pr-comment-responder
PR review coordinator who gathers comment context, acknowledges every piece of feedback, and ensures all reviewer comments are addressed systematically. Triages by actionability, tracks thread conversations, and maps each comment to resolution status. Use when handling PR feedback, review threads, or bot comments.
- License 许可
- MIT
- 最近更新
- 2026-03-11
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- pr-comment-responder
- model
- claude-sonnet-4-5
- agents
- [ "implementer", "analyst" ]
- license
- MIT
- metadata
- { "version": "2.0.0", "argument-hint": "Specify the PR number or review comments to address" }
- description
- PR review coordinator who gathers comment context, acknowledges every piece of feedback, and ensures all reviewer comments are addressed systematically. Triages by actionability, tracks thread conversations, and maps each comment to resolution status. Use when handling PR feedback, review threads, or bot comments.
02 资源文件 8
- 其他.build-trigger24 B
- 其他articles/.gitkeep—
- 资产文件assets/.gitkeep—
- 参考文档references/bots.md3.2 KB
- 参考文档references/gates.md4.6 KB
- 参考文档references/templates.md2.6 KB
- 参考文档references/workflow.md6.7 KB
- 参考文档site.yaml2.9 KB
03 SKILL.md 正文
PR Comment Responder
Coordinates PR review responses through context gathering, comment tracking, and orchestrator delegation.
Triggers
| Phrase | Action |
|---|---|
respond to PR comments |
Full workflow |
address review feedback on PR #123 |
Full workflow |
handle PR review comments |
Full workflow |
fix PR review issues |
Full workflow |
reply to reviewer on PR #123 |
Target specific PR |
Quick Reference
Context Inference (Phase -1)
ALWAYS extract PR context from prompt first. Never prompt for information already provided.
Extract PR context from user prompt or use gh pr view to get PR metadata.
Supported patterns:
- Text:
PR 806,PR #806,pull request 123,#806 - URLs:
github.com/owner/repo/pull/123
See references/workflow.md Phase -1 for full details.
Tools
| Operation | Command |
|---|---|
| Context extraction | Extract PR number from prompt or use gh pr view |
| PR metadata | gh pr view [number] --json title,body,state,author,baseRefName,headRefName |
| Comments | gh pr view [number] --json comments,reviewDecision,reviews |
| Reviewers | gh pr view [number] --json reviewRequests,reviews |
| Reply | gh pr comment [number] --body "[response]" |
| Reaction | gh api repos/{owner}/{repo}/issues/comments/{id}/reactions -f content=eyes |
| Resolve thread | gh api graphql with resolveReviewThread mutation |
Reviewer Priority
| Priority | Reviewer | Signal |
|---|---|---|
| P0 | cursor[bot] | 100% actionable |
| P1 | Human reviewers | High |
| P2 | coderabbitai[bot] | ~50% |
| P2 | Copilot | ~44% |
Domain-Based Priority
Comments are classified into domains for priority-based triage:
| Priority | Domain | Keywords | Use Case |
|---|---|---|---|
| P0 | Security | CWE-*, vulnerability, injection, XSS, SQL, CSRF, auth, secrets, credentials, TOCTOU, symlink, traversal | Process FIRST - security-critical issues |
| P1 | Bug | error, crash, exception, fail, null, undefined, race condition, deadlock, memory leak | Address functional issues |
| P2 | Style | formatting, naming, indentation, whitespace, convention, prefer, consider, suggest | Apply improvements when time permits |
| P3 | Summary | Bot-generated summaries (## Summary, ### Overview) | Informational only |
Domain-First Processing Workflow:
# Get all review comments and PR comments
comments=$(gh api repos/{owner}/{repo}/pulls/{number}/comments)
issue_comments=$(gh api repos/{owner}/{repo}/issues/{number}/comments)
# Process by domain priority:
# 1. Security (CWE, vulnerabilities, injection) - process FIRST
# 2. Bug (errors, crashes, null references)
# 3. Style (formatting, naming, conventions)
# 4. General comments
# 5. Skip summary comments (bot-generated noise)
Benefits:
- Security issues processed before style suggestions
- Reduces noise from bot-generated summaries
- Enables metrics tracking (security vs style comment distribution)
When to Use
Use this skill when:
- A PR has unaddressed review comments from humans or bots
- You need to systematically triage and respond to all review feedback
- CI review bots (CodeRabbit, Copilot, cursor) left comments requiring action
Use direct gh pr comment instead when:
- Replying to a single known comment (no triage needed)
- You already know the exact response to post
Process
Phase 1: Context and Gather
- Extract PR number from prompt (BLOCKING) or use
gh pr view - Search Brain memory for
pr-comment-responderrelated notes - Gather PR metadata, reviewers, all comments (use
--group-by-domainfor priority triage) - Batch eyes reactions on all comments
Phase 2: Triage and Delegate
- Generate comment map (track in session or Brain memory note)
- Delegate each comment to orchestrator (process security domain first)
- Implement changes via orchestrator delegation
Phase 3: Verify
- All comments resolved (COMPLETE or WONTFIX)
- No new comments after 45s wait
- CI checks passing, all threads resolved, commits pushed
See references/workflow.md for full phase details.
Verification
- [ ] All comments resolved (COMPLETE or WONTFIX)
- [ ] No new comments after 45s wait
- [ ] CI checks passing
- [ ] All threads resolved
- [ ] Commits pushed
See references/gates.md for gate implementation.
Response Templates
See references/templates.md for:
- Won't Fix responses
- Clarification requests
- Resolution replies
Bot Handling
See references/bots.md for:
- Copilot follow-up PR handling
- CodeRabbit commands
- cursor[bot] patterns
Anti-Patterns
| Avoid | Why | Instead |
|---|---|---|
| Replying to bot summaries as actionable comments | Wastes time on informational noise | Skip Summary domain comments |
| Processing style before security | Misses critical issues | Process domains in P0-P3 priority order |
| Prompting user for PR number already in prompt | Redundant and frustrating | Parse PR number from input text or use gh pr view |
Extension Points
- Add new domain classifiers for comment triage
- Add reviewer priority entries for new bot integrations
- Add response templates in
references/templates.md
04 同仓库更多 Skills
validation-authority
Treat upstream validators as authoritative. Align local config to them. Use when validation fails unexpectedly, before modifying validator behavior, or when tempted to change upstream tool code.
using-brain-memory
Guidance for using Brain semantic memory effectively. Applies Zettelkasten atomic note principles with observations and relations. Use when deciding whether to query or create notes, structuring note content, or understanding the semantic knowledge graph.
threat-modeling
Structured security analysis using OWASP Four-Question Framework and STRIDE methodology. Generates threat matrices with risk ratings, mitigations, and prioritization. Use for attack surface analysis, security architecture review, or when asking what can go wrong.
taste-lints
Custom lints with agent-readable remediation instructions. Enforces taste invariants (file size, naming conventions, structured logging, complexity) and surfaces errors that agents can act on directly. Use when writing or reviewing code to catch style violations early.
style-enforcement
Validate code against style rules from .editorconfig, StyleCop.json, and Directory.Build.props. Detects line ending violations, naming convention issues, indentation problems, and charset mismatches across C#, Python, TypeScript, and JavaScript. Produces JSON reports for pre-commit hooks and CI pipelines.
steering-matcher
Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.