Skill Claude CodeCodex
Add support for a newly-released LLM model in pydantic-ai (e.g. openai:gpt-5.6, anthropic:claude-sonnet-5). Use when a provider ships a new model id and you need to wire literals, profile flags, and tests to recognize it. Handles SDK-lag, gateway list conventions, and capability probing.
Skill Claude CodeCodex
Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. Use when wiring a provider feature through the library — it enforces reasoning from the existing cross-provider abstraction before designing…
Skill Claude CodeCodex
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
Skill Claude CodeCodex
Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. Use whenever responding to ANY message — coding, debugging, planning, casual. Lead with the result or the decision. Surface anything needing the user's input as a structured question, never buried in prose they'll…
Skill Claude CodeCodex
Independent power-user audit of a big new-feature PR. Research the feature domain from external sources before reading any implementation code, design the ideal test suite from a power-user's perspective, then gap-compare it against the PR to produce evidence-backed, precedent-linked review items. Use when a large…
Skill Claude CodeCodex
Open and advance a PR — write a current title and body, label it, review before every push, watch CI, and triage every comment. Use whenever you open a PR or push a commit to one.
Settings file Claude Code
Agent settings declaring 21 allowed tools.
Skill Claude CodeCodex
Find and address unresolved PR review comments for the current branch, then continue the canonical push, reply, reaction, and resolution workflow.
Skill Claude CodeCodex
Run a high-judgment local review of the current branch before pushing, both before a PR exists and between PR iterations.
Skill Claude CodeCodex
Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.
Instructions file CodexOpenCode
Instructions for pydantic/pydantic-ai, covering your primary responsibility is to the project and its users, gathering context on the task, ensuring the task is ready for implementation, philosophy and requirements of all contributions.
Instructions file
Instructions for pydantic/pydantic-ai, a project described as: How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
Cursor rule Cursor
Always reference the python code in the docs e.g. ModelSettings should link to [ModelSettings][pydanticai.settings.ModelSettings].
Skill Claude CodeCodex
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 pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
Skill Claude CodeCodex
Migrate Python LangChain or LangGraph applications to Pydantic AI. Use for LangChain agents, chains, LCEL, or direct LangGraph graphs, persistence, interrupts, and streaming. Do not use for migrations centered on createdeepagent or Deep Agents harness features.
Agent Codex
Use as the documentation gate before a branch or PR merges. Verifies that a user-visible change is reflected across all four documentation surfaces (README.md, docs/, limitations/, crate READMEs), that no divergence leaked into docs/ instead of limitations/, and that every snippet runs. Reports findings; does not edit.
Skill Claude CodeCodex
Fetch coverage diff from Codecov for the current branch or a specific PR. Shows uncovered lines, patch coverage, and overall coverage change.
Skill Claude CodeCodex
Use fastmod to make mass code updates to avoid many repetitive changes.
Skill Claude CodeCodex
Read the review comments left by the known agent reviewers on the current PR, resolve and reply. Use when asked to deal with PR comments, review feedback, or bot review findings.
Skill Claude CodeCodex
Run and test Python code in a dedicated playground directory. Use when you need to execute Python scripts, test code snippets, investigate CPython behavior, or experiment with Python without affecting the main codebase.
Skill Claude CodeCodex
Review the current branch against its merge base for bugs, CPython divergence, sandbox escapes, resource-limit escapes, performance regressions, verbose comments and missing ./limitations/ or docs/ updates. Use for a general pre-merge review of a branch or PR.
Skill Claude CodeCodex
Security review of the current branch against its merge base — sandbox escapes, memory errors, panics and resource-limit bypasses. Use when reviewing changes for security risk, or before merging anything touching heap.rs, pathsecurity.rs, the wire protocol or the pool.
Skill Claude CodeCodex
Check whether the common Python code an LLM would plausibly write still works on this branch, testing real cases in ./playground against CPython. Use to find behaviour that diverges from CPython or trips up ordinary idiomatic code.
Skill Claude CodeCodex
Rewrite excessively verbose comments and docstrings added by this branch, and delete tautologous ones. Use after writing a feature to tighten up its comments; this skill edits code rather than only reporting.