agentleFS
Sign inStart free
lgtm-hqlgtm-hq/ai-skills/skills/coderabbit/SKILL.md

coderabbit

Skill1 starsChanged 8 days agoMITView on GitHub

Run CodeRabbit CLI for pre-push AI diff review. Use when asked for CodeRabbit, cr review, or as part of the default pre-push review set with greptile and lintro-review. Max 2-3 runs per change set.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run CodeRabbit (cr / coderabbit) for automated diff review before push.

    line 11
  2. Distinctive:

    Do not duplicate full analyze rubrics here.

    line 25
  3. Distinctive:

    Default pre-push flow when CI runs the review tools:

    line 29
  4. Distinctive:

    Run greptile, coderabbit, and lintro-review in parallel when possible.

    line 37
  5. Very specific:

    Always use --agent for agent workflows (structured JSON output)

    line 56
  6. Distinctive:

    Must run from an initialized Git repository root

    line 59
  7. Very specific:

    Only use -t uncommitted for quick pre-commit spot checks

    line 60
  8. Distinctive:

    When asked to run CodeRabbit or as part of pre-push review:

    line 64
  9. Very specific:

    Ensure lint and tests pass (the commit skill's checklist, or the lint and test skills explicitly)

    line 66
  10. Very specific:

    Run coderabbit review --agent --type committed --base main (background if needed)

    line 68
  11. Distinctive:

    After fixes, run one verification pass if CodeRabbit had findings

    line 70

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CodeRabbit CLI Review

Run CodeRabbit (cr / coderabbit) for automated diff review before push. Pair with greptile and lintro-review for the default pre-push review set — the tools catch different issues and mirror CI. When CodeRabbit (or Greptile) is rate-limited, do not wait for the reset: the lintro-review pass is the review of record for that push.

Relationship to analyze-* skills

The analyze-code, analyze-project, and analyze-tests skills are for manual or agent-driven pre-review checks—they run concrete commands (lintro, ripgrep, coverage, etc.) and produce structured findings before you open a PR.

This skill uses CodeRabbit CLI for external AI diff review. Follow the lint and test skills (or the commit skill, which includes them) before invoking CodeRabbit. Do not duplicate full analyze rubrics here.

Relationship to greptile and lintro-review

Default pre-push flow when CI runs the review tools:

commit → [greptile ‖ coderabbit ‖ lintro-review] → pr

Each step names the skill to follow.

Run greptile, coderabbit, and lintro-review in parallel when possible. Do not re-run on unchanged code.

Commands

  • cr -h / coderabbit --help — Show CodeRabbit help
  • coderabbit review --agent --type committed --base main — Full branch diff against main (default for agents; matches CI intent)
  • coderabbit review --agent --type uncommitted — Uncommitted (staged + unstaged); quick spot check
  • coderabbit doctor — Verify install, auth, and Git repo readiness
  • coderabbit review findings — Replay findings from the last local review

cr is an alias for coderabbit. --prompt-only is deprecated; use --agent.

Rules

  • Max 2–3 CodeRabbit runs per change set (Pro plan: 5 CLI reviews per developer — rate limits)
  • Always use --agent for agent workflows (structured JSON output)
  • Default to --base main unless the repo uses a different default branch
  • Reviews can take 7–30+ minutes — run in the background when possible
  • Must run from an initialized Git repository root
  • Only use -t uncommitted for quick pre-commit spot checks

Usage

When asked to run CodeRabbit or as part of pre-push review:

  1. Ensure lint and tests pass (the commit skill's checklist, or the lint and test skills explicitly)
  2. Run coderabbit review --agent --type committed --base main (background if needed)
  3. Analyze findings; address critical/major issues
  4. After fixes, run one verification pass if CodeRabbit had findings
  5. Track run count (max 2–3 per change set)

Note: -t committed with --base main reviews the full branch diff. -t uncommitted includes staged and unstaged changes (empty after a full commit with a clean tree).

References

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free