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

# 查询单个 skill 元数据

> 返回指定 skill 的元数据和入参 JSON Schema。构造调用前可用它确认参数。



## OpenAPI

````yaml /openapi.json get /skills/{skill_key}
openapi: 3.1.0
info:
  title: DropCV Skills API
  version: 1.0.0
  description: >-
    DropCV 对外开放的人才库能力接口。所有能力（skill）走统一的调用形态：


    `POST /skills/{skill_key}/invoke`


    用 API Key 鉴权（`Authorization: Bearer drop_cv_...`）。同一套能力也通过 MCP Server 和
    `@dropcv/cli` 命令行暴露。
servers:
  - url: https://api.dropcv.work/api/external/v1
    description: 生产环境
security:
  - ApiKeyAuth: []
paths:
  /skills/{skill_key}:
    get:
      tags:
        - Skills
      summary: 查询单个 skill 元数据
      description: 返回指定 skill 的元数据和入参 JSON Schema。构造调用前可用它确认参数。
      operationId: getSkill
      parameters:
        - name: skill_key
          in: path
          required: true
          description: skill 标识
          schema:
            type: string
            enum:
              - candidate_search
              - candidate_profile_read
              - jd_parse
              - save_candidate
              - candidate_update
      responses:
        '200':
          description: skill 元数据
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SkillMeta'
        '404':
          description: skill_key 不存在
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorEnvelope'
components:
  schemas:
    SkillMeta:
      type: object
      description: skill 的元数据。
      properties:
        key:
          type: string
          description: skill 标识
          example: candidate_search
        name:
          type: string
          description: 人类可读名称
          example: 人才库搜索
        description:
          type: string
          description: 功能描述
        input_schema:
          type: object
          description: params 的 JSON Schema（由 Pydantic 反射生成）
        requires_write_scope:
          type: boolean
          description: 调用是否需要 API Key 的 write 权限
    ErrorEnvelope:
      type: object
      properties:
        success:
          type: boolean
          const: false
        skill_key:
          type:
            - string
            - 'null'
          example: candidate_search
        invocation_id:
          type: string
          example: inv_01HXXXXXXXXXXXXXXXXXXXXXXX
        error:
          type: object
          properties:
            code:
              type: string
              description: 封闭错误码枚举
              enum:
                - INVALID_API_KEY
                - INSUFFICIENT_PERMISSION
                - SKILL_NOT_FOUND
                - CANDIDATE_NOT_FOUND
                - FILE_NOT_FOUND
                - INVALID_PARAMS
                - BUSINESS_ERROR
                - INTERNAL_ERROR
            message:
              type: string
              description: 人类可读错误说明
  securitySchemes:
    ApiKeyAuth:
      type: http
      scheme: bearer
      description: DropCV API Key。在 设置 → API Keys 生成，格式 drop_cv_<32 位随机字符>。

````