From ui-operator
Rerun ui-operator web or mobile capture, compare, and review after UI code changes, preserving prior evidence. Use for "다시 캡처", "모바일 다시 캡처", "개선 후 재비교", "반복 확인", "rerun UI compare", "iterate visual review", "after fix screenshots". Writes a new artifacts/ui-operator/SLUG/iterations/RUN_ID/ evidence set or updates review.md with iteration notes. Do not modify product code.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ui-operator:iterateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use after the user or agent has changed UI code and wants the same page/state evidence rerun.
Use after the user or agent has changed UI code and wants the same page/state evidence rerun.
Writes only under:
artifacts/ui-operator/<slug>/iterations/<run-id>/
├── comparison-data.json
├── report.html
├── review.md
└── screenshots/
May append an iteration summary to:
artifacts/ui-operator/<slug>/review.md
Never modify product source files.
Load prior run
capture-plan.json, comparison-data.json, report.html, and review.md if present.Decide rerun scope
Capture again
iterations/<run-id>/, not over the prior evidence.Compare and review
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 edonghyun/donghyuns-agent-tools