By edonghyun
Evidence-backed UI iteration operator for comparing baseline and current web, mobile web, native mobile, and local session-derived UI states during product UI changes.
Capture UI screenshots for ui-operator web route/state plans and native mobile screen/state plans, including pages, screens, modals, dropdowns, drawers, bottom sheets, tabs, and responsive states. Use for "페이지 캡처", "모바일 화면 캡처", "iOS/Android 스샷", "모달 스샷", "상태별 스크린샷", "baseline/current 캡처", "capture UI states", "modal screenshots". Writes screenshots and comparison-data.json under artifacts/ui-operator/SLUG/. Do not use for external PoC intake.
Generate a ui-operator side-by-side baseline/current comparison report from web URLs, native mobile capture commands, a capture plan, or existing screenshot folders. Use for "before/after 비교", "baseline current 비교", "모바일 화면 비교", "비교 리포트", "visual diff", "side-by-side report", "스크린샷 비교". Writes artifacts/ui-operator/SLUG/report.html and comparison-data.json only. Do not modify source code.
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.
Map a web/mobile UI task, current diff, changed files, PR, branch, or local Codex session id into a ui-operator capture plan. Use for "영향받는 페이지 잡아줘", "모바일 화면 목록", "세션 기반 캡처 계획", "캡처 계획", "페이지/모달 목록", "iOS/Android 화면 캡처 계획", "diff 기반 UI 캡처", "affected surfaces", "capture plan". Writes artifacts/ui-operator/SLUG/capture-plan.json and manifest.json only. Do not use when the user only wants to run an existing plan.
Write screenshot-backed web or mobile UI/UX findings from a ui-operator comparison report. Use for "UI 리뷰", "모바일 UI 리뷰", "비교 분석", "개선점 정리", "UX 리스크", "visual review", "design QA findings". Writes artifacts/ui-operator/SLUG/review.md only. Do not use without screenshot or blocker evidence.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A host-neutral personal plugin marketplace for coding agents, focused on safety nets — plugins that keep code, spec, tests, and team knowledge in sync rather than generating net-new content.
Read
docs/PHILOSOPHY.mdfor the mission,docs/CONVENTIONS.mdfor the rules every plugin follows, anddocs/CONTRIBUTING.mdto add a new plugin or skill.
# Add marketplace from GitHub.
claude plugin marketplace add edonghyun/donghyuns-agent-tools
# Or, during local development.
claude plugin marketplace add /Users/idonghyeon/projects/donghyuns-agent-tools
# Install plugins.
claude plugin install spec-mirror@donghyuns-agent-tools
claude plugin install qa-operator@donghyuns-agent-tools
claude plugin install feature-intake@donghyuns-agent-tools
claude plugin install ui-operator@donghyuns-agent-tools
# Refresh after marketplace changes.
claude plugin marketplace update donghyuns-agent-tools
claude plugin update qa-operator@donghyuns-agent-tools
claude plugin update feature-intake@donghyuns-agent-tools
claude plugin update ui-operator@donghyuns-agent-tools
Codex support reuses the same plugins/<plugin>/skills/ tree and adds Codex-specific manifests next to the Claude manifests:
.agents/plugins/marketplace.jsonplugins/<plugin>/.codex-plugin/plugin.json# Add marketplace from GitHub.
codex plugin marketplace add edonghyun/donghyuns-agent-tools --ref main
# Or, during local development.
codex plugin marketplace add /Users/idonghyeon/projects/donghyuns-agent-tools
# Install Codex-supported plugins.
codex plugin add qa-operator@donghyuns-agent-tools
codex plugin add feature-intake@donghyuns-agent-tools
codex plugin add ui-operator@donghyuns-agent-tools
# Refresh after marketplace changes.
codex plugin marketplace upgrade donghyuns-agent-tools
codex plugin add qa-operator@donghyuns-agent-tools
codex plugin add feature-intake@donghyuns-agent-tools
codex plugin add ui-operator@donghyuns-agent-tools
Start a new Codex thread after install or update so the refreshed plugin skills are loaded into the session.
Run evidence-backed UI iteration loops for changes already inside a product. ui-operator turns a web, mobile web, native mobile UI task, branch, PR, diff, local Codex session, or paired baseline/current targets into affected page/screen/state planning, route and modal screenshot capture, native app screenshot collection, side-by-side comparison reports, UI/UX findings, and recapture notes after improvements.
Just say:
이번 UI 변경 diff 기준으로 영향받는 페이지/모달 스샷 계획 잡고 baseline/current 비교해줘.
baseline은 localhost:3002, current는 localhost:3004야. 관리자 화면들 before/after 비교 리포트 만들어줘.
iOS/Android 앱 화면도 baseline/current로 스크린샷 수집해서 비교해줘.
이전 로컬 Codex session id에서 UI 작업 맥락을 뽑아서 capture plan 만들어줘.
UI 개선 중간 확인용으로 작업 내용에 따른 캡처와 리뷰 남겨줘.
Skills:
| Command | Description |
|---|---|
/ui-operator:start | Natural-language entry. Plans affected surfaces, captures, compares, reviews, and optionally iterates. |
/ui-operator:plan | Map a task, diff, PR, local session id, or changed files into page/screen/state capture recipes. |
/ui-operator:capture | Capture current or paired baseline/current screenshots for web routes, mobile screens, modals, dropdowns, and responsive states. |
/ui-operator:compare | Generate side-by-side comparison reports from URLs or existing capture folders. |
/ui-operator:review | Write screenshot-backed UI/UX findings grounded in comparison evidence. |
/ui-operator:iterate | Rerun affected captures after code changes and preserve iteration evidence. |
Workflow:
/ui-operator:start
├─ plan
├─ capture
├─ compare
├─ review
└─ iterate, after changes
Plugin docs: CONCEPTS · WORKFLOW-GUIDE · EXAMPLES · TROUBLESHOOTING
Turn external feature artifacts into product integration analysis packages. feature-intake takes VoC-driven PoCs, demo apps, Figma prototypes, internal tools, AI experiments, or screenshots from another team and produces screenshot-backed page-walk traversal, user flows, user journeys, use cases, page-state/control-reaction coverage, product framing, integration fit, risks, MVP boundaries, and handoff documentation.
Just say:
이 PoC를 feature-intake 해줘. 스크린샷 포함해서 유저플로우, 유저저니, 유즈케이스, 제품 편입 분석까지 정리해줘.
와이어프레임 설계용으로 모든 페이지 상태와 버튼 클릭 반응까지 한 번에 정리해줘.
시작 페이지부터 페이지를 순회하면서 링크, 탭, 버튼, 모달 상태까지 캡처해줘.
Skills:
npx claudepluginhub edonghyun/donghyuns-agent-toolsDelegated browser QA operator: plan, run, monitor, triage, and optionally repair acceptance checks from requirements with evidence dashboards.
Turn external feature artifacts, PoCs, demos, prototypes, and VoC experiments into screenshot-backed page-walk product integration analysis packages.
Generate, drift-check, lint, test-stub, coverage-audit and scope-walk E2E specs against the current implementation. A six-skill safety net for keeping code, spec, tests, and team knowledge in sync.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.