This skill should be used for integrating PR review comments back into devloop plan, parsing review feedback, addressing reviewer concerns
Integrates PR review comments into devloop plan by parsing feedback and creating trackable tasks.
npx claudepluginhub zate/cc-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Parse PR review comments and integrate actionable items into the devloop plan.
Get PR details with comments:
# View PR with all comments
gh pr view --json number,title,body,comments,reviews,reviewDecision
# Get review comments (inline code comments)
gh api repos/{owner}/{repo}/pulls/{number}/comments
# Get PR conversation comments
gh api repos/{owner}/{repo}/issues/{number}/comments
Key fields to extract:
| Field | Purpose |
|---|---|
reviewDecision | APPROVED, CHANGES_REQUESTED, REVIEW_REQUIRED |
reviews | List of reviews with state and body |
comments | Conversation comments |
Categorize feedback:
| Type | Description |
|---|---|
| Blocker | Must fix before merge |
| Suggestion | Should consider |
| Question | Needs response |
| Nitpick | Nice to have |
Identify actionable items:
Look for patterns:
Create PR Feedback section in plan:
## PR Feedback
PR #123 - Review by @reviewer (CHANGES_REQUESTED)
### Blockers
- [ ] [PR-123-1] Fix null handling in parseConfig (@reviewer)
- [ ] [PR-123-2] Add tests for edge cases (@reviewer)
### Suggestions
- [ ] [PR-123-3] Consider caching config (@reviewer)
### Questions
- [ ] [PR-123-4] Respond: Why not use existing parser? (@reviewer)
Task ID format: [PR-{number}-{item}]
When addressing feedback:
Reply template:
gh pr comment {number} --body "Addressed in commit {sha}:
- Fixed null handling
- Added edge case tests"
# 1. Check PR status
gh pr view --json reviewDecision,reviews
# 2. If changes requested, get details
gh pr view --comments
# 3. Parse into plan tasks (manual or use /devloop:pr-feedback)
# 4. Work through feedback tasks
# 5. Push and reply
git push
gh pr comment --body "Ready for re-review"
The /devloop:pr-feedback command automates:
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.