Respond — Git skill for Claude Code
Respond to all comments and reviews on a PR.
How to install Respond
Installs to ~/.claude/commands/fotoetienne-gru-respond.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/fotoetienne/gru/HEAD/.claude/commands/respond.md -o ~/.claude/commands/fotoetienne-gru-respond.md Restart Claude Code, or start a new session, for it to be picked up.
What Respond does
description: Respond to all comments and reviews on a PR allowed-tools: Bash(gh:*), Bash(gh pr checks:*), Bash(git:*), Bash(just:*), Read, Glob, Grep, Edit, Write, Task, TodoWrite, WebFetch
Respond to all comments and reviews on a GitHub pull request.
**Pull Request:** $ARGUMENTS
**Workflow:**
1. Fetch Comments and Reviews
- Use
gh pr view $ARGUMENTSto get PR details - Use
gh api repos/{owner}/{repo}/pulls/{pr#}/commentsto fetch all review comments - Use `gh api repos/{owner
Alternatives in Git
- Address PR Comments 71.9k ★
- 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 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Work On Ticket Respond To PR Comments
You are a principal engineer with equity stake in the company building this software.
Implement Respond
Fetch PR review comments, propose responses, apply code changes
Mention Respond
Respond to an @AetherClaude mention on an issue or PR with a single comment
Respond Discussion
Answer a community question in GitHub Discussions
Scout Repo Agent
Scout is a Github Repository Agent that can respond to issues
Resolve Reviews
指定したPRの未解決レビューコメントに対応する
Related Agents
PR Monitor
Use this agent to manage the full lifecycle of a GitHub PR — check CI status, read Buildkite failures, respond
Mr Comment Responder
Analyzes review comments received on your MR/PR and creates a response strategy. Use when you have received re
Experiment Scientist
Analyze experiment results, respond to audits and reviews, update STATE.md, and plan the next experiment round