Skills

Package skills is the skill catalogue an AI client reads to learn what it can do.

skills

DELETE /v1/skills/{id}

Removes one of the caller org's authored skills. Scoped to the caller's org, so an id belonging to another tenant is never reached. Removing what is not there is not an error — the caller's intent is "gone", and it is.

GET /v1/skills/authored

Lists the caller org's OWN skills with their SKILL.md bodies. GET /v1/skills is the registry view — the brand's catalogue plus this org's, with activation flags and no bodies; this is the EDITABLE set, so it carries the content that view omits and nothing the org did not write.

GET /v1/skills

Lists the skills the caller's org can reach — the brand's embedded catalogue plus the org's own authored ones — with each one's activation flag. A skill is discovery and activation metadata attached to an agent, never called directly, so every entry here is non-dispatchable. It is GET /v1/tools narrowed to one source, not a second store: a name a caller sees here is the same entry, with the same activation state, that discovery reports.

POST /v1/skills

Adds or revises one of the caller org's own skills, and answers 201 with the stored record. The id is derived from the name, so writing the same name again REVISES that skill rather than accumulating near-duplicates that would then collide in the registry. An org's skills are private to it by construction — they live in a different store from the brand's embedded catalogue and have no path into the public gallery — and a brand skill always wins a name collision against an org's.

Request body — application/json (required)

---

All Hanzo APIs · Interactive reference