mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-11 19:47:12 +03:00
37 lines
1.7 KiB
Markdown
37 lines
1.7 KiB
Markdown
# PydanticAI & PydanticGraph — Type-Safe AI Agents & Graph Workflows
|
|
|
|
Build production-grade AI agents and graph-based state machines with PydanticAI and PydanticGraph. Agent creation, function tools, dependency injection, structured output, streaming, and graph control flow.
|
|
|
|
## Why Install This Skill
|
|
|
|
When your agent loads this skill, it becomes a **PydanticAI expert** who can:
|
|
|
|
- **Create type-safe agents** — one-line agent creation with structured output validation
|
|
- **Build function tools with dependencies** — RunContext for dependency injection
|
|
- **Stream outputs** — text, events, and graph node streaming
|
|
- **Use built-in capabilities** — Thinking, WebSearch, MCP, Hooks, and 20+ more with on-demand loading
|
|
- **Create graph state machines** — PydanticGraph with BaseNode, GraphBuilder, parallel map/broadcast, joins with reducers
|
|
- **Test systematically** — TestModel, FunctionModel, Pydantic Evals
|
|
- **Deploy to production** — multi-agent patterns, MCP servers, durable execution
|
|
|
|
## What You Get
|
|
|
|
| Directory | Purpose |
|
|
|-----------|---------|
|
|
| `SKILL.md` | Quick reference, when-to-load table, common pattern gallery |
|
|
| `references/` | 8 reference files: core agents, capabilities/hooks, graph, models/output, patterns, testing/evals, examples, API reference, hybrid LangGraph patterns |
|
|
| `templates/` | Runnable template implementations |
|
|
|
|
## Triggers
|
|
|
|
Load this whenever building agents, tool-using LLM workflows, or graph-based state machines in Python.
|
|
|
|
## Requirements
|
|
|
|
Python 3.10+ with `pydantic-ai` or `pydantic-ai-slim` package.
|
|
|
|
|
|
## Quick Start
|
|
|
|
Start with the setup and first workflow in SKILL.md, then use the linked resources for the specific task you need to complete.
|