[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B3BCPBW729D6XVBJK8M7WJ":3,"skill-same:01M7B3BCPBW729D6XVBJK8M7WJ":57},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7B3BCPBW729D6XVBJK8M7WJ","pydantic-ai-harness",null,"Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness -- currently Code Mode, which collapses many tool calls into one sandboxed Python execution. Use when the user mentions pydantic-ai-harness, CodeMode, Monty, code mode, or tool sandboxing, when they want an agent to run agent-written Python, or when a Pydantic AI agent would benefit from orchestrating multiple tool calls in a single sandboxed script.","cianfhoghlaim\u002Fciandlithe","cianfhoghlaim","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F57019547?v=4","01M6DWR3GAV495PYDTZSR1FZNX","Cian Mac (an Déisigh Uí) Liatháin || Deacy-Lyons","01M7B2QN19FG7B5G3DCB73XWEK",1,"MIT","https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpydantic\u002Fpydantic-ai-harness\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pydantic-ai-harness\ndescription: Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness -- currently Code Mode, which collapses many tool calls into one sandboxed Python execution. Use when the user mentions pydantic-ai-harness, CodeMode, Monty, code mode, or tool sandboxing, when they want an agent to run agent-written Python, or when a Pydantic AI agent would benefit from orchestrating multiple tool calls in a single sandboxed script.\nlicense: MIT\ncompatibility: Requires Python 3.10+ and pydantic-ai-slim>=1.95.1\nmetadata:\n  version: \"0.1.0\"\n  author: pydantic\n---\n\n# Building with Pydantic AI Harness\n\nPydantic AI Harness is the official capability library for Pydantic AI. Capabilities that need model or\nframework support -- and those fundamental to every agent -- live in core `pydantic-ai`; optional,\nbatteries-included capabilities live here. Both are composed onto an agent through the same\n`capabilities=[...]` API.\n\nThis skill covers the capabilities shipped by `pydantic-ai-harness`. For the core framework -- agents,\ntools, structured output, hooks, and testing -- use the `building-pydantic-ai-agents` skill instead.\n\n## When to Use This Skill\n\nInvoke this skill when:\n- The user mentions `pydantic-ai-harness`, `CodeMode`, code mode, or the Monty sandbox\n- An agent makes many sequential tool calls that could collapse into one sandboxed Python execution\n- The user wants the model to write Python that loops, branches, aggregates, or parallelizes tool calls with `asyncio.gather`\n- The user asks to sandbox or constrain the code an agent runs\n\nDo **not** use this skill for:\n- Core Pydantic AI usage -- building agents, adding tools, structured output, streaming, or testing (use `building-pydantic-ai-agents`)\n- Capabilities that ship in core `pydantic-ai`, such as web search, tool search, and thinking\n- The Pydantic validation library on its own (`pydantic`\u002F`BaseModel` without agents)\n\n## Supported Capabilities\n\n| Capability | Description | Reference |\n|---|---|---|\n| `CodeMode` | Wraps eligible tools into a single sandboxed `run_code` tool so the model orchestrates them in Python | [Code Mode](.\u002Freferences\u002FCODE-MODE.md) |\n\nMore capability areas are tracked in the\n[capability matrix](https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai-harness#capability-matrix); as they stabilize,\nthis skill grows to cover them.\n\n## Install\n\n```bash\nuv add pydantic-ai-harness\n```\n\nEach capability declares its own extra. Code Mode needs the Monty sandbox:\n\n```bash\nuv add \"pydantic-ai-harness[codemode]\"   # `code-mode` is also accepted as an alias\n```\n\nRequires Python 3.10+ and `pydantic-ai-slim>=1.95.1`.\n\n## Quick Start\n\nA harness capability is added to the agent like any other. Here `CodeMode` wraps an MCP server's tools into\na single `run_code` tool that the model drives with Python.\n\n```python {test=\"skip\"}\nfrom pydantic_ai import Agent\nfrom pydantic_ai.capabilities import MCP  # MCP ships in core pydantic-ai\n\nfrom pydantic_ai_harness import CodeMode\n\nagent = Agent(\n    'anthropic:claude-sonnet-4-6',\n    capabilities=[\n        # native=False routes the MCP tools through a local toolset so CodeMode can wrap them.\n        # Without it, providers with native MCP run the tools server-side and bypass the sandbox.\n        MCP('https:\u002F\u002Fhn.caseyjhand.com\u002Fmcp', native=False),\n        CodeMode(),\n    ],\n)\n\nresult = agent.run_sync(\n    'Across the top and best Hacker News feeds, find the most-discussed story with at '\n    'least 100 points and summarize its comment thread in one paragraph.'\n)\nprint(result.output)\n#> The most-discussed story clearing 100 points is ...\n```\n\nInstead of one model round-trip per tool call, the model writes a single Python script that fetches both\nfeeds with `asyncio.gather`, dedupes and ranks them in plain Python, and pulls the winning thread --\ncollapsing many calls into one `run_code`.