pr-feedback
This skill should be used for integrating PR review comments back into devloop plan, parsing review feedback, addressing reviewer concerns
Best use case
pr-feedback is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
This skill should be used for integrating PR review comments back into devloop plan, parsing review feedback, addressing reviewer concerns
Teams using 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/pr-feedback/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How pr-feedback Compares
| Feature / Agent | 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?
This skill should be used for integrating PR review comments back into devloop plan, parsing review feedback, addressing reviewer concerns
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
# PR Feedback - Integrate Review Comments
Fetch PR review feedback and add actionable items to the plan. **You do the work directly.**
## Step 1: Identify PR
**If PR number provided:** Use `$ARGUMENTS`
**Otherwise, detect from current branch:**
```bash
gh pr view --json number,title,state,reviewDecision
```
If no PR found for current branch, inform user and exit.
## Step 2: Fetch Feedback
**Get PR details:**
```bash
gh pr view --json number,title,body,reviews,reviewDecision,comments
```
**Get inline code comments:**
```bash
gh api repos/{owner}/{repo}/pulls/{number}/comments --jq '.[] | {path, line, body, user: .user.login}'
```
## Step 3: Parse Comments
**Categorize each comment:**
| Pattern | Category |
|---------|----------|
| Review state = CHANGES_REQUESTED | Blocker |
| "must", "need to", "please fix" | Blocker |
| "should", "consider", "might" | Suggestion |
| "why", "what if", "?$" | Question |
| "nit", "minor", "optional" | Nitpick |
**Extract actionable items:**
For each comment/review body:
1. Check if it requests action
2. Summarize the request
3. Note the author
4. Track file/line if inline comment
## Step 4: Present Findings
**Display to user:**
```markdown
## PR #123 Feedback
**Status**: CHANGES_REQUESTED by @reviewer
### Blockers (must address)
1. Fix null handling in parseConfig (src/config.ts:42)
2. Add tests for edge cases
### Suggestions
3. Consider caching the parsed config
### Questions (respond or address)
4. Why not use the existing parser?
### Nitpicks (optional)
5. Rename variable for clarity
```
**Ask which to add to plan:**
```yaml
AskUserQuestion:
questions:
- question: "Which feedback items should be added to the plan?"
header: "Select"
multiSelect: true
options:
- label: "All blockers"
description: "Add items 1-2"
- label: "Blockers + suggestions"
description: "Add items 1-3"
- label: "All items"
description: "Add everything"
- label: "Select individually"
description: "Choose specific items"
```
## Step 5: Update Plan
**Add PR Feedback section to `.devloop/plan.md`:**
```markdown
---
## PR Feedback
PR #123 - @reviewer (CHANGES_REQUESTED)
### Blockers
- [ ] [PR-123-1] Fix null handling in parseConfig
- [ ] [PR-123-2] Add tests for edge cases
### Suggestions
- [ ] [PR-123-3] Consider caching config
---
```
**Add Progress Log entry:**
```markdown
- YYYY-MM-DD: Added N PR feedback items from review
```
## Step 6: Next Steps
```yaml
AskUserQuestion:
questions:
- question: "Feedback added to plan. What next?"
header: "Action"
multiSelect: false
options:
- label: "Start fixing"
description: "Work on first blocker"
- label: "Respond first"
description: "Reply to questions"
- label: "Review plan"
description: "See updated plan"
```
---
## Handling Responses
**For questions that need responses (not code changes):**
```bash
gh pr comment {number} --body "Re: [question]
[Your response]"
```
**After addressing feedback:**
```bash
gh pr comment {number} --body "Addressed feedback:
- [x] Fixed null handling
- [x] Added edge case tests
Ready for re-review."
```
---
## Quick Reference
| Command | Purpose |
|---------|---------|
| `gh pr view` | Get PR details |
| `gh pr view --comments` | See all comments |
| `gh api .../comments` | Get inline comments |
| `gh pr comment` | Reply to PR |
---
## Example Output
```
Fetching PR #42 feedback...
Found 5 comments from review by @alice:
BLOCKERS (2):
1. [src/parser.ts:15] Handle null input
2. [src/parser.ts:42] Add input validation
SUGGESTIONS (1):
3. Consider using zod for validation
QUESTIONS (1):
4. Why a custom parser vs. existing library?
Added 4 items to plan under "PR Feedback" section.
```Related Skills
Example Skill
Brief description of what this skill does and the domain expertise it provides.
vulnerability-patterns
Index of vulnerability detection pattern skills. Routes to core patterns (universal) and language-specific patterns for security scanning.
vuln-patterns-languages
Language-specific vulnerability detection patterns for JavaScript/TypeScript, Python, Go, Java, Ruby, and PHP. Provides regex patterns and grep commands for common security vulnerabilities.
vuln-patterns-core
Universal vulnerability detection patterns applicable across all programming languages. Includes hardcoded secrets, SQL/command injection, path traversal, and configuration file patterns.
scan
Run a security assessment using deterministic static analysis tools with LLM-powered triage
results
View the most recent security scan results without re-running the scan
remediation-library
Index of security remediation skills. Routes to specialized skills for injection, cryptography, authentication, and configuration vulnerabilities.
remediation-injection
Security fix patterns for injection vulnerabilities (SQL, Command, XSS). Provides language-specific code examples showing vulnerable and secure implementations.
remediation-crypto
Security fix patterns for cryptographic vulnerabilities (weak algorithms, insecure randomness, TLS issues). Provides language-specific secure implementations.
remediation-config
Security fix patterns for configuration and deployment vulnerabilities (path traversal, debug mode, security headers). Provides language-specific secure implementations.
remediation-auth
Security fix patterns for authentication and authorization vulnerabilities (credentials, JWT, deserialization, access control). Provides language-specific secure implementations.
fix
Fix or guide remediation for a specific security finding from the latest scan report