Python Testing

SkillAI & models

python claude skill is a skill that helps an AI agent select and run verification for Python SDK changes. It covers nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use it when adding Python tests, diagnosing Python CI, or validating Python SDK or provider changes. It is not for TypeScript-only checks.

Use Python Testing in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Python Testing and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Python Testing skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have a Python project with its test, lint, type, and build tooling already configured.

Python TestingStart free

What your AI can do with it

  • Choose and run nox sessions for Python SDK verification
  • Run Makefile targets for tests, lint, and build checks
  • Run Ruff for linting and formatting checks
  • Run mypy for type checking and type inference checks
  • Select pytest markers and sanity tests for a change
  • Diagnose Python CI failures from test, type, or build output

Getting started

  1. Have a Python project with its test, lint, type, and build tooling already configured.
  2. Add the skill to your agent's available skills.
  3. Point the agent at the Python SDK or provider change you want verified.
  4. Ask the agent to select and run the relevant nox, Makefile, Ruff, mypy, pytest, and build checks.

What this skill tells your AI

The instructions your AI receives, as published by composiohq/composio in .agents/skills/python-testing/SKILL.md and read by ahel’s review.

Use this skill to choose Python verification.

Read references/nox-make.md before running broad Python checks or adding test coverage.

Signals

GitHub stars
30k
Forks
5k
Last commit
Oct 2026

Questions

What is python-testing?
It is a skill that helps an AI agent select and run Python SDK verification: nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks.
When should I use it?
Use it when adding Python tests, diagnosing Python CI, or validating Python SDK or provider changes.
When should I not use it?
Do not use it for TypeScript-only checks.
Does it run the checks itself?
It selects and runs the Python SDK verification commands through your agent, using the project's existing nox, Makefile, Ruff, mypy, pytest, and build setup.
What tools does it cover?
nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks.
Advanced
Item type
skill
Key
python-testing-composiohq
Source
github.com/composiohq/composio