From rn-launch-harness
Displays rn-harness pipeline status, progress, current phase, rounds, scores, and recent events from state.md and build-log.md. Useful for monitoring automated build and QA cycles.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rn-launch-harness:rn-harness-statusThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
현재 파이프라인 진행 상황을 표시한다.
현재 파이프라인 진행 상황을 표시한다.
/rn-harness --status/rn-harness-status--verbose — 최신 피드백 요약 포함--log — 최근 20개 이벤트 표시docs/harness/state.md에서:
라운드별 결과 테이블.
[프로젝트명]
Status: [running/paused/completed]
Phase: [current_phase] | Round: [current_round]
Next: [next_role]
Pipeline Progress:
[x] Research — 완료
[x] Plan — 완료
[x] Design — 완료
[x] Contract — 완료
[ ] Generator — 진행 중 (Round 2)
[ ] Evaluator
[ ] AdMob
[ ] Build
[ ] Screenshot
[ ] Submit
Round | Phase | Score | Duration | Notes
------|-------|-------|----------|------
1 | Build | - | 45m |
1 | QA | 5/10 | 8m | 7 criteria failed
2 | Build | - | 20m | Fix round
--verbose 시:
Latest Feedback:
- [FAIL] 기준 3: SafeAreaView 누락 (profile.tsx)
- [FAIL] 기준 7: 에러 상태 미처리
- Score: 5/10
--log 시:
Recent Events:
| Time | Event | Phase | Details |
|------|-------|-------|---------|
| 14:30 | DISPATCH | generator | Round 2 시작 |
| 14:10 | JUDGMENT | evaluator | FAIL (5/10) |
| 13:25 | DISPATCH | evaluator | Round 1 QA |
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub tjdrhs90/rn-launch-harness --plugin rn-launch-harness