# load_skill (/docs/build/mcp-reference/load_skill)

{/* GENERATED by scripts/generate-mcp-reference.mjs from the MCP server tools/list. Do not edit. */}

| Group | Access | MCP name |
| --- | --- | --- |
| Coach | Read-only | `load_skill` |

## Description [#description]

The description the MCP server sends to the model, word for word. Its rules apply to every call.

> Read one of the user's saved Coach skills in full. Pass a slug from list_skills.

## Arguments [#arguments]

| Argument | Type | Required | Description |
| --- | --- | --- | --- |
| `slug` | `string` | Yes | The slug of one skill from your skill list. Max length 40. |

## Example call [#example-call]

The smallest valid request: required arguments only, with placeholder values.

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "load_skill",
    "arguments": {
      "slug": "…"
    }
  }
}
```

## Result [#result]

The result has `structuredContent` that matches this schema. The same data is also in `content` as JSON text.

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `description` | `string` | Yes |  |
| `id` | `string` | Yes |  |
| `instructions` | `string` | Yes |  |
| `slug` | `string` | Yes |  |
| `title` | `string` | Yes |  |
| `version` | `number` | Yes |  |

## Annotations [#annotations]

| Hint | Value |
| --- | --- |
| `readOnlyHint` | `true` |
| `destructiveHint` | `false` |
| `openWorldHint` | `false` |

The full input and output JSON Schemas for every tool are in [/mcp-tools.json](/mcp-tools.json).