Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts GitHub PR Comment Resolver with CLI

agent coding skill risk: low

GitHub PR Comment Resolver with CLI

Instructs the model to use the GitHub CLI (`gh`) to fetch PR comments, categorize and plan fixes, apply changes after confirmation, and respond to threads as resolved.

  • External action: medium

SKILL 1 file

SKILL.md
---
name: antigravity-awesome-skills-address-github-comments-89402419
description: "Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI."
---
# Address GitHub Comments

## Overview

Efficiently address PR review comments or issue feedback using the GitHub CLI (`gh`). This skill ensures all feedback is addressed systematically.

## Prerequisites

Ensure `gh` is authenticated.

```bash
gh auth status
```

If not logged in, run `gh auth login`.

## Workflow

### 1. Inspect Comments

Fetch the comments for the current branch's PR.

```bash
gh pr view --comments
```

Or use a custom script if available to list threads.

### 2. Categorize and Plan

- List the comments and review threads.
- Propose a fix for each.
- **Wait for user confirmation** on which comments to address first if there are many.

### 3. Apply Fixes

Apply the code changes for the selected comments.

### 4. Respond to Comments

Once fixed, respond to the threads as resolved.

```bash
gh pr comment <PR_NUMBER> --body "Addressed in latest commit."
```

## Common Mistakes

- **Applying fixes without understanding context**: Always read the surrounding code of a comment.
- **Not verifying auth**: Check `gh auth status` before starting.

## When to Use
This skill is applicable to execute the workflow or actions described in the overview.

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

REQUIRED CONTEXT

  • current branch's PR
  • review or issue comments

TOOLS REQUIRED

  • gh

ROLES & RULES

  1. Wait for user confirmation on which comments to address first if there are many
  2. Always read the surrounding code of a comment
  3. Check `gh auth status` before starting
  4. Use this skill only when the task clearly matches the scope described above
  5. Do not treat the output as a substitute for environment-specific validation, testing, or expert review
  6. Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing

EXPECTED OUTPUT

Format
markdown
Constraints
  • follow numbered workflow steps
  • include gh CLI commands
  • wait for user confirmation when many comments

FAILURE MODES

  • Applying fixes without understanding context
  • Not verifying auth

CAVEATS

Dependencies
  • gh CLI authenticated
Missing context
  • How to obtain or pass the PR_NUMBER when multiple PRs exist
  • Preferred format for listing and categorizing comments
  • Criteria for deciding when user confirmation is required
Ambiguities
  • 'Or use a custom script if available' does not specify how the script is discovered or invoked.
  • 'Apply the code changes for the selected comments' gives no concrete method or commands.
  • 'Propose a fix for each' leaves the proposal format and depth unspecified.

QUALITY

OVERALL
0.74
CLARITY
0.82
SPECIFICITY
0.68
REUSABILITY
0.78
COMPLETENESS
0.72

IMPROVEMENT SUGGESTIONS

  • Replace the placeholder <PR_NUMBER> with an explicit instruction to extract it via `gh pr view --json number -q .number`.
  • Add a required output format (e.g., markdown checklist) for the 'Categorize and Plan' step.
  • Specify exact `gh` subcommands or API calls for marking threads resolved instead of a generic comment.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT