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

# Evaluations for Agents

> Give your AI coding agents the tools and knowledge to evaluate AI quality through Skills, MCP, CLI, or API.

Coval works with any AI coding agent. Whether you use Claude Code, Cursor, Windsurf, Codex, or another tool, your agent can run evaluations, manage test sets, and score AI outputs through the interface that fits your workflow.

## Get Started

<CardGroup cols={2}>
  <Card title="Agent Skills" icon="graduation-cap" href="/agents/skills">
    Install evaluation expertise with one command. Your agent learns how to build test sets, select metrics, and run evals.
  </Card>

  <Card title="Guided Onboarding" icon="wand-magic-sparkles" href="/agents/onboarding">
    Run `/onboard` and your agent walks you through setting up a complete evaluation from scratch.
  </Card>

  <Card title="MCP Server" icon="plug" href="/mcp/overview">
    Connect the Coval MCP server for native tool access in Claude Desktop, Cursor, and other MCP clients.
  </Card>

  <Card title="CLI" icon="terminal" href="/cli/overview">
    The Coval CLI gives agents structured JSON output for scripting evaluations in any terminal.
  </Card>
</CardGroup>

## Three Ways Agents Use Coval

| Layer            | What It Does                                          | Install                                         |
| ---------------- | ----------------------------------------------------- | ----------------------------------------------- |
| **Agent Skills** | Teaches agents *how* to evaluate well (knowledge)     | `npx skills add coval-ai/coval-external-skills` |
| **MCP Server**   | Gives agents *tools* to execute evaluations           | `npx coval-mcp`                                 |
| **CLI**          | Runs evaluations from *any terminal* with JSON output | `brew install coval-ai/tap/coval`               |

Skills and MCP are complementary — Skills give your agent the expertise to design good evaluations, while MCP and CLI let it execute them. Use whichever combination fits your workflow.

## Supported Agents

<CardGroup cols={3}>
  <Card title="Claude Code" icon="terminal">
    Skills + MCP + CLI
  </Card>

  <Card title="Cursor" icon="code">
    Skills + MCP
  </Card>

  <Card title="Windsurf" icon="wind">
    Skills + MCP
  </Card>

  <Card title="Codex" icon="robot">
    Skills + CLI
  </Card>

  <Card title="GitHub Copilot" icon="github">
    CLI + API
  </Card>

  <Card title="Any Agent" icon="globe">
    CLI + API
  </Card>
</CardGroup>

## AI-Readable Documentation

Coval publishes machine-readable documentation following the [llms.txt standard](https://llmstxt.org):

* **[llms.txt](https://docs.coval.ai/llms.txt)** — Curated index of all documentation pages (\~7KB)
* **[llms-full.txt](https://docs.coval.ai/llms-full.txt)** — Complete documentation in a single file (\~386KB)

Point your agent at these files when it needs context about Coval's platform, API, or concepts.