Repository
pydantic/pydantic-ai agent skills
- skills
- 20
- official
- 20
- GitHub stars
- 20k
GitHub description: “How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.”
- Stars
- 20,497 (2,885 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Jun 2024
- Homepage
- pydantic.dev/pydantic-ai
- agent-framework
- pydantic
- python
- genai
- llm
- harness
- harness-engineering
Install all skills
npx skills add pydantic/pydantic-aiAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in pydantic/pydantic-ai, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Adds optional capabilities to Pydantic AI agents from pydantic-ai-harness, led by Code Mode, which runs many tool calls as one sandboxed Python script. | pydantic/ | 20k | — | ~4.9k | Automated safety check: Pass | MIT | yesterday |
| 2 | Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns. | pydantic/ | 20k | — | ~8k | Automated safety check: Pass | MIT | yesterday |
| 3 | Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. | pydantic/ | 20k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 4 | Record, rewrite, and debug VCR cassettes for HTTP recordings. | pydantic/ | 20k | — | ~839 | Automated safety check: Notes | MIT | yesterday |
| 5 | Migrate Python Agno applications to Pydantic AI and, only when needed, Pydantic AI Harness. | pydantic/ | 20k | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 6 | Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness. | pydantic/ | 20k | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 7 | Migrates Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness while preserving the application's observed behavior. | pydantic/ | 20k | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 8 | Migrate Python Google Agent Development Kit (ADK) applications to Pydantic AI. | pydantic/ | 20k | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 9 | Migrate Python LangChain, LangGraph, or Deep Agents applications to Pydantic AI and, when the source uses harness features, Pydantic AI Harness. | pydantic/ | 20k | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 10 | Migrate TypeScript Mastra applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. | pydantic/ | 20k | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 11 | Migrate Python OpenAI Agents SDK applications to Pydantic AI and, when warranted, Pydantic AI Harness. | pydantic/ | 20k | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 12 | Migrate TypeScript Pi coding-agent applications, extensions, or packages to Python with Pydantic AI and Pydantic AI Harness. | pydantic/ | 20k | — | ~2.1k | Automated safety check: Pass | MIT | yesterday |
| 13 | Migrate TypeScript Vercel AI SDK or Eve applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. | pydantic/ | 20k | — | ~2.3k | Automated safety check: Pass | MIT | yesterday |
| 14 | Add support for a newly-released language or image generation model in pydantic-ai (e.g. | pydantic/ | 20k | — | ~10k | Automated safety check: Notes | MIT | yesterday |
| 15 | Covers what to do on opening a pull request and after every push: apply a label, watch CI to green, answer every review comment and escalate real design trade-offs. | pydantic/ | 20k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 16 | Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. | pydantic/ | 20k | — | ~3.2k | Automated safety check: Pass | MIT | yesterday |
| 17 | Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. | pydantic/ | 20k | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 18 | Independent power-user audit of a big new-feature PR. An agent skill from pydantic/pydantic-ai. | pydantic/ | 20k | — | ~2.9k | Automated safety check: Pass | MIT | yesterday |
| 19 | Use as the final documentation gate before a pydantic-ai-harness capability PR merges. | pydantic/ | 20k | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 20 | Find and address unresolved PR review comments for the current branch, then continue the canonical push, reply, reaction, and resolution workflow. | pydantic/ | 20k | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
Questions, answered from the data.
What is the best skill in pydantic/pydantic-ai?
Pydantic AI Harness (official) from pydantic/pydantic-ai ranks first of the 20 skills in pydantic/pydantic-ai listed here, with the highest score: its repository has 20k GitHub stars, its SKILL.md loads about 4.9k tokens and it passes the automated safety check with no findings. Next come Building Pydantic AI Agents and Complete Partial PR.
Are the skills in pydantic/pydantic-ai official?
20 of the 20 skills in pydantic/pydantic-ai are official, published by the vendor's own GitHub organization: Pydantic AI Harness, Building Pydantic AI Agents, Complete Partial PR, Testing Skill, Migrating Agno To Pydantic AI and 15 more.
How do I install all skills from pydantic/pydantic-ai?
Run npx skills add pydantic/pydantic-ai in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.