Agent Skills

Updated Oct 21, 2026

Fireargs ships Agent Skills that tell coding agents such as Claude Code, Cursor and Codex how a Fireargs CLI works. Once installed, your agent knows how pydantic fields become arguments and options, how to wire a subcommand tree and how to drive a CLI through --json and --llms. You don't have to explain any of it in the prompt.

Install from the website

fireargs.dev publishes its skills under /.well-known/agent-skills/, so the skills CLI can install them from the site URL. Run this at your project root:

npx skills add https://fireargs.dev

It asks which skills and agents to install for; the site also serves the TypeScript skills, so pick the fireargs-python-* ones. To skip the prompts, pass them as flags:

npx skills add https://fireargs.dev --skill fireargs-python-commands --agent claude-code

Add --global to install for your user instead of the project, and --list to see what's available without installing anything. Run npx skills update later to pull newer versions.

Install from the package

The skills also ship inside the PyPI package, at fireargs/skills in your environment's site-packages. Installing them from there keeps them matched to the Fireargs version in your lockfile, while the website always serves the latest release:

npx skills add "$(python -c 'import fireargs, pathlib; print(pathlib.Path(fireargs.__file__).parent / "skills")')"

Run it with the environment's Python — uv run python in a uv project.

Use them

You don't need to invoke a skill yourself. Agents read each skill's description and load it when a task matches. For example, asking for a new deploy command loads fireargs-python-commands, and asking to group commands under a db subcommand loads fireargs-python-programs. If your agent supports invoking skills by name, you can also call one directly, as with /fireargs-python-automation in Claude Code.

See also

• LLMs mode — the --llms manifest an agent reads at runtime, rather than while writing code.