← ClaudeAtlas

coderabbitlisted

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.
lgtm-hq/ai-skills · ★ 0 · Code & Development · score 66
Install: claude install-skill lgtm-hq/ai-skills
# 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: ```text 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 - `c