skill_get

Fetch one ad-ops playbook (Skill) by slug, including its full instructions and current revision.

Fetches a single Skill by its slug, returning the full instruction body plus the current revision. Discover slugs first with skill_list.

Input

Field	Type	Required	Description
`skill_name`	`string`	yes	The Skill slug (its per-organization handle).

Output

{ slug, name, description, body, revision }. The body is the playbook the agent follows; revision is the optimistic-concurrency token.

Example

“Load my weekly-meta-audit playbook and run it.”

skill_get({ skill_name: 'weekly-meta-audit' });
// → { slug: 'weekly-meta-audit', name: '…', body: '# Playbook\n…', revision: 3 }

The agent reads the body as its instructions, then calls whatever AdCrunch tools the playbook names (list_entities, query_insights, …).

Errors

Returns an error result when no Skill with that slug exists in your organization.
401 or 403 — see Errors, which every tool shares. This one needs skill:read.

Reference

Fetch a single ad-ops playbook (Skill) by its slug, returning the full instruction body and the current revision. Echo the revision back as base_revision when updating the Skill.

Input

Argument	Type	Required	Description
`skill_name`	string	yes	The Skill slug (its stable per-organization handle).

Failure codes

A failed call has isError set, and structuredContent.error holds one of these codes. Errors describes the shape of a failed call.

not_found
forbidden
invalid_request
internal_error

Scope

The token must hold skill:read. Auth & scopes lists each scope.

Annotations

A client reads these hints. A hint that the tool does not declare has the default value of the MCP specification.

Read-only. The tool changes nothing.
Closed world. The tool reads and writes the data of AdCrunch only.