\n\n## Key Practices\n\n- **Confirm a harness capability is actually needed.** If core Pydantic AI tools and capabilities are enough, use the `building-pydantic-ai-agents` skill instead -- don't reach for the harness by default.\n- **Read the reference before writing code.** Each capability has its own configuration, constraints, and gotchas -- load the linked reference (e.g. [Code Mode](.\u002Freferences\u002FCODE-MODE.md)) first.\n- **Install the capability's extra.** Importing `CodeMode` without `pydantic-ai-harness[codemode]` raises an `ImportError`; the Monty sandbox is an optional dependency.\n\n## Common Gotchas\n\n- **`native=True` tools bypass `CodeMode`.** Provider-native MCP servers and web search execute server-side, so `run_code` never sees them. Construct them with `native=False` to keep them local and wrappable.\n- **The Monty sandbox is a Python subset.** No class definitions, no third-party imports, and only a small stdlib allowlist -- read [Code Mode](.\u002Freferences\u002FCODE-MODE.md#sandbox-restrictions) before debugging generated code that fails to run.\n- **`CodeMode` needs its extra.** Install `pydantic-ai-harness[codemode]`, not the bare package.\n","# Building with Pydantic AI Harness\n\nPydantic AI Harness is the official capability library for Pydantic AI. Capabilities that need model or\nframework support -- and those fundamental to every agent -- live in core `pydantic-ai`; optional,\nbatteries-included capabilities live here. Both are composed onto an agent through the same\n`capabilities=[...]` API.\n\nThis skill covers the capabilities shipped by `pydantic-ai-harness`. For the core framework -- agents,\ntools, structured output, hooks, and testing -- use the `building-pydantic-ai-agents` skill instead.\n\n## When to Use This Skill\n\nInvoke this skill when:\n- The user mentions `pydantic-ai-harness`, `CodeMode`, code mode, or the Monty sandbox\n- An agent makes many sequential tool calls that could collapse into one sandboxed Python execution\n- The user wants the model to write Python that loops, branches, aggregates, or parallelizes tool calls with `asyncio.gather`\n- The user asks to sandbox or constrain the code an agent runs\n\nDo **not** use this skill for:\n- Core Pydantic AI usage -- building agents, adding tools, structured output, streaming, or testing (use `building-pydantic-ai-agents`)\n- Capabilities that ship in core `pydantic-ai`, such as web search, tool search, and thinking\n- The Pydantic validation library on its own (`pydantic`\u002F`BaseModel` without agents)\n\n## Supported Capabilities\n\n| Capability | Description | Reference |\n|---|---|---|\n| `CodeMode` | Wraps eligible tools into a single sandboxed `run_code` tool so the model orchestrates them in Python | [Code Mode](.\u002Freferences\u002FCODE-MODE.md) |\n\nMore capability areas are tracked in the\n[capability matrix](https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai-harness#capability-matrix); as they stabilize,\nthis skill grows to cover them.\n\n## Install\n\n```bash\nuv add pydantic-ai-harness\n```\n\nEach capability declares its own extra. Code Mode needs the Monty sandbox:\n\n```bash\nuv add \"pydantic-ai-harness[codemode]\"   # `code-mode` is also accepted as an alias\n```\n\nRequires Python 3.10+ and `pydantic-ai-slim>=1.95.1`.\n\n## Quick Start\n\nA harness capability is added to the agent like any other. Here `CodeMode` wraps an MCP server's tools into\na single `run_code` tool that the model drives with Python.\n\n```python {test=\"skip\"}\nfrom pydantic_ai import Agent\nfrom pydantic_ai.capabilities import MCP  # MCP ships in core pydantic-ai\n\nfrom pydantic_ai_harness import CodeMode\n\nagent = Agent(\n    'anthropic:claude-sonnet-4-6',\n    capabilities=[\n        # native=False routes the MCP tools through a local toolset so CodeMode can wrap them.\n        # Without it, providers with native MCP run the tools server-side and bypass the sandbox.\n        MCP('https:\u002F\u002Fhn.caseyjhand.com\u002Fmcp', native=False),\n        CodeMode(),\n    ],\n)\n\nresult = agent.run_sync(\n    'Across the top and best Hacker News feeds, find the most-discussed story with at '\n    'least 100 points and summarize its comment thread in one paragraph.'\n)\nprint(result.output)\n#> The most-discussed story clearing 100 points is ...\n```\n\nInstead of one model round-trip per tool call, the model writes a single Python script that fetches both\nfeeds with `asyncio.gather`, dedupes and ranks them in plain Python, and pulls the winning thread --\ncollapsing many calls into one `run_code`.\n\n## Key Practices\n\n- **Confirm a harness capability is actually needed.** If core Pydantic AI tools and capabilities are enough, use the `building-pydantic-ai-agents` skill instead -- don't reach for the harness by default.\n- **Read the reference before writing code.** Each capability has its own configuration, constraints, and gotchas -- load the linked reference (e.g. [Code Mode](.\u002Freferences\u002FCODE-MODE.md)) first.\n- **Install the capability's extra.