Agent skill · Testing & QA

frontend

MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router and brand references; perfection for Playwright/Chromium Lighthouse/Core Web Vitals; ui-ux-db palettes/fonts/guidelines; designpowers personas/accessibility/critique/handoff; plus curl-only lazyweb real-app-screen research and the beui.dev interaction catalog. Triggers: frontend, UI, UX, design, redesign, styling, layout, animation, motion, interaction, micro-interaction, make it feel alive, premiu

YeonGyu-Kim69,732★ · +488/wk · 2 repos on radarProfile →
claude-codecodexcursorships scriptsNOASSERTION
Install
npx skills add code-yeongyu/oh-my-openagent --skill frontend --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 26
SKILL.md size: 19 KB
Bundled scripts: yes
Path: packages/shared-skills/skills/frontend/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 67,209 · +483 this week
Language: TypeScript
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Frontend This file is a router, not a rulebook. The rules live in four rulesets under `references/`; your first job is to load the smallest set of files that covers the request, state which you loaded in one sentence, then execute under their guidance. Loading nothing and freestyling produces the generic AI-slop output this skill exists to prevent; loading everything wastes context and creates contradictory instructions. **The bar is not clean-and-correct — it is work a senior designer at Linear, Stripe, or Supabase would ship.** Correct-but-flat is a failure, not a finish. Protect the surface as hard as you protect the build: design is a first-class deliverable, not a one-shot decision you lock and walk away from. ## Phase 0 — Route (before any UI work) | Request involves… | Read | |---|---| | ANY UI implementation, styling, redesign, mockup, or visual decision | `references/design/README.md` FIRST. It enforces two mandatory gates — the Design System Gate (a `DESIGN.md` must exist before any component is written) and the React Dev Tooling Gate (react-grab / react-scan / react-doctor installed by default) — then routes to the taste and brand references below. | | Interaction or m

What's inside
Steps it walks through
  1. Phase 0 — Route (before any UI work)
  2. Design System and Component Workflow
  3. Ruleset 1 — design (references/design/)
  4. Layer 0 — architecture
  5. Layer B — brand design systems (orthogonal to Layer A; stack freely)
  6. React dev tooling
  7. Ruleset 2 — perfection (references/perfection/)
  8. Ruleset 3 — ui-ux-db (references/ui-ux-db/)
  9. Ruleset 4 — designpowers (references/designpowers/)
  10. Quick routes — most common requests
  11. Shared axioms (all four rulesets agree — apply always)
  12. When to load something else instead
  13. Activation
Ships with 24 files
  • .gitignore
  • .npmignore
  • ATTRIBUTION.md
  • LICENSE-Apache-2.0.txt
  • references/design/README.md
  • references/design/_INDEX.md
  • references/design/aside.md
  • references/design/clone-from-url.md
  • references/design/design-system-architecture.md
  • references/design/interaction-skill.md
  • references/design/layout-skill.md
  • references/design/lazyweb.md
  • references/design/react-dev-tooling-skill.md
  • references/designpowers/EVIDENCE.md
  • references/designpowers/README.md
  • references/designpowers/UPSTREAM.md
  • references/designpowers/lane-a-direction.md
  • references/designpowers/lane-b-execution.md
  • references/designpowers/lane-c-review.md
  • references/designpowers/lane-d-memory.md
  • references/designpowers/orchestration.md
  • references/designpowers/routing.md
  • references/perfection/README.md
  • references/perfection/react-perf-tooling.md
first 24 of 26
Commands it runs
uv run $SKILL_DIR/scripts/perfection/lighthouse-audit.py https://localhost:3000
python3 $SKILL_DIR/references/ui-ux-db/scripts/search.py "<query>" --design-system -p "Project"   # full design-system generation
python3 $SKILL_DIR/references/ui-ux-db/scripts/search.py "<query>" --domain <domain>             # targeted lookup
python3 $SKILL_DIR/references/ui-ux-db/scripts/search.py "<query>" --stack <stack>               # stack best practices
More from oh-my-openagent
All skills →
About this skill
What does the frontend skill do?

MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router and brand references; perfection for Playwright/Chromium Lighthouse/Core Web Vitals; ui-ux-db palettes/fonts/guidelines; designpowers personas/accessibility/critique/handoff; plus curl-only lazyweb real-app-screen research and the beui.dev interaction catalog. Triggers: frontend, UI, UX, design, redesign, styling, layout, animation, motion, interaction, micro-interaction, make it feel alive, premiu

How do I install it?

Run `npx skills add code-yeongyu/oh-my-openagent --skill frontend --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From code-yeongyu/oh-my-openagent, a repository with 67,209 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going