brainstorming-extensio…
Enforces design review gate after brainstorming — bridges superpowers:brainstorming into the metaswarm quality pipeline
Address PR review feedback systematically — fetch inline comments, review bodies, handle outside-diff-range comments, resolve threads with proper attribution
$ npx -y skills add dsifry/metaswarm --skill handling-pr-comments --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/handling-pr-commentsContext preview
The summary Claude sees to decide when to auto-load this skill.
Address PR review feedback systematically — fetch inline comments, review bodies, handle outside-diff-range comments, resolve threads with proper attribution
name: handling-pr-comments description: Address PR review feedback systematically — fetch inline comments, review bodies, handle outside-diff-range comments, resolve threads with proper attribution
Use when addressing PR review feedback, after receiving review comments from CodeRabbit, Cursor, or human reviewers - ensures systematic responses to each comment thread with proper attribution and thread resolution.
Activate this skill when ANY of these conditions are true:
**Most developers forget steps 4-6. This skill ensures they happen.**
Run the filtering script to identify actionable comments:
# Filter actionable vs non-actionable comments bin/pr-comments-filter.sh <PR_NUMBER>
This script:
The filter script categorizes by priority:
| Priority | Marker | Action | | --------------- | -------------------------------------------------------- | ---------------- | | CRITICAL | `_⚠️ Potential issue_ \| _🔴 Critical_` | Fix immediately | | HIGH | `_⚠️ Potential issue_ \| _🟠 Major_` | Fix before merge | | MEDIUM | `_🟡 Minor_` or `_🛠️ Refactor suggestion_ \| _🟠 Major_` | Should fix | | LOW | `_🔵 Trivial_` / `_🧹 Nitpick_` | Fix if quick | | HUMAN | Non-bot comments | Always process |
For each actionable comment, further categorize as:
1. **Bug/Issue** - Must fix 2. **Enhancement** - Should fix 3. **Nitpick** - Nice to fix 4. **Question** - Needs clarification 5. **Intentional** - Decline with explanation 6. **Out-of-Scope** - See Phase 2b
**COMMONLY MISSED**: CodeRabbit posts "Outside diff range" comments in the **review body**, not as inline threads. These are actionable feedback that MUST be addressed.
# Extract Outside diff range comments from review bodies
PR_NUMBER=<number>
OWNER=$(gh repo view --json owner -q .owner.login)
REPO_NAME=$(gh repo view --json name -q .name)
echo "=== OUTSIDE DIFF RANGE COMMENTS ==="
gh api "repos/$OWNER/$REPO_NAME/pulls/$PR_NUMBER/reviews" --paginate | \
jq -r '.[] | select(.body | test("Outside diff range"; "i")) |
"Review ID: \(.id)\n\(.body)\n---"'**These comments are NOT in threads** - they cannot be replied to inline. You must:
1. Parse the file paths and line numbers from the review body 2. Address the feedback in your code 3. Commit and push 4. Leave a general PR comment acknowledging you addressed them
Run the out-of-scope detection script:
# Detect out-of-scope comments bin/pr-comments-out-of-scope.sh <PR_NUMBER>
This script detects comments that:
**IMPORTANT**: Treat out-of-scope comments as **IN SCOPE** by default.
Use **ultrathink** to evaluate each out-of-scope comment:
ultrathink: Analyze this out-of-scope review comment: - What is the reviewer asking for? - How complex is this change? (lines of code, files affected) - Does it require refactoring other systems? - Can I complete this in under 30 minutes? - Are there any risks or dependencies? Recommend: FIX_NOW or CREATE_ISSUE
| Criteria | Action | | --------------------------------------------- | ----------------------------------------- | | Simple fix (< 30 min, < 3 files, no refactor) | **FIX_NOW** - Make the change immediately | | Medium complexity (unclear scope) | **ASK_USER** - Present options | | Major refactor (multiple systems, risky) | **CREATE_ISSUE** - Document for follow-up |
1. Make the fix 2. Commit with descriptive message 3. Push to the PR branch 4. Reply: "Fixed in commit <hash>. This was outside the original PR scope but straightforward to address." 5. Resolve the thread
1. Create GitHub issue with context 2. Reply: "Created issue #<number> to track this." 3. Resolve the thread
Fix the actual code issues. Commit and push.
**After pushing fixes, respond to EACH comment thread individually:**
PR_NUMBER=<number> OWNER=$(gh repo view --json owner -q .owner.login) REPO_NAME=$(gh repo view --json name -q .name) CURRENT_USER=$(gh api user -q '.login') COMMENT_ID=<id-from-filter-script> gh api "/repos/$OWNER/$REPO_NAME/pulls/$PR_NUMBER/comments/$COMMENT_ID/replies" \ -X POST \ -f body="Fixed in commit $(git rev-parse --short HEAD). *(Response by Claude on behalf of @$CURRENT_USER)*"
**Every thread must be resolved after responding.** Use GraphQL to resolve:
THREAD_ID="PRRT_kwDOK-xA485..." # From GraphQL query
gh api graphql -f query='mutation {
resolveReviewThread(input: {threadId: "'"$THREAD_ID"'"}) {
thread { id isResolved }
}
}'1. **Query the comment author** asking for
A self-improving multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI.
Enforces design review gate after brainstorming — bridges superpowers:brainstorming into the metaswarm quality pipeline
Create comprehensive GitHub issues with TDD plans, acceptance criteria, and agent instructions for autonomous PR lifecycle…
Automatic review gate that runs after brainstorming completes - spawns PM, Architect, Designer, Security, and CTO agents in…
Delegate implementation and review tasks to external AI CLI tools (Codex, Gemini) with cross-model adversarial review
Analyze the current session and write a self-contained handoff document so a fresh agent can resume the work with full context —…
Migrate from npm-installed metaswarm to the marketplace plugin — removes redundant files with safety checks