Pydantic AI is a Python framework designed for creating AI agents and LLM-powered applications. This skill offers patterns and architecture guidance along with tested code examples.
$ npx skills add https://github.com/pydantic/skills --skill building-pydantic-ai-agentsThis skill provides patterns and architecture guidance for building AI agents with Pydantic AI, a Python framework designed for LLM-powered applications. Learn how to implement agent tools, capabilities, streaming, and testing through practical code examples. The skill is compatible with 30+ agents via the agentskills.io standard, making it accessible across Claude Code, Codex, Cursor, and other platforms. It integrates seamlessly with Logfire for observability and can be extended with harness capabilities like Code Mode for sandboxed code execution. Whether you're prototyping a single-tool agent or building complex multi-capability systems, this skill provides the foundation and best practices needed.
Install the skill using the command: `$ npx skills add https://github.com/pydantic/skills --skill building-pydantic-ai-agents`
Creating AI agents using Pydantic AI
Adding tools and capabilities to agents
Defining agents from YAML/JSON specs
Streaming agent events and testing agent behavior
$ npx skills add https://github.com/pydantic/skills --skill building-pydantic-ai-agentsgit clone https://github.com/pydantic/skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Check the GitHub repository or documentation for usage examples.
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan