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

# CodeRabbit Skills

> Install agent-native skills to trigger AI-powered code reviews using natural language.

## Overview

**Skills** are a standardized format for packaging AI agent capabilities as structured Markdown files (`SKILL.md`). Each skill describes a capability — its purpose, usage triggers, and the steps the agent should follow to execute it. This gives AI agents a consistent, discoverable, interoperable way to understand and invoke external tools without manual configuration. You can learn more about the open standard at [agentskills.io](https://agentskills.io/what-are-skills).

CodeRabbit Skills are open-source, agent-installable capabilities built on this standard — browse and contribute at [github.com/coderabbitai/skills](https://github.com/coderabbitai/skills). With these skills, any compatible agent can trigger a full review without explanations on how to run specific console commands.

<Info>
  **Skills vs. manual CLI integration**

  Skills are a standardized, installable capability — a structured way for agents to discover and invoke tools. Manual CLI integration (covered in the [agent integration guides](/cli/index#integration-guides)) means directly prompting your agent to run `coderabbit` CLI commands. The two approaches are complementary: skills provide a consistent, zero-configuration trigger mechanism on top of the same underlying CLI.
</Info>

Skills complement the existing agent integrations documented in the [CLI section](/cli/index). You can use skills alongside manual CLI workflows or as a replacement when you want a more natural, language-driven interface.

## Prerequisites

Before installing skills with `coderabbit skills`, make sure the CodeRabbit CLI is installed. Authentication is not required to install or update skills; authenticate before using a skill to start a CodeRabbit review.

Install the CodeRabbit CLI:

<Tabs>
  <Tab title="Install script">
    ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
    curl -fsSL https://cli.coderabbit.ai/install.sh | sh
    ```

    If `coderabbit` is not available immediately after installation, start a new shell, or run the exact shell-specific reload command printed under **Next steps**. If the install script offers browser sign-in without first asking for a region, EU users should skip it and authenticate later with an explicit `--region eu`.
  </Tab>

  <Tab title="Homebrew">
    ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
    brew install coderabbit
    ```

    If `coderabbit` is not available immediately after installation, start a new shell.
  </Tab>

  <Tab title="Windows">
    ```powershell PowerShell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
    irm https://cli.coderabbit.ai/install.ps1 | iex
    ```

    See [Install CodeRabbit CLI on Windows](/cli/windows) for prerequisites, version pinning, and troubleshooting. If `coderabbit` is not available immediately after installation, open a new PowerShell window.
  </Tab>
</Tabs>

For full CLI setup instructions, see the [CLI overview](/cli/index).

## Supported agents

The CodeRabbit CLI detects and installs user-level skills for Codex, Claude Code, Cursor, Gemini CLI, and GitHub Copilot. The package-runner alternative supports 35+ compatible agents; see the [coderabbitai/skills repository](https://github.com/coderabbitai/skills) for the complete list.

<Info>
  If you prefer to configure agent integrations manually, see the dedicated guides for [Claude Code](/cli/claude-code-integration), [Cursor](/cli/cursor-integration), [Codex](/cli/codex-integration), and [Gemini CLI](/cli/gemini-integration).
</Info>

## Install or update skills

Use the first-party CodeRabbit CLI command for supported agents:

```bash theme={null}
coderabbit skills
```

The command:

1. Downloads the latest published `coderabbitai/skills` release and verifies its release manifest and checksums.
2. Detects supported coding agents already installed on your machine.
3. Shows every planned install or update, including the exact destination paths and anything it will leave unchanged.
4. Asks once for confirmation, defaulting to **No**, before writing any skill files.

Check `coderabbit skills --help` before using the agent flow below. If it does not list `--agent` and `--confirm`, including on CLI 0.7.6, run `coderabbit skills` in an interactive terminal. On those versions, a non-interactive invocation does not install or update skill files, although it can clean stale CLI ownership records before it stops.

<Info>
  CLI 0.7.6 cannot reliably update automatically. If you choose to upgrade, run `coderabbit update` (Homebrew: `brew upgrade coderabbit`), then verify with `coderabbit --version`. For an organization-managed or self-hosted installation, use your administrator's update process. Existing reviews do not require an upgrade to continue.
</Info>

### Set up skills from an agent

On versions that list the agent options in `coderabbit skills --help`, a detected coding agent receives a preview without writing skill files or ownership state. If detection is unavailable or ambiguous, request the preview explicitly:

```bash theme={null}
coderabbit skills --agent
```

The output contains a readable plan followed by an `action_required` JSON record with `status: "awaiting_confirmation"` when changes are available. It is not an NDJSON stream. The agent must show the complete plan to the user, including destination paths, replacements of local modifications, and refreshes of externally managed files.

Only after the user explicitly approves that plan, the agent runs the confirmation command returned in the preview:

```bash theme={null}
coderabbit skills --confirm <plan-hash>
```

Confirmation works without an interactive terminal and applies only to the unchanged plan. A changed release, destination, ownership, or file fingerprint requires a new preview and approval. If the user declines, the agent stops without running the confirmation command. Agent detection and a successful preview do not authorize installation.

Here, `coderabbit skills --agent` requests an approval preview. The package runner's `skills add --agent <name>` option selects an installation target; it is a separate command with separate prompts and ownership.

### Updates and existing installations

The CLI safely reconciles existing CodeRabbit skills:

* Missing and outdated CLI-managed skills are offered for installation or update.
* Locally modified CLI-managed copies can be replaced after the CLI shows the affected paths and you confirm the change.
* Verified global installs managed by the package runner, and verified Cursor plugin installs, can be refreshed after confirmation. Their original installer retains ownership and may replace them later.
* Skills from the official CodeRabbit plugins for Codex and Claude Code are never replaced by `coderabbit skills`; update those through the plugin marketplace.
* Project-level and generic, unverifiable, ambiguous, duplicate, or cross-owner installations are left unchanged.

If a conflict is left unchanged, resolve it with the owning installer and run `coderabbit skills` again.

### Package-runner alternative

Use a package runner when you need project-scoped installation, agent-specific selection, or an agent outside the five supported directly by the CodeRabbit CLI:

<CodeGroup>
  ```bash npx theme={null}
  npx skills add coderabbitai/skills
  ```

  ```bash bunx theme={null}
  bunx skills add coderabbitai/skills
  ```

  ```bash pnpm theme={null}
  pnpm dlx skills add coderabbitai/skills
  ```

  ```bash yarn theme={null}
  yarn dlx skills add coderabbitai/skills
  ```
</CodeGroup>

#### Package-runner options

Customize how skills are installed with these flags:

| Flag | Purpose |
| - | - |
| `-g, --global` | Install to user directory instead of the current project |
| `-a, --agent` | Target a specific agent (for example, `-a claude-code`) |
| `-s, --skill` | Install a particular skill by name |
| `--all` | Install all skills to all agents without prompts |

<CodeGroup>
  ```bash npx theme={null}
  # Install for all detected agents in the current project
  npx skills add coderabbitai/skills

  # Install globally to your user directory
  npx skills add coderabbitai/skills -g

  # Install only for Claude Code
  npx skills add coderabbitai/skills -a claude-code
  ```

  ```bash bunx theme={null}
  # Install for all detected agents in the current project
  bunx skills add coderabbitai/skills

  # Install globally to your user directory
  bunx skills add coderabbitai/skills -g

  # Install only for Claude Code
  bunx skills add coderabbitai/skills -a claude-code
  ```

  ```bash pnpm theme={null}
  # Install for all detected agents in the current project
  pnpm dlx skills add coderabbitai/skills

  # Install globally to your user directory
  pnpm dlx skills add coderabbitai/skills -g

  # Install only for Claude Code
  pnpm dlx skills add coderabbitai/skills -a claude-code
  ```

  ```bash yarn theme={null}
  # Install for all detected agents in the current project
  yarn dlx skills add coderabbitai/skills

  # Install globally to your user directory
  yarn dlx skills add coderabbitai/skills -g

  # Install only for Claude Code
  yarn dlx skills add coderabbitai/skills -a claude-code
  ```
</CodeGroup>

The package runner installs `SKILL.md` files into `~/.agents/skills` or the selected agent's designated skills directory. Its prompts, flags, and ownership remain separate from `coderabbit skills`, even when the CLI offers to refresh a verified global package-runner installation.

## Available skills

### CodeRabbit review

The CodeRabbit review skill triggers a full CodeRabbit analysis of your current changes directly from an explicit natural-language request.

#### Triggering the skill

Activate the skill using natural language inside your AI agent:

* "Run a CodeRabbit review"
* "Review my changes with CodeRabbit"
* "Use CodeRabbit to check this branch"
* "Ask CodeRabbit to review my PR"

The agent reads the installed `SKILL.md` file and automatically invokes the CodeRabbit CLI.

#### How it works

When triggered, the agent will:

1. Check that the CodeRabbit CLI is installed and authenticated
2. Run the review on your current changes
3. Present findings grouped by severity — **Critical**, **Warning**, and **Info**
4. Optionally fix issues and re-review until the output is clean

#### CLI integration

The skill runs a CodeRabbit CLI review with structured agent output, selects the review scope from your request, and can compare changes against a base branch. The exact CLI flags are an implementation detail and may change independently of the skill's natural language interface.

#### Autonomous workflow

Skills enable a fully autonomous review-fix loop:

Implement → Review → Fix Critical/Warning issues → Re-review until clean

The agent continues iterating until no Critical or Warning issues remain, then provides a summary of everything that was fixed.

### `autofix`

The `autofix` skill fetches unresolved CodeRabbit review threads on your current branch's pull request and helps you apply fixes interactively or in batch.

