The skill does not execute code and therefore does not contain sandbox escape primitives.",{"category":94,"check":110,"severity":24,"summary":111},"Data Exfiltration","The skill generates code; it does not read or submit any data, confidential or otherwise.",{"category":94,"check":113,"severity":24,"summary":114},"Hidden Text Tricks","The bundled markdown files are free of hidden text tricks and contain only clean, printable ASCII and expected Unicode.",{"category":116,"check":117,"severity":24,"summary":118},"Hooks","Opaque code execution","The bundled scripts are plain, readable Python and do not involve obfuscation techniques like base64 encoding or runtime fetching.",{"category":73,"check":120,"severity":24,"summary":121},"Structural Assumption","The skill suggests standard file locations (`\u003Cproject>/tools/\u003Ctool_name>_tool.py`) but does not enforce them strictly, allowing flexibility.",{"category":123,"check":124,"severity":24,"summary":125},"Trust","Issues Attention","In the last 90 days, 6 issues were opened and 7 were closed, indicating active maintenance and responsiveness.",{"category":127,"check":128,"severity":24,"summary":129},"Versioning","Release Management","The project has a `LICENSE` file, indicating a clear licensing status. The repository also has a CHANGELOG.",{"category":65,"check":131,"severity":24,"summary":132},"Validation","The skill emphasizes Pydantic for schema validation in the generated code, ensuring robust input and output handling.",{"category":94,"check":134,"severity":24,"summary":135},"Unguarded Destructive Operations","The skill is a code generator and does not perform destructive operations itself.",{"category":65,"check":137,"severity":24,"summary":138},"Error Handling","The skill guides users to implement typed failure outputs and handle exceptions, promoting robust error handling in generated code.",{"category":65,"check":140,"severity":56,"summary":141},"Logging","This skill is a code generator and does not have runtime actions that require local audit logging.",{"category":143,"check":144,"severity":24,"summary":145},"Compliance","GDPR","The skill generates code that guides users to handle data appropriately, and does not operate on personal data itself.",{"category":143,"check":147,"severity":24,"summary":148},"Target market","The skill is a general Python tool creation framework and has no regional or jurisdictional restrictions.",{"category":73,"check":150,"severity":24,"summary":151},"Runtime stability","The skill generates Python code, which is highly portable across various operating systems and environments.",{"category":47,"check":153,"severity":24,"summary":154},"README","The README file is comprehensive, detailing the project's purpose, installation, examples, and core concepts.",{"category":33,"check":156,"severity":56,"summary":157},"Tool surface size","This skill is a single capability focused on generating tool code, not exposing multiple tools.",{"category":40,"check":159,"severity":56,"summary":78},"Overlapping near-synonym tools",{"category":47,"check":161,"severity":24,"summary":162},"Phantom features","All features described in the README and SKILL.md (tool creation, schema handling, configuration) are implemented within the framework's provided code examples and documentation.",{"category":164,"check":165,"severity":24,"summary":166},"Install","Installation instruction","The README provides clear installation instructions for the package and its dependencies, along with runnable code examples.",{"category":168,"check":169,"severity":24,"summary":170},"Errors","Actionable error messages","The skill guides users on how to implement typed failure outputs and handle errors in the generated code, promoting actionable error reporting.",{"category":172,"check":173,"severity":24,"summary":174},"Execution","Pinned dependencies","The project uses a lockfile (`uv.lock`) to pin dependencies, and Python scripts would typically include shebangs and interpreter declarations.",{"category":33,"check":176,"severity":56,"summary":177},"Dry-run preview","This skill generates code and does not perform state-changing operations itself.",{"category":179,"check":180,"severity":24,"summary":181},"Protocol","Idempotent retry & timeouts","The skill's generated code guides users to implement timeouts and structured error handling, encouraging idempotent operations where