coderabbit-config — Claude Code skill: setup and installation
The coderabbit-config Claude Code skill creates, edits, and validates CodeRabbit repository settings through its official CLI. It activates for .coderabbit.yaml or .coderabbit.yml requests, review-style changes, and path guidance.
MIT 563 installs ★ 224 updated 2026-10-22
npx skills add coderabbitai/skills --skill coderabbit-config -a claude-codeWhat coderabbit-config does
The skill uses the CLI to inspect repository settings, generate changes, validate the schema, and preview a diff before saving. It does not edit YAML directly. Review-style changes can use the chill, quiet, assertive, or default profile.
The workflow requires the official CLI with config protocol v2 support, a Git working tree, and network access to the current schema. Settings are saved locally, so a CodeRabbit login and a review run are not required. A local save does not activate settings for hosted PR reviews.
What it helps with
- validate a repository’s
.coderabbit.yaml - create CodeRabbit settings for a Git repository
- change the review style with a CLI profile
- configure review paths through the interactive flow
Example prompts for the agent
- Validate the CodeRabbit settings in this repository.
- Set the review style to
quietin.coderabbit.yamland show the diff before saving. - Configure CodeRabbit review paths through the interactive flow.
How to install coderabbit-config
1Skills CLI (Vercel)
npx skills add coderabbitai/skills --skill coderabbit-config -a claude-code2Manually: put the files in place
~/.claude/skills/coderabbit-config/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/coderabbit-config/
1Skills CLI (Vercel)
npx skills add coderabbitai/skills --skill coderabbit-config -a codex2Manually: put the files in place
.agents/skills/coderabbit-config/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add coderabbitai/skills --skill coderabbit-config -a cursor2Manually: put the files in place
.cursor/skills/coderabbit-config/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install coderabbitai/skills skills/coderabbit-config2Manually: put the files in place
.github/skills/coderabbit-config/SKILL.md1Skills CLI (Vercel)
npx skills add coderabbitai/skills --skill coderabbit-config -a gemini-cli2Platform CLI
gemini skills install https://github.com/coderabbitai/skills --path skills/coderabbit-configManually: put the files in place
.devin/skills/coderabbit-config/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add coderabbitai/skills --skill coderabbit-config -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about coderabbit-config
How do I install coderabbit-config in Claude Code?
Run npx skills add coderabbitai/skills --skill coderabbit-config -a claude-code. The skill file is available at ~/.claude/skills/coderabbit-config/SKILL.md.
What does coderabbit-config do?
It creates, edits, and validates CodeRabbit repository configuration through the CLI. The workflow previews changes before saving and leaves YAML editing to the CLI.
What does coderabbit-config need to run?
It requires the official CLI with config protocol v2 support, a Git working tree, and network access to the current configuration schema.
Source text
SKILL.md · MIT
--- name: coderabbit-config description: Create, update, or validate CodeRabbit repository configuration through the official CLI. Use for .coderabbit.yaml or .coderabbit.yml setup, review-style changes, path guidance, and configuration validation requests. metadata: version: "0.1.0" --- # CodeRabbit Configuration Requires config protocol v2, a Git working tree, and network access to the current configuration schema. Keep configuration generation, schema validation, previews, and repository writes in the CLI. Do not edit repository YAML yourself, copy a schema, or implement a fallback editor. Configuration is local; it does not need CodeRabbit login or start a review. ## Find the CLI and requested repository Use the intended Git working tree for every invocation. Select the installed workflow before looking for a standalone CLI: - The native Claude source plugin uses the standalone CLI discovery below. Its remote MCP connection does not provide a managed local runtime. - For another installed package that explicitly declares a managed runtime, use its verified launcher and preparation instructions. - For standalone installs, resolve an official installed `coderabbit` to a quoted canonical absolute path, checking PATH and the documented installer location `~/.local/bin/coderabbit` on macOS/Linux. Reject repository-local executables, aliases, and unknown wrappers. If the installation source is uncertain, ask the user to identify their installation. A source checkout's `cli.json` alone does not select a managed runtime. The `<cli>` examples below mean that verified executable, not a literal command. Check `<cli> --version`, `<cli> config --help`, and support for the needed subcommands. CLI 0.9.3 supports this workflow. Missing commands or an unsupported protocol require an upgrade. For a standalone CLI, follow the [official installation instructions](https://docs.coderabbit.ai/cli) for its actual installation method (for example, `brew upgrade coderabbit` for Homebrew). For a managed runtime, update the plugin to a version with a compatible pinned CLI and follow its preparation instructions; never run `<cli> update` on the managed launcher. Do not install or upgrade without authorization. Preserve permission and network errors as such; they do not prove an upgrade is needed. After any upgrade, repeat trusted executable discovery and verification, then recheck version and command support. Do not reuse the old canonical path: an upgrade can replace a versioned installation directory or managed launcher. ## Validate only Run `<cli> config validate --agent` for the repository configuration, or `<cli> config validate <file> --agent` for the user's explicitly selected YAML file. Require exit zero and `ok: true`; report the CLI's validation diagnostics otherwise. Do not generate or apply changes for a validation-only request. ## Create or change review style 1. Run `<cli> config --agent`. Require exit zero, `ok: true`, `protocolVersion: 2`, `operation: inspect`, and `writable: true`. Preserve the returned repository root, target, and `baseHash` (`none` for a new file). Respect authority warnings, including TypeScript, remote configuration, symlinks, and multiple YAML files; do not delete or bypass them. 2. Run `<cli> config --agent --generate`. For a requested style, add `--profile chill` (Balanced), `--profile quiet` (Focused), `--profile assertive` (Thorough), or `--profile default` (remove the local style override). Without a profile, the CLI generates its baseline for a new file and preserves an existing file. Do not infer a style change from a general request to check configuration. 3. Require a successful protocol-v2 `operation: generate` response with the inspected target and base hash. Copy its exact `after` string into a temporary proposal file outside the repository; do not rewrite or extend that YAML. 4. Preview with `<cli> config apply <proposal> --agent --dry-run --base <baseHash>`. Require exit zero and a successful protocol-v2 `operation: apply` result. If unchanged, re-inspect the same base hash and report that no save is needed. Otherwise show the returned before/after diff and obtain approval for it. 5. Save the same proposal with `<cli> config apply <proposal> --agent --yes --base <baseHash>`. Require a successful protocol-v2 result with `applied: true`. Re-inspect and verify the target and saved hash against the approved `proposedHash`, then report the local change. Remove your temporary proposal; preserve any CLI-reported recovery file. On changed input, inspect and preview again instead of bypassing the base hash. On schema, validation, permission, or network errors, report the diagnostic and stop without an alternate writer. An interrupted save has an unknown outcome: inspect the file before retrying or reporting success. ## Guided path settings For path-guidance requests, run `<cli> config --detailed` in an interactive terminal to enter the manual review-style and path-guidance flow directly. For general interactive setup, use `<cli> config` or `<cli> config --generate`. Relay the CLI's actual prompts and preview, using settled user preferences and asking for missing choices. Confirm the displayed changes only after approval. If the host cannot interact with a terminal, give the user the exact command to run in the selected repository and resume after they finish. Do not simulate the wizard with piped answers. For settings the installed CLI cannot edit, explain the capability gap instead of inventing flags or editing YAML yourself. After a successful save, validate and inspect the resulting configuration. Saving locally does not activate settings on hosted PR reviews. Commit, push, dashboard changes, and running a review require their own user-requested scope.
© coderabbitai · MIT · coderabbitai/skills