/review-rabbit
SkillCloud & infraReview CodeRabbit critical issues and human reviewer comments on a PR. Report only the real problems.
Use /review-rabbit in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add /review-rabbit and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the /review-rabbit skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this skill
Containerized Python based Framework for running and visualizing benchmark workloads on any Kubernetes/ OpenShift and runtime kinds pods, kubevirt virtual machines simply and safely
What this skill tells your AI
The instructions your AI receives, as published by redhat-performance/benchmark-runner in .claude/skills/review-rabbit/SKILL.md and read by Ahel’s review.
Review CodeRabbit critical issues and human reviewer comments on a PR. Report only the real problems.
Usage
Pass the PR number as an argument: /review-rabbit 1240
If no argument is provided, use the current branch's open PR.
Steps
-
Find the PR
- If a PR number is provided, use it
- Otherwise, find the open PR for the current branch:
gh pr view --json number --jq '.number'
-
Fetch CodeRabbit critical comments
gh api repos/redhat-performance/benchmark-runner/pulls/{PR_NUMBER}/comments \ --jq '.[] | select(.user.login == "coderabbitai[bot]") | select(.body | test("Critical|critical|🔴")) | {path: .path, line: .line, body: .body[0:800]}' -
Fetch human reviewer comments (arpsharm and others)
gh api repos/redhat-performance/benchmark-runner/pulls/{PR_NUMBER}/comments \ --jq '.[] | select(.user.login != "coderabbitai[bot]") | {id: .id, user: .user.login, path: .path, line: .line, body: .body[0:800]}' -
Analyze each issue
- Read the relevant source file and line for each finding
- For CodeRabbit: determine if the issue is a real bug or a false positive; skip issues where CodeRabbit couldn't verify (e.g., registry checks from sandbox)
- For human reviewers: treat every comment as a real concern that needs to be addressed
-
Reply on the PR for fixed issues
- For every issue (CodeRabbit or human reviewer) that has already been fixed in the current branch, reply to the comment on the PR confirming the fix
- Fetch comment IDs with:
gh api repos/redhat-performance/benchmark-runner/pulls/{PR_NUMBER}/comments \ --jq '.[] | select(.user.login == "coderabbitai[bot]") | select(.body | test("Critical|critical|🔴")) | {id: .id, path: .path, body: .body[0:200]}' - Reply to each fixed issue's comment:
gh api repos/redhat-performance/benchmark-runner/pulls/{PR_NUMBER}/comments/{COMMENT_ID}/replies \ -X POST \ -f body='[Claude Code] Already fixed in commit {SHORT_SHA}. {Brief description of the fix}.'
-
Report findings
- List real critical issues (CodeRabbit) and human reviewer comments with file path, line number, and what needs to be fixed
- If no real issues exist, report that the PR is clean
Notes
- Focus only on critical issues — skip informational and style comments
- Always verify against the actual code before reporting
- Prefix any PR comment replies with [Claude Code]
- Always reply to every CodeRabbit critical comment that has been fixed — do not skip duplicates
Signals
- GitHub stars
- 39
- Forks
- 25
- Last commit
- Oct 2026
Advanced
- Item type
- skill
- Key
review-rabbit- Source
- github.com/redhat-performance/benchmark-runner
github.com/redhat-performance/benchmark-runner
More in Cloud & infra
Skill · vercel-labs
More in Cloud & infraweb-design-guidelines
Skill · vercel-labs
More in Cloud & infraturborepo
Skill · vercel
More in Cloud & inframicrosoft-foundry
Skill · microsoft
More in Cloud & infraazure-diagnostics
Skill · microsoft
More in Cloud & infrauncloud
Skill · affaan-m
More in Cloud & infra