> ## Documentation Index
> Fetch the complete documentation index at: https://docs2.growthbook.io/llms.txt
> Use this file to discover all available pages before exploring further.

# GrowthBook Agent Skills

> Run the full feature-flag and experiment lifecycle from your AI coding agent. Install the GrowthBook Agent Skills for Claude Code, Cursor, and other agents. No MCP server required.

[Agent Skills](https://docs.claude.com/en/docs/agents-and-tools/agent-skills/overview) are folders of instructions, scripts, and resources that an AI agent loads on demand to carry out a specialized task. Anthropic introduced the format, and it works in any agent that follows the [Agent Skills standard](https://agentskills.io), including Claude Code, Cursor, and Codex.

GrowthBook publishes a library of them that runs the entire feature flag and experiment lifecycle from your AI coding agent (create a flag, roll it out, run an experiment, read the results, and clean up afterward) without leaving your editor and **without running an MCP server**.

Each skill is a playbook your agent follows: it knows the GrowthBook REST API, the right order of operations, and the guardrails (draft → review → publish, safe rollouts, two-step deletes) that keep changes safe.

<Info>
  **Open source**

  The skills live at [github.com/growthbook/skills](https://github.com/growthbook/skills) and call the [GrowthBook REST API](/app/api) directly through a small bundled helper.
</Info>

Watch GrowthBook's Head of Experimentation, Luke Sonnet, run an experiment end-to-end using skills.

<Frame>
  <iframe width="560" height="315" style={{aspectRatio: "16/9", width: "100%", height: "auto", marginBottom: "1rem"}} src="https://www.youtube.com/embed/FJG9Q5YsnVs" title="YouTube video player" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerPolicy="strict-origin-when-cross-origin" allowFullScreen />
</Frame>

## Prerequisites

* **A GrowthBook account:** [GrowthBook Cloud](https://app.growthbook.io) or a self-hosted instance.
* **A Personal Access Token (PAT):** create one at [**Account** → **Personal Access Tokens**](https://app.growthbook.io/account/personal-access-tokens). The token is tied to your GrowthBook user, so flags and experiments the skills create are attributed to you automatically.
* **Node.js 18+:** check with `node -v`. Many agents already run on it.

## Installation

### 1. Install the plugin

<Tabs>
  <Tab title="Claude Code">
    Add the marketplace, then install the plugin:

    ```text theme={null}
    /plugin marketplace add growthbook/skills
    /plugin install growthbook@growthbook-skills
    ```
  </Tab>

  <Tab title="Cursor, Codex, and others">
    Install with the [Agent Skills](https://agentskills.io) CLI:

    ```bash theme={null}
    npx skills add growthbook/skills
    ```

    Restart your agent if the skills don't appear right away.
  </Tab>
</Tabs>

### 2. Configure your credentials

Run the setup skill and follow the prompts:

```text theme={null}
/growthbook:gb-setup
```

It asks for your PAT or API key (and, for self-hosted, your API URL), validates them against the live API, and writes `~/.config/growthbook/.env` with `chmod 600`. Every other skill reads that file automatically.

<Tip>
  **Prefer environment variables?**

  The skills read environment variables first and only fall back to the file. Export them instead if you like. Handy for CI:

  ```bash theme={null}
  export GB_API_KEY=<your-key>             # required: PAT or Secret Key
  export GB_API_URL=https://api.your-host  # self-hosted only
  ```
</Tip>

### 3. Verify

```text theme={null}
/growthbook:flag-search
```

This should list your existing feature flags. If something's off with the credentials, the error points you back to `/growthbook:gb-setup`.

## How skills work

Skills fire two ways:

* **Automatically**, when your agent detects matching intent: "create a feature flag for the pricing page" runs `flag-create`; "what should we test next?" runs `experiment-brainstorm`.
* **Explicitly**, by typing the slash command, e.g. `/growthbook:flag-search` or `/growthbook:experiment-launch`.

Because each skill names its trigger phrases and routes to sibling skills, they compose cleanly when chained:

* **Flag-first:** `flag-create` → `flag-toggle` → `flag-targeting` → `flag-ramp` / `flag-monitoring` → `flag-cleanup`
* **Experiment-first:** `experiment-design` → `experiment-launch` → `experiment-analyze` → `experiment-stop` → `flag-cleanup`
* **Experiment on an existing flag:** `flag-experiment` → `experiment-launch` → `experiment-stop` → `flag-cleanup`

## What's included

The skills fall into three groups. The two reference pages list each one with an example prompt you can run.

* **Setup** — `gb-setup` configures and validates your API credentials.
* **[Feature flag skills](/integrations/ai-agents/agent-skills/feature-flags)** — create, target, roll out, ramp, monitor, review, publish, search, and clean up flags across their full lifecycle.
* **[Experiment skills](/integrations/ai-agents/agent-skills/experiments)** — brainstorm, design, launch, analyze, and stop A/B tests.

## Example prompts

* "Create a boolean flag `new-checkout-flow` that defaults to `false`, then roll it out to 10% of US users."
* "What feature flags are stale and safe to clean up?"
* "Design an A/B test for the new pricing page and launch it on the `pricing-v2` flag."
* "What are the results of our checkout experiment? Should we ship the winner?"
* "Stop the `homepage-hero` experiment and roll the winning variation out to everyone."

## Safety and governance

The skills follow GrowthBook's built-in safeguards:

* **Draft → review → publish.** Every flag change is staged on a draft revision. Skills route through `flag-review` and `flag-publish` so approvals and merge conflicts are handled the same way they are in the app. See [Publishing & approval flows](/features/publishing-and-approval-flows).
* **Two-step deletes.** `flag-cleanup` archives a flag, pauses for you to verify nothing broke, and only then deletes. It won't collapse those steps.
* **Read-only by default where it matters.** `flag-search`, `flag-graph`, `experiment-brainstorm`, `experiment-design`, and `experiment-analyze` never write.
* **Secrets stay local.** `gb-setup` writes your key to a `0600` file and recommends a scoped PAT you can revoke independently.

## Next steps

* [Feature flag skills](/integrations/ai-agents/agent-skills/feature-flags): the full flag catalog
* [Experiment skills](/integrations/ai-agents/agent-skills/experiments): design, launch, analyze, and stop tests
* [Agent Skills vs. the MCP Server](/integrations/ai-agents)
* [GrowthBook REST API](/app/api), which the skills call under the hood
* [Skills source on GitHub](https://github.com/growthbook/skills)

[Join our community Slack for additional help, tips, and announcements](https://join.slack.com/t/growthbookusers/shared_invite/zt-2xw8fu279-Y~hwnfCEf7WrEI9qScHURQ)