# load_skill_content

> **Function** in `deepagents_cli`

📖 [View in docs](https://reference.langchain.com/python/deepagents-cli/skills/load/load_skill_content)

Read the full raw SKILL.md content for a skill.

Returns the complete file content including any YAML frontmatter.
Callers are responsible for parsing or stripping frontmatter if needed.

When `allowed_roots` is provided, the resolved path must fall within at
least one root directory. This prevents symlink traversal from reading files
outside known skill directories.

## Signature

```python
load_skill_content(
    skill_path: str,
    *,
    allowed_roots: Sequence[Path] = (),
) -> str | None
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `skill_path` | `str` | Yes | Path to the SKILL.md file (from `SkillMetadata['path']`). |
| `allowed_roots` | `Sequence[Path]` | No | Skill root directories the resolved path must be contained within.  Callers must pre-resolve these via `Path.resolve()` — the resolved skill path is compared directly, so un-resolved roots cause false containment failures.  If empty, containment is not checked. (default: `()`) |

## Returns

`str | None`

Full text content of the SKILL.md file, or `None` on read failure.

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/a827cddf72d72e4b17921b8eb445a3bfb0511cb4/libs/cli/deepagents_cli/skills/load.py#L136)