Peqy — Git skill for Claude Code
Review peqy bot comments on a PR and assess their validity against the codebase.
How to install Peqy
Installs to ~/.claude/commands/rhesis-ai-rhesis-peqy.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/rhesis-ai/rhesis/HEAD/.claude/commands/peqy.md -o ~/.claude/commands/rhesis-ai-rhesis-peqy.md Restart Claude Code, or start a new session, for it to be picked up.
What Peqy does
description: Review peqy bot comments on a PR and assess their validity against the codebase
Review the comments left by peqy[bot] on a pull request and assess whether each comment is valid, actionable, and consistent with the codebase's existing patterns.
Steps
Determine the PR number:
- If
$ARGUMENTSis provided, use it as the PR number - Otherwise, detect the current branch and find its open PR using
gh pr view --json number
- If
Fetch all review comments from peqy u
Alternatives in Git
- Fix PR — by metabase - Fetches and fixes unresolved PR comments by automatically retrieving feedback, addressing review 46.5k ★
- Gh Address Comments — Address review and issue comments on open GitHub PRs via CLI 14.6k ★
- Codebase To Course — by Zara Zhang - A Claude Code skill that turns any codebase into a beautiful, interactive single-page HTML cou 2.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Review Comments
Review GitHub PR comments, assess validity, remediate accepted findings,
PR Comments
Read the review comments on a PR, assess each one, argue when I'm wrong, then implement only what we agreed on
Verify Unresolved PR Comments
Analyze unresolved review comments and PR-level feedback on the active PR and return a triage chart with sever
CI Green
Loop fix-bot-comments + CI rechecks on a PR until all checks pass and every thread is resolved.
Epic Plan
Plan a new epic against a real codebase and a real project board, then — only after explicit approval — create
Self Hosted Review
Review a PR with subagents when no bot reviewer responded — three cycles (architectural, line-level, verificat
Related Agents
Assess Layer Scorer
Scores a codebase against the /assess 0-8 layered contract model, reading the deterministic run-context.json a
Ccd Speckit Converger
Use this agent to assess the implemented codebase against the active feature's spec, plan, and tasks by invoki
Check PR Bots
Fetch and display bot comments on GitHub pull requests. Use PROACTIVELY when checking PR review feedback, bot