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
feedback-observing
Read agent interaction logs across packs and detect operational patterns. Emits state-transition FeedbackEvents for degradation/recovery.
Async Feedback Loop
Enables mid-stream course correction by monitoring a FEEDBACK.md file for user interventions. Allows the agent to incorporate new instructions without restarting the task.
ai-orchestration-feedback-loop
Multi-AI engineering loop orchestrating Claude, Codex, and Gemini for comprehensive validation. USE WHEN (1) mission-critical features requiring multi-perspective validation, (2) complex architectural decisions needing diverse AI viewpoints, (3) security-sensitive code requiring deep analysis, (4) user explicitly requests multi-AI review or triple-AI loop. DO NOT USE for simple features or single-file changes. MODES - Triple-AI (full coverage), Dual-AI Codex-Claude (security/logic), Dual-AI Gemini-Claude (UX/creativity).
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
moai-lang-r
R 4.4+ best practices with testthat 3.2, lintr 3.2, and data analysis patterns.
moai-lang-python
Python 3.13+ development specialist covering FastAPI, Django, async patterns, data science, testing with pytest, and modern Python features. Use when developing Python APIs, web applications, data pipelines, or writing tests.
moai-icons-vector
Vector icon libraries ecosystem guide covering 10+ major libraries with 200K+ icons, including React Icons (35K+), Lucide (1000+), Tabler Icons (5900+), Iconify (200K+), Heroicons, Phosphor, and Radix Icons with implementation patterns, decision trees, and best practices.
moai-foundation-trust
Complete TRUST 4 principles guide covering Test First, Readable, Unified, Secured. Validation methods, enterprise quality gates, metrics, and November 2025 standards. Enterprise v4.0 with 50+ software quality standards references.
moai-foundation-memory
Persistent memory across sessions using MCP Memory Server for user preferences, project context, and learned patterns
moai-foundation-core
MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows
moai-cc-claude-md
Authoring CLAUDE.md Project Instructions. Design project-specific AI guidance, document workflows, define architecture patterns. Use when creating CLAUDE.md files for projects, documenting team standards, or establishing AI collaboration guidelines.
moai-alfred-language-detection
Auto-detects project language and framework from package.json, pyproject.toml, etc.