addressing-pr-feedback
Fetches, organizes, and addresses PR review comments from GitHub. Use when user asks to review PR comments, fix PR feedback, check what reviewers said, address review comments, or handle bot suggestions on a pull request. Triggers on "review PR", "fix comments", "PR feedback", "what did reviewers say", "address PR feedback", "check PR comments".
Best use case
addressing-pr-feedback is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Fetches, organizes, and addresses PR review comments from GitHub. Use when user asks to review PR comments, fix PR feedback, check what reviewers said, address review comments, or handle bot suggestions on a pull request. Triggers on "review PR", "fix comments", "PR feedback", "what did reviewers say", "address PR feedback", "check PR comments".
Teams using addressing-pr-feedback should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/addressing-pr-feedback/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How addressing-pr-feedback Compares
| Feature / Agent | addressing-pr-feedback | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Fetches, organizes, and addresses PR review comments from GitHub. Use when user asks to review PR comments, fix PR feedback, check what reviewers said, address review comments, or handle bot suggestions on a pull request. Triggers on "review PR", "fix comments", "PR feedback", "what did reviewers say", "address PR feedback", "check PR comments".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Addressing PR Feedback
## Overview
Fetch PR review comments, separate bot suggestions from human feedback, present a summary, then let the user select which comments to address.
## Workflow
1. **Identify branch** → from user input or `git branch --show-current`
2. **Find PR** → `gh pr list --head <branch> --json number,title,url --jq '.[0]'`
3. **Fetch all comments** → review comments, issue comments, review summaries
4. **Group by reviewer type** → human reviewers (high priority) vs bots (suggestions)
5. **Present summary** → counts, timestamps, outdated status
6. **User selects** → checkbox multi-select via AskUserQuestion
7. **Fix selected** → read file, apply fix, optionally reply to comment
## Fetching Comments
```bash
# Inline review comments (on specific code lines)
gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/comments
# General PR comments
gh api repos/{owner}/{repo}/issues/<PR_NUMBER>/comments
# Review summaries
gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/reviews
```
**Key fields:**
- `created_at` — display as relative time ("2 hours ago")
- `position` — null means outdated (code changed since comment)
- `in_reply_to_id` — reply thread, group with parent
- `path` — file the comment is on
## Grouping Comments
| Category | Detection | Priority |
|----------|-----------|----------|
| **Bot** | Username contains `[bot]`, ends with `bot`, or is a known CI tool | Lower — automated suggestions |
| **Human** | All other usernames | Higher — requires response |
## Presenting Summary
```
## PR #123: "Add authentication flow"
### Human Reviewers (2 comments) — HIGH PRIORITY
- @alice: 1 comment on src/auth.ts (2 days ago)
- @bob: 1 comment on src/utils.ts (5 hours ago) ⚠️ OUTDATED
### Bot Suggestions (5 comments)
- 3 style/formatting (1 day ago)
- 2 potential improvements (1 day ago) ⚠️ 1 OUTDATED
```
Mark comments as ⚠️ OUTDATED when `position` is null (code changed since the comment was posted).
## User Selection
Use `AskUserQuestion` with `multiSelect: true`:
```
Which comments do you want me to address?
[ ] @alice: "Consider adding error handling for timeout" (2 days ago)
[ ] @bob: "This function could be simplified" (5h ago) ⚠️ OUTDATED
[ ] bot: "Missing return type annotation" (3 similar, 1 day ago)
```
Group similar bot comments to reduce noise. Show relative timestamps. Mark outdated comments — the user may skip these.
## Anti-Patterns
**Dumping all comments raw:** Always summarize and group first.
**Treating all comments equally:** Human comments get priority display over bot suggestions.
**Open-ended questions:** Use checkbox selection, not "which ones do you want me to fix?"
**Fixing without asking:** Always let the user select which comments to address.Related Skills
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
chrome-debug
This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.
lets-go-rss
A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
astro
This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.
advanced-skill-creator
Meta-skill that generates domain-specific skills using advanced reasoning techniques. PROACTIVELY activate for: (1) Create/build/make skills, (2) Generate expert panels for any domain, (3) Design evaluation frameworks, (4) Create research workflows, (5) Structure complex multi-step processes, (6) Instantiate templates with parameters. Triggers: "create a skill for", "build evaluation for", "design workflow for", "generate expert panel for", "how should I approach [complex task]", "create skill", "new skill for", "skill template", "generate skill"