# setup_skills_parser

> **Function** in `deepagents_code`

📖 [View in docs](https://reference.langchain.com/python/deepagents-code/skills/commands/setup_skills_parser)

Setup the skills subcommand parser with all its subcommands.

Each subcommand gets a dedicated help screen so that
`deepagents skills -h` shows skills-specific help, not the
global help.

## Signature

```python
setup_skills_parser(
    subparsers: Any,
    *,
    make_help_action: Callable[[Callable[[], None]], type[argparse.Action]],
    add_output_args: Callable[[argparse.ArgumentParser], None] | None = None,
) -> argparse.ArgumentParser
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `subparsers` | `Any` | Yes | The parent subparsers object to add the skills parser to. |
| `make_help_action` | `Callable[[Callable[[], None]], type[argparse.Action]]` | Yes | Factory that accepts a zero-argument help callable and returns an argparse Action class wired to it. |
| `add_output_args` | `Callable[[argparse.ArgumentParser], None] \| None` | No | Optional hook to add a shared `--json` flag. (default: `None`) |

## Returns

`argparse.ArgumentParser`

The skills subparser for argument handling.

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/d1c6946218b4f0f86ab7b02b6bb6af1e4b75cede/libs/code/deepagents_code/skills/commands.py#L856)