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

# Agent kit

> Help AI agents find and use Valendata on their own: llms.txt, the Valendata Agent Skill, and the Claude Code plugin.

Three things let an AI agent discover Valendata and use it without help. Each one points to the pages it needs, so it never goes stale.

## llms.txt

Agents that read [llms.txt](https://llmstxt.org) find Valendata in two places:

| File | What it holds |
| - | - |
| `https://valendata.com/llms.txt` | A short map: the API base, how to sign in, how to find, run, and create a skill, and links to the pages below. |
| `https://docs.valendata.com/llms.txt` | Every docs page with a one-line summary. |
| `https://docs.valendata.com/llms-full.txt` | All docs pages in one file. |

Any docs page also reads as Markdown: add `.md` to its URL.

## The Valendata Agent Skill

`skills/valendata/SKILL.md` is an [Agent Skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview). It loads when a task needs data from a website, and teaches the agent to:

1. Find a skill for the task with `GET /v1/marketplace/search?q=` (MCP tool: `search_skills`). No key is needed for the public marketplace. Add `kind=workflow` to find a workflow (MCP tool: `search_workflows`).
2. Read its inputs, sample rows, and price, in the search result or with [Get a skill](/api-reference/skills/get) or [Get a workflow](/api-reference/workflows/get).
3. Clone one that is not yours with [Clone a skill](/api-reference/skills/clone) or [Clone a workflow](/api-reference/workflows/clone) (MCP tools: `clone_skill`, `clone_workflow`). A public skill never runs directly: the API answers `403` `clone_required`.
4. Run the copy and wait, or start it in the background and poll. See [Run a skill](/guides/run-a-skill).
5. Handle `402`, `429`, and `needs_user`. See [Errors and limits](/api-reference/errors).
6. Create a skill when none fits. See [Create a skill](/guides/create-a-skill#from-a-sentence).

It uses the [MCP tools](/ai-assistants/mcp-tools) when they are connected, and the API with your key when they are not.

## The Claude Code plugin

The agent kit is also a Claude Code plugin. It adds the skill above and the Valendata MCP server, signed in with an API key.

1. Make an [API key](/account/api-keys) with only the scopes the agent needs. Add `workflows:read` and `workflows:invoke` if it should use workflows, and `skills:write` if it should create skills.

2. Set it in your shell before you start Claude Code:

   ```bash theme={null}
   export VALENDATA_API_KEY="vd_sk_YOUR_API_KEY"
   ```

3. In Claude Code, add the kit as a marketplace and install the plugin:

   ```text theme={null}
   /plugin marketplace add <path-or-repo-of-the-agent-kit>
   /plugin install valendata@valendata
   ```

4. Run `/mcp` to check that `valendata` is connected.

To sign in with OAuth instead of a key, or to connect another assistant, see [Connect your AI assistant](/ai-assistants/connect).


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