# /smithery/skills/search `POST /api/smithery/skills/search` Price: 10 credits Search the Smithery catalog of agent skills — packaged instruction sets an agent loads to perform a task. Returns each skill's id, publisher namespace, description, categories, source repository link, GitHub star and fork counts of that repository, quality score, activation and unique-user counts, and its verified flag. Results can be narrowed to verified publishers, to one publisher namespace or to one category. Omitting `query` browses the whole catalog in relevance order. ## How to use it Skills and MCP servers are separate catalogs: a skill is instructions an agent reads, a server is a tool endpoint it calls — search /smithery/servers/search when you need the latter. Matching is semantic and never goes empty, so a query with no real match still returns a full page of loosely related skills; judge relevance from the descriptions. `external_stars` and `external_forks` count stars and forks on the whole source repository, not on the skill, so a skill inside a popular monorepo inherits a large number; `total_activations` is the per-skill usage figure. Pass a returned `id` to /smithery/skills for the skill's actual instruction text. Leave `query` out entirely to browse the catalog; `category` takes one of the values a result row's own `categories` carries, and a multi-word category or namespace still needs an exact match. ## Parameters - `access-token` (string, required) ## Request body - `timeout` (integer) — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500) - `query` (string, nullable) — What the skill should do, or its name. Matching is semantic, so a phrase works as well as a keyword. Leave it out to browse the whole catalog in relevance order (examples: "pdf", "write a slide deck", "review terraform"; minLength: 1) - `count` (integer, required) — Max number of results (examples: 21; min: 1; max: 504) - `verified_only` (boolean) — Keep only skills whose publisher Smithery has verified (default: false) - `namespace` (string, nullable) — Keep only skills published under this owner namespace, as it appears before the slash in a skill id (examples: "openclaw", "anthropics"; minLength: 1) - `category` (string, nullable) — Keep only skills tagged with this category, as returned in a result row's `categories` (examples: "Productivity", "Writing", "Data & Analytics"; minLength: 1) ## Response ### 200 — Successful Response - `@type` (string) (default: "SmitherySkill") - `id` (string, required) - `url` (string, required) - `name` (string, nullable) - `namespace` (string, nullable) - `alias` (string, nullable) - `uuid` (string, nullable) - `description` (string, nullable) - `git_url` (string, nullable) - `categories` (array) (default: []) - `external_stars` (integer, nullable) - `external_forks` (integer, nullable) - `quality_score` (number, nullable) - `relevance_score` (number, nullable) - `total_activations` (integer, nullable) - `unique_users` (integer, nullable) - `upvotes` (integer, nullable) - `downvotes` (integer, nullable) - `review_count` (integer, nullable) - `verified` (boolean, nullable) - `listed` (boolean, nullable) - `owner_id` (string, nullable) - `created_at` (string, nullable) ## Errors ### 422 — Validation Error The request body did not validate What to do: Check the fields against this schema. A URN with the wrong prefix is the most common cause. - `detail` (array) - `loc` (array, required) - `msg` (string, required) - `type` (string, required) - `input` (any) - `ctx` (object) ### 408 The request ran past its time limit What to do: Raise `timeout` in the request body, up to the maximum this endpoint documents. Lowering `count` or turning off the `with_*` flags also helps, because less work finishes sooner. ### 412 The entity was not found, or a precondition failed What to do: Retrying will not help: either the entity does not exist, or the input points at a different one. ### 429 Too many requests: a rate limit or a usage window is exhausted What to do: When the response carries an X-Retry-After header, wait that many seconds and retry: the same number is in the body as `detail.retry_after`, and the limit clears once that window passes. The message in the body names the limit that was hit. ### 500 Something broke on our side What to do: Retrying will not help. If it keeps happening, send us the X-Request-ID from the response headers. ### 529 Rate limit reached, or the endpoint is overloaded What to do: Wait at least 30 seconds, then retry. ## Response envelope Success: Array of objects (may be empty if no results) Error: Error may coexist with partial results if it occurs mid-execution. Check X-Error header and status code. Every response carries these headers: - `X-Error` — Error message text (present only on error) - `X-Request-ID` — Unique request identifier - `X-Execution-Time` — Execution time in seconds - `X-Result-Count` — How many records the body carries. 0 means an empty result, which is a normal answer and not by itself an error. A non-zero count can come back together with X-Error when the failure happened partway through — read this header and X-Error independently. - `X-Total-Available-Results` — How many records exist for this query, when the endpoint can say. On a `dry_run` request this is the answer and the body is empty. It saturates: the endpoint's documented maximum means 'at least that many', any smaller number is exact. - `X-Warning` — Present when the request body carried keys this endpoint does not document. They were ignored, so any filter you meant to apply through them did not apply. Check the spelling against this schema and retry. - `X-Retry-After` — Seconds to wait before retrying. Present only on 429.