home / skills / openai / skills / gh-address-comments

gh-address-comments skill

safe

This skill helps you identify, review, and address open PR comments on the current branch using gh, with authentication checks.

npx playbooks add skill openai/skills --skill gh-address-comments

Review the files below or copy the command above to add this skill to your agents.

Files (6)

SKILL.md

1.2 KB

---
name: gh-address-comments
description: Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
metadata:
  short-description: Address comments in a GitHub PR review
---

# PR Comment Handler

Guide to find the open PR for the current branch and address its comments with gh CLI. Run all `gh` commands with elevated network access.

Prereq: ensure `gh` is authenticated (for example, run `gh auth login` once), then run `gh auth status` with escalated permissions (include workflow/repo scopes) so `gh` commands succeed. If sandboxing blocks `gh auth status`, rerun it with `sandbox_permissions=require_escalated`.

## 1) Inspect comments needing attention
- Run scripts/fetch_comments.py which will print out all the comments and review threads on the PR

## 2) Ask the user for clarification
- Number all the review threads and comments and provide a short summary of what would be required to apply a fix for it
- Ask the user which numbered comments should be addressed

## 3) If user chooses comments
- Apply fixes for the selected comments

Notes:
- If gh hits auth/rate issues mid-run, prompt the user to re-authenticate with `gh auth login`, then retry.

Overview

This skill helps you find the open GitHub pull request for the current branch and address its review and issue comments using the gh CLI. It verifies that gh is authenticated and prompts you to authenticate if needed. The skill guides you through inspecting comment threads, selecting which comments to address, and applying fixes automatically where possible.

How this skill works

It first checks gh authentication and asks you to run gh auth login if not authenticated or if scopes are insufficient. It runs a script to fetch and summarize all review threads and comments on the PR, numbers them, and asks which items you want to address. For chosen comments it attempts to apply fixes, and if gh reports auth or rate limits mid-run it prompts for re-authentication and retries.

When to use it

You are working on a branch with an open PR and want to resolve review comments quickly.
You need to batch-review and address multiple comment threads before merging.
You want an interactive flow that verifies gh authentication and reduces manual gh CLI work.
You want automatic fixes for straightforward review suggestions where supported.

Best practices

Ensure gh is logged in and granted necessary scopes (workflow/repo) before starting.
Run authentication checks with elevated network permissions if sandboxing blocks gh status.
Review the numbered summaries before applying fixes to avoid unintended changes.
Re-authenticate immediately if gh reports rate limits or permission errors and then retry.
Keep the local branch up to date with the PR base to minimize merge conflicts when applying fixes.

Example use cases

Run a quick pass to fetch all PR review threads, pick low-risk suggestions, and apply them automatically.
Enumerate and summarize comments so you can ask a teammate for clarification on specific threaded feedback.
Batch-handle style or documentation fixes across a PR without manually locating each comment.
Detect an authentication issue, prompt to log in, then continue the flow once gh is authorized.

FAQ

What if gh auth status is blocked by sandboxing?

Rerun the check with elevated permissions (sandbox_permissions=require_escalated) or run gh auth login outside the sandbox to grant required scopes.

What happens if a fix causes a merge conflict?

The skill will surface the conflict so you can resolve it manually; automatic fixes stop before making conflicting changes.