skills/coderabbit/SKILL.md
Local AI code reviews via CodeRabbit CLI. ONLY use when (1) user explicitly requests "coderabbit"/"cr review", OR (2) code changes are high-risk (security, concurrency, complex logic). Rate-limited to 1 review/hour—be highly selective.
npx skillsauth add indrasvat/claude-code-skills coderabbitInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
AI code reviews locally. Rate limit: 1 review/hour. Use sparingly.
USE CodeRabbit for:
SKIP CodeRabbit for:
When uncertain, ask user: "This looks like it could benefit from a CodeRabbit review (1/hour limit). Want me to run one?"
# Check if installed
command -v cr &>/dev/null || {
echo "Installing CodeRabbit CLI..."
curl -fsSL https://cli.coderabbit.ai/install.sh | sh
source ~/.zshrc # or ~/.bashrc
}
# Check auth status, login if needed
cr auth status || cr auth login
If CLI missing, prompt user: "CodeRabbit CLI not installed. Install it now?" Then run install + auth.
ALWAYS run in background with monitoring:
# Start review in background, capture output
cr review --prompt-only --type uncommitted > /tmp/cr-review.txt 2>&1 &
CR_PID=$!
# Monitor completion (reviews take 7-30 min)
while kill -0 $CR_PID 2>/dev/null; do sleep 30; done
# Read results
cat /tmp/cr-review.txt
Flags:
--prompt-only — Always use. AI-optimized, token-efficient output--type uncommitted — Faster, reviews only unstaged/staged changes--type committed — Only committed changes vs base--base <branch> — Compare against specific branch (default: main)git status, verify --base branchcr auth logindevelopment
Fetch, categorize, and address PR review comments in priority order. Classifies each comment as BLOCKER, QUESTION, SUGGESTION, or NITPICK and works through blockers first. Use when the user says "address PR comments", "fix review feedback", "respond to PR", "handle review comments", "triage PR", "what does the reviewer want", "address feedback", "PR comments", "review feedback", or needs to work through pull request review comments systematically.
testing
Create a pull request with a standards compliance review gate. Reviews the diff against CLAUDE.md and repo conventions before creating the PR, stopping on discrepancies. Supports tiered PR templates (small, standard, complex). Use when the user says "create PR", "open PR", "ship it", "ship PR", "make a pull request", "push and PR", "ready for review", "send for review", "create a pull request", or wants to create a GitHub pull request from the current branch.
testing
Verify Kubernetes deployment health — pod status, rollout progress, events, readiness, HPA state, and recent errors. Use when the user says "check rollout", "is deploy healthy", "rollout status", "deployment health", "pod status", "check pods", "why is deploy failing", "k8s health", "verify deployment", "are pods ready", "check deployment", or wants to verify a Kubernetes deployment is healthy after a rollout.
documentation
Generate comprehensive Product Requirements Documents with interactive discovery, progress tracking, and True Ralph Loop support for autonomous implementation. Use when user wants to (1) create a PRD for a new project/feature, (2) implement a PRD autonomously with fresh Claude sessions, (3) track implementation progress, (4) recover context after session loss. Creates docs/PRD.md and docs/PROGRESS.md.