** Importing `CodeMode` without `pydantic-ai-harness[codemode]` raises an `ImportError`; the Monty sandbox is an optional dependency.\n\n## Common Gotchas\n\n- **`native=True` tools bypass `CodeMode`.** Provider-native MCP servers and web search execute server-side, so `run_code` never sees them. Construct them with `native=False` to keep them local and wrappable.\n- **The Monty sandbox is a Python subset.** No class definitions, no third-party imports, and only a small stdlib allowlist -- read [Code Mode](.\u002Freferences\u002FCODE-MODE.md#sandbox-restrictions) before debugging generated code that fails to run.\n- **`CodeMode` needs its extra.** Install `pydantic-ai-harness[codemode]`, not the bare package.\n",{"name":5,"license":15,"metadata":24,"description":7,"compatibility":27},{"author":25,"version":26},"pydantic","0.1.0","Requires Python 3.10+ and pydantic-ai-slim>=1.95.1","main","6283bdef5afa434010d035c077fed63a4ff0c00d",".agents\u002Fskills\u002Fpydantic\u002Fpydantic-ai-harness",0,"https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe","https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim","cianfhoghlaim.ie","Irish-British teacher, mathematician, foghlaimeoir || minority-language AI researcher || Lucht Siúil ||\r\nFine Gael + Alliance Party + Liberal Democrats Member","2026-11-13 20:49:56",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add cianfhoghlaim\u002Fciandlithe --skill pydantic-ai-harness",{"tool":43,"command":44},"bunx","bunx skills add cianfhoghlaim\u002Fciandlithe --skill pydantic-ai-harness",{"tool":46,"command":47},"pnpm","pnpm dlx skills add cianfhoghlaim\u002Fciandlithe --skill pydantic-ai-harness","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpydantic\u002Fpydantic-ai-harness\u002FSKILL.md",true,[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002FCODE-MODE.md","REFERENCE","参考文档",5354,"https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpydantic\u002Fpydantic-ai-harness\u002Freferences\u002FCODE-MODE.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7B3AQKKPS8AFZBJADH7PR01","building-pydantic-ai-agents","Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools\u002Fcapabilities, defer capability loading, stream output, define agents from YAML, or test agent behavior.","https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpydantic\u002Fbuilding-pydantic-ai-agents\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7B39YG1J49ASJBKHKGBW03C","motherduck-share-data","Create and manage MotherDuck data shares for zero-copy, read-only data distribution. Use whenever someone wants to share a database with team members, another organization, or the public — covers CREATE SHARE, access\u002Fvisibility\u002Fupdate modes, GRANT READ ON SHARE, attaching share URLs, UPDATE SHARE, and REFRESH DATABASE.","https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmotherduck\u002Fmotherduck-share-data\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7B39TVXB76BAE248616DTYR","motherduck-security-governance","Explain MotherDuck security, governance, and access-control patterns. Use for any question about SOC 2, GDPR, compliance, data residency, regions, SSO, service accounts, token handling, tenant isolation, sharing boundaries, snapshots and recovery, or governance posture — including when a security_compliance_owner, technical_owner, or application_builder is evaluating MotherDuck.","https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmotherduck\u002Fmotherduck-security-governance\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7B39R4FJJTPXF6TAFA11F7V","motherduck-rest-api","MotherDuck REST API control-plane reference. Use when calling api.motherduck.com to provision service accounts, create, list, rotate, or revoke access tokens, configure Duckling instance sizes and read scaling, inspect active accounts, or mint Dive embed sessions. Not for SQL or data-plane query work.","https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmotherduck\u002Fmotherduck-rest-api\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7B39NW25YGBFJHP36DAK521","motherduck-query","Execute DuckDB SQL queries against MotherDuck databases. Use when running analytics, aggregations, transformations, or any SQL operation. Covers query best practices, CTEs, window functions, QUALIFY, and performance optimization.","https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmotherduck\u002Fmotherduck-query\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7B39JY2KA5576JG3BSZ0TKK","motherduck-pricing-roi","Explain MotherDuck pricing and ROI tradeoffs. Use for any pricing, cost, billing, plan-comparison, instance-sizing, chargeback, or budget question — when an economic_buyer, technical_owner, or analytics_lead asks about spend, budget guardrails, workload cost drivers, plan fit, vendor cost comparisons, or whether MotherDuck is worth adopting.","https:\u002F\u002Fgithub.com\u002Fcianfhoghlaim\u002Fciandlithe\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmotherduck\u002Fmotherduck-pricing-roi\u002FSKILL.md",[],[]]