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

> ## Agent Instructions
> To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the atlanai CLI; `atlanai --map json` prints its command map. Run a read-only identity check before any write.
> The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects.
> SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript.

# Skills

> Every published skills operation, generated from the contract.

16 operations on `client.skills`, including `skills.traces`, `skills.versions`.

Path parameters come first, positionally; the request body is last, as a plain
object. Method names are `snake_case` in Python and `camelCase` in
TypeScript, and resource names follow the same rule.

<CodeGroup>
  ```python Python theme={null}
  result = client.skills.aggregate(body)
  ```

  ```typescript TypeScript theme={null}
  const result = await client.skills.aggregate(body);
  ```
</CodeGroup>

## Operations

| Call | Route | Does |
| - | - | - |
| `client.skills.aggregate(body)` | `POST /skill/v1/skills/aggregate` | Aggregate skills |
| `client.skills.archive(skill_id)` | `POST /skill/v1/skills/{skill_id}/archive` | Archive a skill |
| `client.skills.bulk_create(body)` | `POST /skill/v1/skills/bulk` | Create many skills from bundles |
| `client.skills.create()` | `POST /skill/v1/skills` | Create a skill from a bundle |
| `client.skills.get_bundle(skill_id)` | `GET /skill/v1/skills/{skill_id}/bundle` | Download a skill bundle |
| `client.skills.get_enriched(skill_id)` | `GET /skill/v1/skills/{skill_id}` | Read a skill with its files' L1 embedded |
| `client.skills.list()` | `GET /skill/v1/skills` | List skills |
| `client.skills.list_insights(skill_id)` | `GET /skill/v1/skills/{skill_id}/insights` | List a skill's derived insights |
| `client.skills.search(body)` | `POST /skill/v1/skills/search` | Search skills |
| `client.skills.update(skill_id, body)` | `PATCH /skill/v1/skills/{skill_id}` | Update a skill's envelope |
| `client.skills.traces.get(skill_id, trace_id)` | `GET /skill/v1/skills/{skill_id}/traces/{trace_id}` | Read one skill trace |
| `client.skills.traces.list(skill_id)` | `GET /skill/v1/skills/{skill_id}/traces` | List traces for a skill |
| `client.skills.traces.list_spans(skill_id, trace_id)` | `GET /skill/v1/skills/{skill_id}/traces/{trace_id}/spans` | List spans in a skill trace |
| `client.skills.traces.query_stats(skill_id, body)` | `POST /skill/v1/skills/{skill_id}/traces/stats/query` | Query skill trace statistics |
| `client.skills.versions.get_bundle(skill_id, version_ordinal)` | `GET /skill/v1/skills/{skill_id}/versions/{version_ordinal}/bundle` | Download a pinned skill version's bundle |
| `client.skills.versions.get_enriched(skill_id, version_ordinal)` | `GET /skill/v1/skills/{skill_id}/versions/{version_ordinal}` | Read a pinned skill version with its files' L1 embedded |

## Related

<CardGroup cols={2}>
  <Card title="How the client is organised" icon="list" href="/tools/sdk/how-tos/operations">
    Resources, call shapes, and errors.
  </Card>

  <Card title="Errors and retries" icon="triangle-exclamation" href="/platform/references/errors-and-retries">
    What the SDK raises, and which calls are safe to retry.
  </Card>
</CardGroup>