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

# List builtin and user-defined skills

> Returns the builtin skill catalog, the account's disabled-builtin list, and the account's user-defined skills. A fresh account (no aggregate yet) returns empty `disabled_builtins` and `skills` rather than an error. Subject: `microstrate.hub.get.coworker-skills`.



## OpenAPI

````yaml /api-reference/endpoint/abbie/openapi.json get /hub/coworker/skills
openapi: 3.1.0
info:
  title: Abbie API (beta)
  version: 1.0.0
  description: >
    **Beta.** This API is in beta: operations and fields may change without a
    deprecation period. Do not depend on undocumented fields. It covers the
    subset of Abbie's API used by the Quiva coworker MCP server: skills, todos,
    memory, profile, corrections, environment and models.


    HTTP surface of hub-service for Abbie/Coworker configuration, agent rapport
    & context, chat-session sharing, and MCP registration.


    ## Transport and response envelope


    Every operation here is a gateway mapping onto a Bellerophon/kraken subject
    of the form `microstrate.hub.<method>.<endpoint-slug>` (see
    `hub-service/service/service.go` and `docs/abbie-gateway-mappings.md`).
    Handlers reply on the mesh with an envelope `{"status_code": <int>, "body":
    <object>}`; the gateway unwraps it, so `status_code` becomes the HTTP status
    and `body` becomes the HTTP response body. **The schemas below describe the
    unwrapped `body`.**


    Errors are always `{"error": "<message>"}` with the matching HTTP status.


    ## Parameter conventions


    The gateway forwards URL parameters to the handler as request headers:


    - `x-param-query-<name>` — a query-string parameter (`?name=value`)

    - `x-param-<name>` — a path parameter


    Every parameter documented as `in: query` or `in: path` below corresponds to
    one of those headers, and the header suffix is named in each parameter's
    description where it is not obvious.


    ## Authentication


    All operations require the caller's bearer token; the account id, user id
    and user public key are always taken from the JWT and never from the URL or
    body. Endpoints that additionally require an account **admin** role are
    marked in their description — a failed role lookup answers **502**, never
    403 and never a pass.


    ## Two path notes


    - `PATCH /hub/agent-session-visibility/{session_id}` — the handler reads the
    path parameter as `x-param-session_id`, matching its sibling `PATCH
    /hub/agent-session/{session_id}`.

    - `GET|POST|PUT /hub/agent/user-context/{id}` — the handler requires the
    **agent id** as `x-param-id`; the frontend calls
    `/hub/agent/user-context/<agentId>`.
servers:
  - url: https://api.quiva.ai
    description: Production API server
security:
  - bearerAuth: []
  - apiKeyAuth: []
tags:
  - name: Skills
  - name: Todos
  - name: Memory
  - name: Profile and personality
  - name: Corrections
  - name: Environment
  - name: Models
paths:
  /hub/coworker/skills:
    get:
      tags:
        - Skills
      summary: List builtin and user-defined skills
      description: >-
        Returns the builtin skill catalog, the account's disabled-builtin list,
        and the account's user-defined skills. A fresh account (no aggregate
        yet) returns empty `disabled_builtins` and `skills` rather than an
        error. Subject: `microstrate.hub.get.coworker-skills`.
      operationId: getCoworkerSkills
      responses:
        '200':
          description: The account's skill registry
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetSkillsResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '502':
          $ref: '#/components/responses/UpstreamError'
components:
  schemas:
    GetSkillsResponse:
      type: object
      properties:
        builtins:
          type: array
          items:
            $ref: '#/components/schemas/BuiltinSkill'
        disabled_builtins:
          type: array
          items:
            type: string
        skills:
          type: array
          items:
            $ref: '#/components/schemas/SkillConfig'
    BuiltinSkill:
      type: object
      description: One platform-provided skill.
      properties:
        id:
          type: string
        name:
          type: string
        title:
          type: string
        description:
          type: string
        keywords:
          type: array
          items:
            type: string
        patterns:
          type: array
          items:
            type: string
        negative_patterns:
          type: array
          items:
            type: string
        tool_ids:
          type: array
          items:
            type: string
        always_on:
          type: boolean
        locked:
          type: boolean
          description: A locked builtin can never be disabled
    SkillConfig:
      type: object
      description: One user-defined skill.
      properties:
        id:
          type: string
          pattern: ^[a-z0-9][a-z0-9-]{1,62}$
          description: Lowercase slug, 2–63 characters, must not collide with a builtin id
        name:
          type: string
          maxLength: 80
          description: Required
        title:
          type: string
          description: Authored display name. Preserved when omitted.
        description:
          type: string
          maxLength: 2048
          description: >-
            Under the Agent Skills convention this carries the activation
