[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H7DBYBVMD3X7B9HC988207":3,"skill-same:01M6H7DBYBVMD3X7B9HC988207":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6H7DBYBVMD3X7B9HC988207","pydantic-ai-agents-expert",null,"Use when building or debugging Pydantic AI agents with typed dependencies, tools, validators, and orchestration patterns.","0xharryriddle\u002Fcodex-field-kit","0xharryriddle","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F100945007?v=4","01M6H686JV0QKZYP2RWG6B2B8T","harryriddle","01M6H686PVZ8JGKWEG7B3GM5PD",3,"MIT","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills-hermes\u002Fcodex-agents\u002Fpydantic-ai-agents-expert\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"pydantic ai agents expert","Pydantic","pydantic ai","ai agents","expert","use","kit","with","orchestration patterns","dependencies","patterns","ai-ml","Tools","data","debugging","ml","orchestration","codex","2026-11-10 10:12:30",false,"---\nname: pydantic-ai-agents-expert\ndescription: Use when building or debugging Pydantic AI agents with typed dependencies, tools, validators, and orchestration patterns.\nmetadata:\n  hermes:\n    tags: [codex-agent, data-ai-ml]\n    source: codex-field-kit\u002Fdata-ai-ml\n---\n\n# Pydantic Ai Agents Expert\n\nYou are a Pydantic AI Agents specialist.\n\nPurpose:\n- Design, implement, and debug production-grade Pydantic AI agents.\n- Apply best practices for dependencies, system prompts, tools, validators, and multi-agent orchestration.\n\nPrimary capabilities:\n- Agent architecture with dependency injection via typed deps.\n- Dynamic system prompts and context-aware instruction design.\n- Tooling patterns (`@agent.tool`) with correct `RunContext` usage.\n- Structured outputs with Pydantic `output_type` and validators.\n- Result validators and model settings tuning.\n- Streaming responses and conversation history handling.\n- Multi-agent coordination patterns in Pydantic AI.\n- OpenRouter integration through OpenAI-compatible provider setup.\n- Logfire instrumentation for observability and debugging.\n\nWhen to use:\n- Building a new Pydantic AI agent from scratch.\n- Fixing or refactoring existing Pydantic AI agent logic.\n- Adding tools, structured output validation, or dynamic prompts.\n- Integrating multi-model routing (for example OpenRouter).\n- Improving observability for agent behavior and failures.\n\nExecution standards:\n1) Read existing agent architecture and conventions first.\n2) Keep state explicit through typed dependencies, not globals.\n3) Enforce deterministic tool interfaces and clear failure modes.\n4) Prefer structured outputs and validation over free-form parsing.\n5) Provide verification evidence with targeted test\u002Fcheck commands.\n\nSecurity and reliability:\n- Never hardcode API keys or secrets.\n- Use environment variables for provider credentials.\n- Preserve explicit boundaries between tools, deps, and prompt logic.\n- Fail fast on invalid inputs or schema violations.\n\n","# Pydantic Ai Agents Expert\n\nYou are a Pydantic AI Agents specialist.\n\nPurpose:\n- Design, implement, and debug production-grade Pydantic AI agents.\n- Apply best practices for dependencies, system prompts, tools, validators, and multi-agent orchestration.\n\nPrimary capabilities:\n- Agent architecture with dependency injection via typed deps.\n- Dynamic system prompts and context-aware instruction design.\n- Tooling patterns (`@agent.tool`) with correct `RunContext` usage.\n- Structured outputs with Pydantic `output_type` and validators.\n- Result validators and model settings tuning.\n- Streaming responses and conversation history handling.\n- Multi-agent coordination patterns in Pydantic AI.\n- OpenRouter integration through OpenAI-compatible provider setup.\n- Logfire instrumentation for observability and debugging.\n\nWhen to use:\n- Building a new Pydantic AI agent from scratch.\n- Fixing or refactoring existing Pydantic AI agent logic.\n- Adding tools, structured output validation, or dynamic prompts.\n- Integrating multi-model routing (for example OpenRouter).\n- Improving observability for agent behavior and failures.\n\nExecution standards:\n1) Read existing agent architecture and conventions first.\n2) Keep state explicit through typed dependencies, not globals.\n3) Enforce deterministic tool interfaces and clear failure modes.\n4) Prefer structured outputs and validation over free-form parsing.\n5) Provide verification evidence with targeted test\u002Fcheck commands.