<Info>
  The `autofix` skill additionally requires the [GitHub CLI (`gh`)](https://cli.github.com/) to locate pull requests, query review threads, and post comments. The skill will attempt to install `gh` automatically if it is not found, but GitHub authentication must be completed manually.
</Info>

#### Triggering the skill

Activate the skill using natural language inside your AI agent:

* "Autofix CodeRabbit comments"
* "Fix CodeRabbit review issues"
* "Review and fix CodeRabbit feedback"

The agent reads the installed `SKILL.md` file, finds your open PR, and pulls unresolved CodeRabbit review threads.

#### How it works

When triggered, the agent will:

1. Check local branch status and warn about uncommitted or unpushed changes
2. Locate the open pull request for the current branch
3. Fetch unresolved review threads authored by CodeRabbit
4. Extract issue metadata and fix prompts from each thread
5. Let you choose either review-each-fix mode or auto-fix-all mode
6. Apply selected fixes and create one consolidated commit
7. Prompt the user if the commit should be pushed upstream

#### CLI commands used by the skill

The skill relies on GitHub CLI plus Git commands:

| Command | Purpose |
| - | - |
| `gh pr list --head $(git branch --show-current) --state open --json number,title` | Find the open PR for the current branch |
| `gh api graphql ... pullRequest.reviewThreads ...` | Fetch unresolved CodeRabbit review threads |
| `gh pr comment <pr-number> --body "<summary>"` | Post a run summary after fixes are applied |
| `git add ... && git commit -m "fix: apply CodeRabbit auto-fixes"` | Create one consolidated commit |

#### Fix modes

The skill supports two fix paths:

* **Review each issue**: See each proposed fix and approve, defer, or modify it.
* **Auto-fix all**: Apply all eligible fixes in batch, prioritized from highest severity first.

In both modes, the skill uses CodeRabbit's "Prompt for AI Agents" (the agent-ready fix instruction) guidance from each unresolved thread as the fix specification.

## Troubleshooting

<AccordionGroup>
  <Accordion title="Skill not found">
    Verify that the skill has a `SKILL.md` file in the directory expected by your agent. Run `coderabbit skills` again for a supported CLI installation, or repeat the package-runner command that owns the existing installation.
  </Accordion>

  <Accordion title="Skill doesn't load in agent">
    Check two things:

    1. **Installation directory**: The skill file must be in the path your agent expects (see [Supported agents](#supported-agents)).
    2. **Frontmatter validity**: The `SKILL.md` file must have valid frontmatter. Run `coderabbit skills` to preview whether the CLI can safely update it; unverifiable or ambiguous conflicts are left unchanged.
  </Accordion>

  <Accordion title="Permission errors during install">
    If you encounter permission errors when writing to the project directory, try installing to your user directory instead:

    <CodeGroup>
      ```bash npx theme={null}
      npx skills add coderabbitai/skills -g
      ```

      ```bash bunx theme={null}
      bunx skills add coderabbitai/skills -g
      ```

      ```bash pnpm theme={null}
      pnpm dlx skills add coderabbitai/skills -g
      ```

      ```bash yarn theme={null}
      yarn dlx skills add coderabbitai/skills -g
      ```
    </CodeGroup>
  </Accordion>

  <Accordion title="&#x22;NOT_INSTALLED&#x22; error">
    This error means the CodeRabbit CLI is not installed or not on your `PATH`. Reinstall the CLI and then restart your shell:

    <Tabs>
      <Tab title="Install script">
        ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
        curl -fsSL https://cli.coderabbit.ai/install.sh | sh
        ```

        If `coderabbit` is not available immediately after installation, start a new shell, or run the exact shell-specific reload command printed under **Next steps**. If the install script offers browser sign-in without first asking for a region, EU users should skip it and authenticate later with an explicit `--region eu`.
      </Tab>

      <Tab title="Homebrew">
        ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
        brew install coderabbit
        ```

        If `coderabbit` is not available immediately after installation, start a new shell.
      </Tab>

      <Tab title="Windows">
        ```powershell PowerShell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
        irm https://cli.coderabbit.ai/install.ps1 | iex
        ```

        See [Install CodeRabbit CLI on Windows](/cli/windows) for prerequisites, version pinning, and troubleshooting. If `coderabbit` is not available immediately after installation, open a new PowerShell window.
      </Tab>
    </Tabs>
  </Accordion>

  <Accordion title="Authentication failures">
    Re-authenticate the CodeRabbit CLI:

    ```bash theme={null}
    coderabbit auth login
    ```

    For a first login to an EU-hosted CodeRabbit account, use `coderabbit auth login --region eu`. When no region is specified or saved, the CLI uses the US region.

    A browser window opens automatically. Sign in to CodeRabbit and the authentication completes in the browser.

    If you belong to multiple CodeRabbit organizations, the sign-in choice sets your default org only. Review attribution still depends on the current repository. See [Organization selection](/cli#organization-selection).
  </Accordion>
</AccordionGroup>

### Verification commands

Use these commands to confirm your CLI setup is working before filing a skills-related issue:

```bash theme={null}
# Check the installed CLI version
coderabbit --version

# Verify authentication status
coderabbit auth status
```

For detailed CLI troubleshooting, see the [CLI overview](/cli/index).


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