applicable.",{"category":143,"check":183,"severity":24,"summary":184},"Telemetry opt-in","The skill focuses on code generation and does not emit telemetry itself. The underlying framework encourages opt-in telemetry.",1778683348358,"This skill guides users through the process of creating Python `BaseTool` subclasses for AI agents. It covers defining input/output schemas, configurations, handling secrets, and implementing synchronous or asynchronous run methods, with a focus on typed failure outputs.",[188,189,190,191,192],"Builds `BaseTool` subclasses with typed schemas.","Supports synchronous (`run`) and asynchronous (`run_async`) methods.","Guides configuration of secrets via environment variables and `BaseToolConfig`.","Promotes typed failure outputs for robust error handling.","Provides skeleton implementations for local and HTTP-backed tools.",[194,195,196],"Creating agents or entire AI applications.","Managing the deployment or distribution of tools.","Handling general framework questions outside of tool creation.",[198,199,137],"Tool Development","Schema Design",[201,202,203],"Python 3.8+","Atomic Agents library installed","Pydantic installed","3.0.0","4.4.0","To provide a structured and guided process for developers to create custom tools for AI agents using the Atomic Agents framework.","Excellent documentation and code quality, with a clear focus on a single responsibility. Minor improvements could be made in the depth of examples for advanced error handling patterns.",99,"A high-quality skill for generating robust `BaseTool` subclasses with excellent documentation and examples.",[211,212,213,214,215,216],"python","code-generation","developer-tools","agent-framework","pydantic","instructor","global","verified",[220,221,222,223],"When a user asks to add a new tool to their AI agent.","When a user needs to wrap an external API as a tool.","When building utility tools like calculators, search functions, or database query tools.","When creating custom `BaseTool` implementations within the Atomic Agents framework.",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"security":237,"testCoverage":240},{"hasLockfile":226},true,1778683330120,{"descriptionLength":229,"readmeSize":230},361,20431,{"closedIssues90d":232,"forks":233,"hasChangelog":226,"openIssues90d":234,"pushedAt":235,"stars":236},7,506,6,1777460217000,5909,{"hasNpmPackage":238,"license":239,"smitheryVerified":238},false,"MIT",{"hasCi":226,"hasTests":226},{"updatedAt":242},1778683348543,{"basePath":244,"githubOwner":245,"githubRepo":246,"locale":18,"slug":247,"type":248},"claude-plugin/atomic-agents/skills/create-atomic-tool","BrainBlend-AI","atomic-agents","create-atomic-tool","skill",{"_creationTime":250,"_id":251,"community":252,"display":253,"identity":256,"parentExtension":259,"providers":292,"relations":301,"tags":302,"workflow":303},1778683220959.3245,"k17bm61p7zr993vt7thb45838h86mrjy",{"reviewCount":8},{"description":254,"installMethods":255,"name":246,"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":246},{"basePath":257,"githubOwner":245,"githubRepo":246,"locale":18,"slug":246,"type":258},"claude-plugin/atomic-agents","plugin",{"_creationTime":260,"_id":261,"community":262,"display":263,"identity":267,"providers":270,"relations":285,"tags":287,"workflow":288},1778683220959.3242,"k173812k7d1b2wh2bze2r2cdjn86mzva",{"reviewCount":8},{"description":264,"installMethods":265,"name":266,"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":268,"githubOwner":245,"githubRepo":246,"locale":18,"slug":246,"type":269},"","marketplace",{"evaluate":271,"extract":278},{"promptVersionExtension":272,"promptVersionScoring":205,"score":273,"tags":274,"targetMarket":217,"tier":218},"3.1.0",95,[275,276,215,216,211,277],"ai-agents","llm","framework",{"commitSha":279,"license":239,"marketplace":280,"plugin":283},"HEAD",{"name":281,"pluginCount":282},"brainblend-plugins",1,{"mcpCount":8,"provider":284,"skillCount":8},"classify",{"repoId":286},"kd7038dvhwk39adrnvedmx8x3s86mqpq",[275,277,216,276,215,211],{"evaluatedAt":289,"extractAt":290,"updatedAt":291},1778683239491,1778683220959,1778683666542,{"evaluate":293,"extract":299},{"promptVersionExtension":204,"promptVersionScoring":205,"score":294,"tags":295,"targetMarket":217,"tier":218},98,[211,296,277,212,297,298],"agent","development-tools","llm-application-development",{"commitSha":279,"license":239,"plugin":300},{"mcpCount":8,"provider":284,"skillCount":234},{"parentExtensionId":261,"repoId":286},[296,212,297,277,298,211],{"evaluatedAt":304,"extractAt":290,"updatedAt":305},1778683257368,1778683666777,{"evaluate":307,"extract":309},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":308,"targetMarket":217,"tier":218},[211,212,213,214,215,216],{"commitSha":279,"license":239},{"parentExtensionId":251,"repoId":286},{"_creationTime":312,"_id":286,"identity":313,"providers":314,"workflow":502},1778683214161.1255,{"githubOwner":245,"githubRepo":246,"sourceUrl":14},{"classify":315,"discover":489,"github":492},{"commitSha":279,"extensions":316},[317,330,355,364,372,380,388,393,422,430,455,464,473,482],{"basePath":268,"description":264,"displayName":281,"installMethods":318,"rationale":319,"selectedPaths":320,"source":329,"sourceLanguage":18,"type":269},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[321,324,326],{"path":322,"priority":323},".claude-plugin/marketplace.json","mandatory",{"path":325,"priority":323},"README.md",{"path":327,"priority":328},"LICENSE","high","rule",{"basePath":257,"description":254,"displayName":246,"installMethods":331,"license":239,"rationale":332,"selectedPaths":333,"source":329,"sourceLanguage":18,"type":258},{"claudeCode":246},"plugin manifest at claude-plugin/atomic-agents/.claude-plugin/plugin.json",[334,336,337,338,341,343,345,347,349,351,353],{"path":335,"priority":323},".claude-plugin/plugin.json",{"path":325,"priority":323},{"path":327,"priority":328},{"path":339,"priority":340},"skills/create-atomic-agent/SKILL.md","medium",{"path":342,"priority":340},"skills/create-atomic-context-provider/SKILL.md",{"path":344,"priority":340},"skills/create-atomic-schema/SKILL.md",{"path":346,"priority":340},"skills/create-atomic-tool/SKILL.md",{"path":348,"priority":340},"skills/framework/SKILL.md",{"path":350,"priority":340},"skills/new-app/SKILL.md",{"path":352,"priority":328},"agents/atomic-explorer.md",{"path":354,"priority":328},"agents/atomic-reviewer.md",{"basePath":356,"description":357,"displayName":358,"installMethods":359,"rationale":360,"selectedPaths":361,"source":329,"sourceLanguage":18,"type":248},".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",[362],{"path":363,"priority":323},"SKILL.md",{"basePath":365,"description":366,"displayName":367,"installMethods":368,"rationale":369,"selectedPaths":370,"source":329,"sourceLanguage":18,"type":248},"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",[371],{"path":363,"priority":323},{"basePath":373,"description":374,"displayName":375,"installMethods":376,"rationale":377,"selectedPaths":378,"source":329,"sourceLanguage":18,"type":248},"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",[379],{"path":363,"priority":323},{"basePath":381,"description":382,"displayName":383,"installMethods":384,"rationale":385,"selectedPaths":386,"source":329,"sourceLanguage":18,"type":248},"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",[387],{"path":363,"priority":323},{"basePath":244,"description":10,"displayName":247,"installMethods":389,"rationale":390,"selectedPaths":391,"source":329,"sourceLanguage":18,"type":248},{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-tool/SKILL.md",[392],{"path":363,"priority":323},{"basePath":394,"description":395,"displayName":277,"installMethods":396,"rationale":397,"selectedPaths":398,"source":329,"sourceLanguage":18,"type":248},"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",[399,400,402,404,406,408,410,412,414,416,418,420],{"path":363,"priority":323},{"path":401,"priority":340},"references/agents.md",{"path":403,"priority":340},"references/context-providers.md",{"path":405,"priority":340},"references/hooks.md",{"path":407,"priority":340},"references/memory.md",{"path":409,"priority":340},"references/orchestration.md",{"path":411,"priority":340},"references/project-structure.md",{"path":413,"priority":340},"references/prompts.md",{"path":415,"priority":340},"references/providers.md",{"path":417,"priority":340},"references/schemas.md",{"path":419,"priority":340},"references/testing.md",{"path":421,"priority":340},"references/tools.md",{"basePath":423,"description":424,"displayName":425,"installMethods":426,"rationale":427,"selectedPaths":428,"source":329,"sourceLanguage":18,"type":248},"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",[429],{"path":363,"priority":323},{"basePath":431,"displayName