Agent skill
looping-pr-reviews
Waits for PR reviews and automatically applies fixes in a loop. Analyzes review comments and commits corrections until approval. Use for "리뷰 대기", "리뷰 반영", "자동 리뷰 수정", "review loop" requests.
Install this agent skill to your Project
npx add-skill https://github.com/jiunbae/agent-skills/tree/main/development/pr-review-loop
SKILL.md
PR Review Loop
Auto-fix PR reviews until approval.
Flow
PR Created → Wait for Review → Analyze Comments → Fix Issues → Push → Repeat
Workflow
Step 1: Get PR Info
PR_NUMBER=$(gh pr view --json number -q '.number')
LAST_COMMIT=$(git log -1 --format=%cI)
Step 2: Wait for Reviews
# Check for new reviews (every 60s, max 10 attempts)
gh api repos/{owner}/{repo}/pulls/$PR_NUMBER/reviews
gh api repos/{owner}/{repo}/pulls/$PR_NUMBER/comments
Step 3: Analyze Review
Classify comments:
- Fix needed: Code changes, bugs, improvements
- No fix: LGTM, questions, praise
Step 4: Apply Fixes
# Make changes based on review
git add -A
git commit -m "fix: address review comments"
git push
Step 5: Request Re-review
# Comment with /gemini review trigger
gh pr comment $PR_NUMBER --body "Applied fixes.
/gemini review"
⚠️ IMPORTANT: Always include /gemini review in comment to trigger next review!
Exit Conditions
- Review approved (LGTM)
- Max attempts reached (timeout)
- No actionable feedback
Commands
# Check review status
gh pr view --json reviews
# Get review comments
gh api repos/{owner}/{repo}/pulls/{number}/comments
# Request reviewer
gh api repos/{owner}/{repo}/pulls/{number}/requested_reviewers \
--method POST --field 'reviewers[]=username'
Best Practices
DO:
- Always include
/gemini reviewin response comments - Commit atomic fixes
- Report uncertain changes to user
DON'T:
- Auto-fix architecture changes
- Skip test runs
- Ignore review context
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
jiunbae/agent-skills
implementing-in-background
Orchestrates multiple AI agents (Claude, Codex, Gemini) for parallel implementation in the background. Separates independent tasks from planning docs, each agent writes code directly. Context-safe with auto-save. Use for "백그라운드 구현", "bg impl", "병렬 구현", "Codex로 구현", "구현해줘", "코드 작성해줘" requests.
jiunbae/agent-skills
review-fix-loop
Autonomous review-fix cycle that continuously reviews code using background-reviewer, fixes issues, and repeats until all findings are resolved. Use for "리뷰 루프", "자동 개선", "review fix loop", "리뷰 반복", "코드 개선 루프", "keep reviewing" requests.
jiunbae/agent-skills
planning-in-background
Orchestrates multiple AI agents (Claude, Codex, Gemini) for parallel planning in the background with auto-save. Agents continue running even when session hits context limits. Use for "백그라운드 기획", "bg plan", "병렬 기획", "멀티 AI 기획", "기획해줘", "N명이 기획", "계획", "플래닝", "plan", "설계" requests.
jiunbae/agent-skills
background-reviewer
Orchestrates multi-LLM parallel code review using Claude, Codex, and Gemini. Each agent reviews from a different perspective using agent personas (security, architecture, code quality, performance). Supports persona-based review via `agt persona review`. Use for "코드 리뷰", "리뷰해줘", "bg review", "멀티 리뷰", "background review", "페르소나 리뷰" requests.
jiunbae/agent-skills
managing-context
Discovers and loads relevant project context from markdown documentation before each task. Matches context documents based on keywords, file paths, and task types. Use at task start to access project plans, architecture, and implementation status.
jiunbae/agent-skills
indexing-static-context
Provides an index of global static context files in ~/.agents/. Returns appropriate static file paths for natural language queries like "내 정보", "보안 규칙". Use when other skills or agents need to locate reference information.
Didn't find tool you were looking for?