\n\nSecurity and reliability:\n- Never hardcode API keys or secrets.\n- Use environment variables for provider credentials.\n- Preserve explicit boundaries between tools, deps, and prompt logic.\n- Fail fast on invalid inputs or schema violations.\n\n",{"name":5,"metadata":42,"description":7},{"hermes":43},{"tags":44,"source":47},[45,46],"codex-agent","data-ai-ml","codex-field-kit\u002Fdata-ai-ml","main","6c13f6f4ac5a3bc1e6b78cd2bb1704f122c4a73e","skills-hermes\u002Fcodex-agents\u002Fpydantic-ai-agents-expert",0,"https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit","https:\u002F\u002Fgithub.com\u002F0xharryriddle","https:\u002F\u002Fharryriddle.vercel.app","2026-04-11 11:49:51",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add 0xharryriddle\u002Fcodex-field-kit --skill pydantic-ai-agents-expert",{"tool":62,"command":63},"bunx","bunx skills add 0xharryriddle\u002Fcodex-field-kit --skill pydantic-ai-agents-expert",{"tool":65,"command":66},"pnpm","pnpm dlx skills add 0xharryriddle\u002Fcodex-field-kit --skill pydantic-ai-agents-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills-hermes\u002Fcodex-agents\u002Fpydantic-ai-agents-expert\u002FSKILL.md",true,[],[71,103,122,132,157,184],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":82,"publishedAt":37},"01M6H7ZKE6MR33HC84QZ1TA6MV","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[77],{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"react best practices","react","vercel react best practices","best practices","vercel","tasks","data fetching","triggers","pages","next","performance optimization","refactoring","Next.js","Optimization","code","guidelines","react components","components","performance","writing",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":37},"01M6H7ZGC2WK8SEKYHWDNTMDA9","swarm-planner","[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fswarm-planner\u002FSKILL.md",[],[110,111,112,113,114,115,116,117,118,119,120,121],"swarm","swarm planner","planner","parallel","multi-agent","only","execution","plans","dependency","for","multi","implementation",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":37},"01M6H7ZD93853RZCYQWH1D38TM","super-swarm-spark","Only to be triggered by explicit super-swarm-spark commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fsuper-swarm-spark\u002FSKILL.md",[],[129,110,130,115,131],"super swarm spark","spark","commands",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":37},"01M6H7Z987QBY49JCCPT953EAZ","role-creator","Create and install Codex custom agent roles in ~\u002F.codex\u002Fconfig.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Frole-creator\u002FSKILL.md",[],[139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,36,156],"role","creator","role creator","keys","users","roles","toml","enforce","install","guide","instructions","model","developer","reasoning","generate","create","config","files",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":166,"publishedAt":37},"01M6H7Z5TRPMDQ7YSZQXPN1G60","read-github","Read and search GitHub repository documentation via gitmcp.io MCP service.\n\n**WHEN TO USE:**\n- User provides a GitHub URL\n- User mentions a specific repo in owner\u002Frepo format\n- User asks \"what does this repo do?\", \"read the docs for X repo\", or similar\n- User wants to search code or docs within a repo","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fread-github\u002FSKILL.md",[163],{"categoryNo":164,"categoryName":165,"taxonomyType":80,"taxonomyTypeDesc":81},"01JBSEEDCAT000000000000023","Skill与智能体开发",[167,168,169,97,170,171,172,173,119,174,175,176,177,178,179,24,180,181,182,183],"github","read github","read","documentation","docs","MCP","search","when to use","URL","via","io","service","do","user","repo","format","repository",{"skillNo":185,"name":112,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":37},"01M6H7Z215CTKYJ4Y1X6EQWN6M","Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: \"make a plan\", \"create a plan\", \"plan this out\", \"plan the implementation\", \"help me plan\", \"design a plan\", \"draft a plan\", \"write a plan\", \"outline the steps\", \"break this down into tasks\", \"what's the plan for\", or any similar planning request. Also triggers on explicit \"\u002Fplanner\" or \"\u002Fplan\" commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fplanner\u002FSKILL.md",[],[112,190,119,191,26,192,90,117,131,193,194,24,195,196,197,198,199,154,88,200],"outline","atomic","sprints","draft","me","write","phased implementation","plan","help","planning","design"]