":432,"installMethods":433,"rationale":434,"selectedPaths":435,"source":329,"sourceLanguage":18,"type":454},"atomic-examples/mcp-agent/example-mcp-server","example-mcp-server",{"pypi":432},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/mcp-agent/example-mcp-server/pyproject.toml",[436,438,439,441,444,446,448,450,452],{"path":437,"priority":323},"pyproject.toml",{"path":325,"priority":323},{"path":440,"priority":340},"example_mcp_server/server.py",{"path":442,"priority":443},"example_mcp_server/tools/__init__.py","low",{"path":445,"priority":443},"example_mcp_server/tools/add_numbers.py",{"path":447,"priority":443},"example_mcp_server/tools/batch_operations.py",{"path":449,"priority":443},"example_mcp_server/tools/divide_numbers.py",{"path":451,"priority":443},"example_mcp_server/tools/multiply_numbers.py",{"path":453,"priority":443},"example_mcp_server/tools/subtract_numbers.py","mcp",{"basePath":456,"displayName":457,"installMethods":458,"rationale":459,"selectedPaths":460,"source":329,"sourceLanguage":18,"type":454},"atomic-examples/progressive-disclosure/servers/data_server","pd-data-server",{"pypi":457},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/data_server/pyproject.toml",[461,462],{"path":437,"priority":323},{"path":463,"priority":340},"data_server/server.py",{"basePath":465,"displayName":466,"installMethods":467,"rationale":468,"selectedPaths":469,"source":329,"sourceLanguage":18,"type":454},"atomic-examples/progressive-disclosure/servers/math_server","pd-math-server",{"pypi":466},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/math_server/pyproject.toml",[470,471],{"path":437,"priority":323},{"path":472,"priority":340},"math_server/server.py",{"basePath":474,"displayName":475,"installMethods":476,"rationale":477,"selectedPaths":478,"source":329,"sourceLanguage":18,"type":454},"atomic-examples/progressive-disclosure/servers/text_server","pd-text-server",{"pypi":475},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/text_server/pyproject.toml",[479,480],{"path":437,"priority":323},{"path":481,"priority":340},"text_server/server.py",{"basePath":268,"displayName":246,"installMethods":483,"rationale":484,"selectedPaths":485,"source":329,"sourceLanguage":18,"type":454},{"pypi":246},"pyproject.toml with mcp/fastmcp dependency + scripts at pyproject.toml",[486,487,488],{"path":437,"priority":323},{"path":325,"priority":323},{"path":327,"priority":328},{"sources":490},[491],"manual",{"closedIssues90d":232,"description":493,"forks":233,"license":239,"openIssues90d":234,"pushedAt":235,"readmeSize":230,"stars":236,"topics":494},"Building AI agents, atomically",[495,496,497,498,499,500,501],"ai","artificial-intelligence","large-language-model","large-language-models","llms","openai","openai-api",{"classifiedAt":503,"discoverAt":504,"extractAt":505,"githubAt":505,"updatedAt":503},1778683220596,1778683214161,1778683218333,[214,212,213,216,215,211],{"evaluatedAt":242,"extractAt":290,"updatedAt":508},1778683668676,[],[511,538,570,588,613,645],{"_creationTime":512,"_id":513,"community":514,"display":515,"identity":521,"providers":524,"relations":532,"tags":534,"workflow":535},1778695021936.555,"k1715rn9402s29yge55y9nt0x986n2tf",{"reviewCount":8},{"description":516,"installMethods":517,"name":519,"sourceUrl":520},"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":518},"openai/skills","cli-creator","https://github.com/openai/skills",{"basePath":522,"githubOwner":500,"githubRepo":523,"locale":18,"slug":519,"type":248},"skills/.curated/cli-creator","skills",{"evaluate":525,"extract":531},{"promptVersionExtension":204,"promptVersionScoring":205,"score":526,"tags":527,"targetMarket":217,"tier":218},100,[528,212,213,529,530],"cli","codex","automation",{"commitSha":279},{"repoId":533},"kd75n2zj3yh472p25zffgycved86mnpx",[530,528,212,529,213],{"evaluatedAt":536,"extractAt":537,"updatedAt":536},1778695068759,1778695021936,{"_creationTime":539,"_id":540,"community":541,"display":542,"identity":548,"providers":552,"relations":563,"tags":566,"workflow":567},1778695116697.1924,"k1714hg6p3104jz49mqr6yn47s86nz7n",{"reviewCount":8},{"description":543,"installMethods":544,"name":546,"sourceUrl":547},"Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library",{"claudeCode":545},"Orchestra-Research/AI-Research-SKILLs","Instructor","https://github.com/Orchestra-Research/AI-Research-SKILLs",{"basePath":549,"githubOwner":550,"githubRepo":551,"locale":18,"slug":216,"type":248},"16-prompt-engineering/instructor","Orchestra-Research","AI-Research-SKILLs",{"evaluate":553,"extract":562},{"promptVersionExtension":204,"promptVersionScoring":205,"score":294,"tags":554,"targetMarket":217,"tier":218},[555,216,556,215,557,558,559,560,561],"prompt-engineering","structured-output","data-extraction","json-parsing","type-safety","validation","streaming",{"commitSha":279,"license":239},{"parentExtensionId":564,"repoId":565},"k17155ws9qc0hw7a568bg79sfd86max8","kd70hj1y80mhra5xm5g188j5n586mg18",[557,216,558,555,215,561,556,559,560],{"evaluatedAt":568,"extractAt":569,"updatedAt":568},1778697010260,1778695116697,{"_creationTime":571,"_id":572,"community":573,"display":574,"identity":577,"providers":578,"relations":583,"tags":584,"workflow":585},1778683220959.3254,"k170nd3h8zeayffrxe6pscxyy986m7em",{"reviewCount":8},{"description":382,"installMethods":575,"name":576,"sourceUrl":14},{"claudeCode":12},"Create Atomic Schema",{"basePath":381,"githubOwner":245,"githubRepo":246,"locale":18,"slug":383,"type":248},{"evaluate":579,"extract":582},{"promptVersionExtension":204,"promptVersionScoring":205,"score":294,"tags":580,"targetMarket":217,"tier":218},[581,215,216,246,211],"schema",{"commitSha":279,"license":239},{"parentExtensionId":251,"repoId":286},[246,216,215,211,581],{"evaluatedAt":586,"extractAt":290,"updatedAt":587},1778683329867,1778683668488,{"_creationTime":589,"_id":590,"community":591,"display":592,"identity":596,"providers":601,"relations":607,"tags":609,"workflow":610},1778685991755.7273,"k175b8b0kpk0gsz87sd34639z586nn67",{"reviewCount":8},{"description":543,"installMethods":593,"name":216,"sourceUrl":595},{"claudeCode":594},"davila7/claude-code-templates","https://github.com/davila7/claude-code-templates",{"basePath":597,"githubOwner":598,"githubRepo":599,"locale":18,"slug":600,"type":248},"cli-tool/components/skills/ai-research/prompt-engineering-instructor","davila7","claude-code-templates","prompt-engineering-instructor",{"evaluate":602,"extract":606},{"promptVersionExtension":204,"promptVersionScoring":205,"score":603,"tags":604,"targetMarket":217,"tier":605},75,[555,216,556,215,557,276],"community",{"commitSha":279},{"repoId":608},"kd71fzn4s7r0269fkw47wt670n86ndz0",[557,216,276,555,215,556],{"evaluatedAt":611,"extractAt":612,"updatedAt":611},1778688700350,1778685991755,{"_creationTime":614,"_id":615,"community":616,"display":617,"identity":623,"providers":627,"relations":638,"tags":640,"workflow":641},1778693511416.365,"k1758b69g51wttzw4r6epd3jrs86mtk8",{"reviewCount":8},{"description":618,"installMethods":619,"name":621,"sourceUrl":622},"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":620},"mksglu/context-mode","context-mode-ops","https://github.com/mksglu/context-mode",{"basePath":624,"githubOwner":625,"githubRepo":626,"locale":18,"slug":621,"type":248},".claude/skills/context-mode-ops","mksglu","context-mode",{"evaluate":628,"extract":637},{"promptVersionExtension":204,"promptVersionScoring":205,"score":526,"tags":629,"targetMarket":217,"tier":218},[630,631,632,212,633,634,635,636],"context-window","llm-optimization","session-continuity","developer-tool","productivity","security","compliance",{"commitSha":279},{"repoId":639},"kd764b2fctbqg4b8j8y6xvmkvs86m29m",[212,636,630,633,631,634,635,632],{"evaluatedAt":642,"extractAt":643,"updatedAt":644},1778693567505,1778693511416,1778693817147,{"_creationTime":646,"_id":647,"community":648,"display":649,"identity":655,"providers":659,"relations":666,"tags":668,"workflow":669},1778692607327.2307,"k17bwx69hk0p0w7rnpzvv2p16h86mp2k",{"reviewCount":8},{"description":650,"installMethods":651,"name":653,"sourceUrl":654},"Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.",{"claudeCode":652},"majiayu000/vibeguard","fixflow","https://github.com/majiayu000/vibeguard",{"basePath":656,"githubOwner":657,"githubRepo":658,"locale":18,"slug":653,"type":248},"workflows/fixflow","majiayu000","vibeguard",{"evaluate":660,"extract":665},{"promptVersionExtension":204,"promptVersionScoring":205,"score":526,"tags":661,"targetMarket":217,"tier":218},[662,663,213,212,664,635],"code-quality","ai-safety","workflow-automation",{"commitSha":279},{"repoId":667},"kd7b0vh258xpbyerk68bk3e1ks86mk58",[663,212,662,213,635,664],{"evaluatedAt":670,"extractAt":671,"updatedAt":672},1778692812461,1778692607327,1778693059223]