> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/volcengine/OpenViking/llms.txt
> Use this file to discover all available pages before exploring further.

# List Skills

List all available skills in the knowledge base. Skills can be invoked by agents to perform specific tasks.

<Note>
  Skills are stored at `viking://agent/skills/` in the Agent General File System (AGFS).
</Note>

## Authentication

Requires API key authentication via `X-API-Key` header.

## Query Parameters

<ParamField query="uri" type="string" required>
  The URI to list. Use `viking://agent/skills/` to list all skills.
</ParamField>

<ParamField query="simple" type="boolean" default="false">
  If true, returns only skill names. If false, returns full metadata.
</ParamField>

## Response

<ResponseField name="status" type="string">
  Response status (`ok` or `error`)
</ResponseField>

<ResponseField name="result" type="array">
  Array of skills with metadata

  <Expandable title="Skill Object">
    <ResponseField name="name" type="string">
      Skill name in kebab-case (e.g., `search-web`)
    </ResponseField>

    <ResponseField name="uri" type="string">
      Full URI path to the skill (e.g., `viking://agent/skills/search-web/`)
    </ResponseField>

    <ResponseField name="type" type="string">
      Resource type (always `directory` for skills)
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="time" type="number">
  Request processing time in seconds
</ResponseField>

## Example

<CodeGroup>
  ```bash cURL theme={null}
  curl -X GET "http://localhost:1933/api/v1/fs/ls?uri=viking://agent/skills/" \
    -H "X-API-Key: your-key"
  ```

  ```python Python SDK theme={null}
  # List all skills with metadata
  skills = client.ls("viking://agent/skills/")
  for skill in skills:
      print(f"{skill['name']}: {skill['uri']}")

  # Simple list (names only)
  names = client.ls("viking://agent/skills/", simple=True)
  print(names)  # ['search-web', 'calculator', 'code-runner']
  ```

  ```bash CLI theme={null}
  openviking ls viking://agent/skills/
  ```
</CodeGroup>

<ResponseExample>
  ```json Response theme={null}
  {
    "status": "ok",
    "result": [
      {
        "name": "search-web",
        "uri": "viking://agent/skills/search-web/",
        "type": "directory"
      },
      {
        "name": "calculator",
        "uri": "viking://agent/skills/calculator/",
        "type": "directory"
      },
      {
        "name": "code-runner",
        "uri": "viking://agent/skills/code-runner/",
        "type": "directory"
      }
    ],
    "time": 0.05
  }
  ```

  ```json Simple Response theme={null}
  {
    "status": "ok",
    "result": [
      "search-web",
      "calculator",
      "code-runner"
    ],
    "time": 0.02
  }
  ```
</ResponseExample>

## Skill Storage Structure

Each skill is stored as a directory containing:

* `.abstract.md` - L0: Brief description
* `.overview.md` - L1: Parameters and usage
* `SKILL.md` - L2: Full documentation
* Auxiliary files - Any additional resources

## Reading Skill Content

After listing skills, use the content API to read skill documentation at different levels:

```python theme={null}
uri = "viking://agent/skills/search-web/"

# L0: Brief description
abstract = client.abstract(uri)

# L1: Parameters and usage overview
overview = client.overview(uri)

# L2: Full skill documentation
content = client.read(uri)
```

## Related Endpoints

* [Add Skill](/api/skills/add-skill) - Add a new skill
* [Search Skills](/api/retrieval/find) - Semantic search for skills
* [Remove Skill](/api/filesystem/rm) - Delete a skill