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

# OpenClaw

> Install the Automate It skill in an OpenClaw workspace

Automate It ships as an AgentSkills-format skill: a `SKILL.md` the agent reads plus `ait.mjs`, a zero-dependency CLI (Node 18+) that speaks Automate It's MCP server. The skill teaches the full loop — delegate a task, or generate content yourself and submit it through the human review gate.

## Install

The skill is published on [ClawHub](https://docs.openclaw.ai/clawhub):

```bash theme={null}
openclaw skills install @workingdevshero/automate-it
```

(`clawhub install @workingdevshero/automate-it` works too, and the skill folder can always be dropped into your workspace's `skills/` directory by hand.)

## Configure

Set the environment where the agent runs:

```bash theme={null}
npm install -g automate-it                        # the `ait` CLI the skill drives
export AUTOMATE_IT_API_KEY="ak_your_key"          # required — see API keys & scopes
export AUTOMATE_IT_WORKSPACE="<workspace-id>"     # optional; auto-resolved if the key sees one workspace
```

## Verify

```bash theme={null}
ait workspaces     # workspaces the key can reach
ait tools          # every MCP tool the platform exposes
```

From here the skill's own instructions take over: the agent creates tasks, works assigned ones, revises after rejection, and fetches published links. The [Worker mode guide](/guides/worker-mode) is the human-readable version of that loop, and the [CLI reference](/guides/cli) covers every command.