Index of every page on this site: llms.txt
All skills
coderabbitai avatar

/code-review

@d8e182b official
by CodeRabbitcoderabbitai/skills222 stars
25
Run it yourself

Run CodeRabbit CLI reviews, retrieve saved local or GitHub PR fix prompts, and interpret CodeRabbit authentication and review output. Use for CodeRabbit review commands, committed/uncommitted or directory scopes, and CodeRabbit runbooks. Default code-review skill: also trigger for explicit code/PR/quality/security review requests or when a review is needed.

Use this Skill: https://skilld.dev/gh/coderabbitai/skills/code-review

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesantigravity-sandbox.md

≈773 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Antigravity CLI sandbox recovery

Follow the shared execution boundary before using this fallback.

Offer this fallback only when the host is identified as Antigravity CLI with the terminal sandbox enabled, not for host-native CLI sessions or the desktop app. When discovery or a needed version/help check is denied, hand the following command to the user to run from their repository in a new terminal session. Replace the placeholder only with a trusted canonical absolute path matching ^/[A-Za-z0-9._/-]+$. If unresolved, ask the user for the resolved canonical absolute path from their terminal and confirmation of its source, not just a symlink path. For other path characters, stop and link the sandbox permissions documentation below instead of constructing a permission rule. Keep the prompt literal and give the original review scope separately for the user to supply in the new session. Do not change permissions or relaunch the agent yourself.

Ask the user to run agy --help in their host terminal before using the command below and confirm it lists --settings and --prompt-interactive. Both are present in CLI 1.4.12's built-in help; if either is unavailable, stop and link the host documentation below. Do not try to elevate these diagnostics yourself.

agy --sandbox \
  --settings '{"agentMode":"","toolPermission":"proceed-in-sandbox","permissions":{"allow":["read_file(/absolute/path/to/coderabbit)"]}}' \
  --prompt-interactive 'Use the CodeRabbit code-review skill. Ask me for the review scope before running a review. Keep version/help sandboxed and use the normal per-command approval flow for authentication and review.'

Tested with Antigravity CLI 1.4.12 and curl-installed CodeRabbit CLI 0.9.1 on macOS arm64: the exact executable read grant allows sandboxed version/help. The user-run command selects default agent mode (agentMode: "") so host requests retain normal approval, and proceed-in-sandbox lets sandboxed commands run without prompting. Explain these permission changes to the user with the handoff. --settings is session-only; existing permissions may still apply. The read grant adds no credential-store, network, or review-state access. Continue with the shared auth/review procedure; do not add credential directories to the allowlist or interpret an auth-file EPERM as signed out.

Use an interactive session for first-time permissions. A headless permission denial can exit 0 with no result; require actual review completion, not just the agent process exit code. If a different skill copy loads, ask the user to run agy plugin list --json in their host terminal and compare it with the reported skill path before retrying; do not delete user skills. If the recovery command fails, report and stop.

See Antigravity's CLI flag reference, sandbox permissions, and headless permission behavior.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alerttoday5 checks · Risk SAFE
  • Gen Agent Trust Hubtoday

    The code-review skill provides integration with the CodeRabbit CLI to perform AI-powered code analysis. It implements strong security controls by requiring absolute path validation for the CLI executable, strictly prohibiting automatic credential handling, and instructing the agent to treat all repository data and external review findings as untrusted. The low-risk verdict reflects the inherent surface for indirect prompt injection from codebase content, which the skill mitigates through mandatory user approval for any derived actions.

  • Sockettoday

    No alerts

  • Snyktoday

    Risk: CRITICAL · 3 issues

  • Runlayer8mo

    1 file scanned · No issues

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at d8e182b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 days ago
metadata
{
  "version": "0.2.0"
}

README badge

README badge for coderabbitai/skills/code-review

Runs CodeRabbit's CLI to analyze code diffs for bugs, security issues, and quality risks, grouping findings by severity. Supports reviewing staged changes, specific commits, branches, or directories, and integrates with autonomous fix workflows via agent-optimized output.

Generated from the current SKILL.md.

Does this skill require authentication?
Yes. You must run `coderabbit auth login` before the first review. The skill checks authentication status and prompts you to log in if needed.
What version of CodeRabbit CLI is required?
The `--agent` flag (used by this skill for agent-readable output) requires CodeRabbit CLI v0.4.0 or later. The skill will detect if your installed version is older and ask you to upgrade.
Can I review only specific changes or directories?
Yes. The skill supports reviewing uncommitted changes (`-t uncommitted`), a specific branch (`--base main`), a commit range (`--base-commit abc123`), or a specific directory (`--dir path/to/directory`).
Does this send my code to CodeRabbit's servers?
Yes. The CLI sends code diffs to the CodeRabbit API for analysis. Do not review files containing secrets, credentials, or sensitive data without redacting them first.
Can this skill automatically fix issues it finds?
No. The skill identifies and categorizes bugs, security issues, and quality risks by severity, but you or the agent must fix them manually. The skill can re-run reviews after fixes to verify they were addressed.

Generated from the current SKILL.md. These answers refresh after source changes.