> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs-beta.getzep.com/v4/sdk-reference/agent/skills/list/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs-beta.getzep.com/_mcp/server.

# List Agent Skills

POST https://api.getzep.com/api/v4/agents/{agent_uuid}/skills/list
Content-Type: application/json

Reference: https://docs-beta.getzep.com/sdk-reference/agent/skills/list

## Authentication

- `Authorization` header (required) (prefixed with ` Api-Key  `) — Type "Api-Key" followed by a space and the project API key.

## Request

### Path parameters

- `agent_uuid` (string, required) — Agent UUID

### Query parameters

- `limit` (integer, optional) — Page size (maximum 20)
- `cursor` (string, optional) — Opaque page cursor

### Body (application/json)

This endpoint expects a v4.AgentSkillListRequest.

- `environments` (list of string, optional)
- `kind` (string, optional)
- `task_family` (string, optional)
- `tools` (list of string, optional)

## Response

### 200

OK

- `items` (list of v4.AgentSkillSearchHit, optional)
- `next_cursor` (string, optional)
- `total_size` (integer, optional)

## Errors

### 400 Bad Request Error

Bad Request

- `error` (v4.ErrorBody, optional)

### 401 Unauthorized Error

Unauthorized

- `error` (v4.ErrorBody, optional)

### 403 Forbidden Error

Forbidden

- `error` (v4.ErrorBody, optional)

### 404 Not Found Error

Not Found

- `error` (v4.ErrorBody, optional)

### 503 Service Unavailable Error

Service Unavailable

- `error` (v4.ErrorBody, optional)

## Types

### v4.AgentSkillSearchHit

- `agent_versions` (list of string, optional)
- `description` (string, optional)
- `environments` (list of string, optional)
- `kind` (string, optional)
- `markdown` (string, optional)
- `maturity` (enum, optional) — Maturity is the trust tier of the Skill: provisional (one source attempt family), corroborated (two or more), established (a Trust of 0.6 or more from verified applications), or authored (no compiled source).
  - Allowed values: `provisional`, `corroborated`, `established`, `authored`
- `name` (string, optional)
- `package_name` (string, optional)
- `self_contained` (boolean, optional)
- `skill_id` (string, optional)
- `source_attempt_families` (integer, optional) — SourceAttemptFamilies is the count of distinct, successful, verified attempt families that support the current version.
- `task_family` (string, optional)
- `tools` (list of string, optional)
- `trust` (double, optional) — Trust is the lower bound of the 95% Wilson score interval for the success rate of strongly verified applications of the Skill. It is 0 when the Skill has no verified application.
- `uuid` (string, optional)
- `verified_applications` (integer, optional) — VerifiedApplications is the count of strongly verified applications that end in success or failure.
- `version` (integer, optional)

### v4.ErrorBody

- `code` (string, optional)
- `details` (map from string to any, optional)
- `message` (string, optional)
- `param` (string, optional)
- `request_id` (string, optional)

## Examples

**Request**

```json
{}
```

**Response**

```json
{
  "items": [
    {
      "agent_versions": [
        "string"
      ],
      "description": "string",
      "environments": [
        "string"
      ],
      "kind": "string",
      "markdown": "string",
      "maturity": "provisional",
      "name": "string",
      "package_name": "string",
      "self_contained": true,
      "skill_id": "string",
      "source_attempt_families": 1,
      "task_family": "string",
      "tools": [
        "string"
      ],
      "trust": 0.61,
      "uuid": "string",
      "verified_applications": 6,
      "version": 1
    }
  ],
  "next_cursor": "string",
  "total_size": 1
}
```