            criteria, including negative ones
        keywords:
          type: array
          items:
            type: string
          maxItems: 50
          description: >-
            Zero keywords is allowed — a discovery-only skill, surfaced through
            discovery rather than fast-path activation
        patterns:
          type: array
          items:
            type: string
          maxItems: 20
          description: >-
            Each must compile as a Go regexp with a `(?i)` prefix — a bad regex
            is a 400 at write time, not a silent no-match later
        negative_patterns:
          type: array
          items:
            type: string
          description: Same compilation rule as `patterns`
        instruction:
          type: string
          description: SKILL.md-style body, at most 32 KiB
        tool_ids:
          type: array
          items:
            type: string
          description: No empty strings, no whitespace inside an id
        always_on:
          type: boolean
        resources:
          type: array
          items:
            type: string
          description: >-
            Server-managed — set only by the skill file endpoints; whatever a
            client sends is ignored
          readOnly: true
        disabled:
          type: boolean
        source:
          type: string
          enum:
            - builtin
            - user
          description: Server-managed — always forced to `user` on write
          readOnly: true
        exec_approved:
          type: boolean
          description: >-
            Per-skill half of the script-execution consent. Cleared when
            omitted.
        license:
          type: string
          description: Frontmatter. Preserved when omitted.
        compatibility:
          type: string
          description: Frontmatter. Preserved when omitted.
        metadata:
          type: object
          additionalProperties:
            type: string
          description: Frontmatter. Preserved when omitted.
        allowed_tools:
          type: array
          items:
            type: string
          description: Frontmatter. Preserved when omitted.
        env:
          type: array
          items:
            $ref: '#/components/schemas/EnvDeclaration'
          description: What this skill declares it needs. Preserved when omitted.
        approved_env:
          type: array
          items:
            type: string
          description: >-
            Which declared names a human granted. **Cleared when omitted**, and
            always narrowed to the intersection with `env` — an approval must
            never outlive the declaration it was given against.
        catalog_id:
          type: string
          description: >-
            Catalogue provenance (`owner/repo#skillname`), set once at install.
            Preserved when omitted.
        source_repo:
          type: string
          description: Catalogue provenance. Preserved when omitted.
        enrichment:
          $ref: '#/components/schemas/SkillEnrichment'
      required:
        - name
    Error:
      type: object
      description: The unwrapped error body. The HTTP status carries the code.
      properties:
        error:
          type: string
      required:
        - error
    EnvDeclaration:
      type: object
      description: >-
        One environment variable a skill or MCP server declares it needs. A
        declaration, never a grant — the approval is a separate human act
        recorded in `approved_env`.
      properties:
        name:
          type: string
          description: '`^[A-Z_][A-Z0-9_]*$`, not platform-reserved'
        description:
          type: string
        is_required:
          type: boolean
        is_secret:
          type: boolean
          description: >-
            When true, any `default` is dropped on write so a plaintext
            credential cannot ride in
        format:
          type: string
        default:
          type: string
      required:
        - name
    SkillEnrichment:
      type: object
      description: >-
        Server-managed provenance for generated keywords/patterns. Ignored on
        input and rebuilt from what is stored.
      properties:
        version:
          type: integer
          description: Generator version
        model:
          type: string
        enriched_at:
          type: string
          format: date-time
        source_hash:
          type: string
          description: Fingerprint of the generator's input fields
        keywords_source:
          type: string
          enum:
            - generated
            - manual
        patterns_source:
          type: string
          enum:
            - generated
            - manual
        generated_keywords:
          type: array
          items:
            type: string
        generated_patterns:
          type: array
          items:
            type: string
        probe_queries:
          type: array
          items:
            type: string
          description: Natural-language messages that should activate this skill
  responses:
    Unauthorized:
      description: No account (or user) identity in the auth context
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    UpstreamError:
      description: >-
        A backend read or write failed — deliberately not degraded to an empty
        or default answer
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
    apiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.