Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Coordinates frontend development tasks (React, TypeScript, UI/UX). Use when implementing user interfaces, components, state management, or visual features. Applies frontend-standard.md for quality gates.
.claude/skills/aiskillstore-frontend-orchestrator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -44% | 0% |
Acts as CTO-Frontend, managing all UI/UX tasks, React components, state management, and visual testing.
ai-state/active/frontend/ ├── components.json # Component registry ├── routes.json # Route definitions ├── state.json # State shape └── tasks/ # Active frontend tasks
react-component-skill - Creates/updates React componentsstate-management-skill - Redux/Context updatesroute-config-skill - React Router changesui-test-skill - Playwright visual testsstyle-skill - Tailwind/CSS updatesyamlcontext: task_id: "task-001-auth" components: existing: ["LoginForm", "AuthContext"] design_system: ["Button", "Input", "Card"] state: current: "auth: { user, token, loading }" available_actions: ["login", "logout", "refresh"] standards: - "react-patterns.md" - "accessibility-wcag.md" test_requirements: visual: ["all viewport sizes", "loading states"]
json{ "task_id": "task-001-auth", "what": "Password reset form", "where": "/src/components/auth/" }
json{ "skill": "react-component-skill", "action": "create", "context": "[prepared context]" }
yamlchecks: ✅ Component renders ✅ Form validation works ✅ Error states display ✅ Responsive on mobile ✅ Keyboard navigable ✅ Screen reader compatible
Updates frontend-developer.md with:
json{ "event": "backend.api.updated", "endpoint": "/api/auth/reset", "changes": ["new response format"] }
json{ "event": "frontend.component.created", "component": "PasswordResetForm", "location": "/src/components/auth/", "tests": "passed", "coverage": "92%" }
Solution: Add memoization, check dependency arrays
Solution: Check immutability, verify reducer logic
Solution: Add wait conditions, stabilize animations
❌ Business logic in components ❌ Direct DOM manipulation ❌ Inline styles (use Tailwind) ❌ Skipping error boundaries ❌ Ignoring accessibility ❌ Creating mega-components
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→fail | 20,373 | 14,472 | -29% | 1 | 1 | 0% | 2,379 | 2,686 | +13% | 0 | 0 | — |
case-01 | fail→pass | 43,856 | 23,987 | -45% | 1 | 1 | 0% | 8,256 | 4,801 | -42% | 0 | 0 | — |
case-02 | fail→pass | 21,592 | 18,378 | -15% | 1 | 1 | 0% | 3,946 | 4,595 | +16% | 0 | 0 | — |
case-03 | fail→fail | 47,127 | 19,457 | -59% | 1 | 1 | 0% | 8,255 | 4,575 | -45% | 0 | 0 | — |
case-04 | fail→pass | 24,476 | 11,921 | -51% | 1 | 1 | 0% | 4,900 | 2,434 | -50% | 0 | 0 | — |
case-05 | pass→pass | 15,291 | 7,840 | -49% | 1 | 1 | 0% | 1,727 | 1,449 | -16% | 0 | 0 | — |
case-06 | pass→pass | 32,993 | 11,303 | -66% | 1 | 1 | 0% | 2,444 | 2,849 | +17% | 0 | 0 | — |
case-07 | fail→pass | 17,843 | 39,693 | +122% | 1 | 1 | 0% | 3,411 | 3,872 | +14% | 0 | 0 | — |
case-08 | pass→pass | 21,370 | 15,072 | -29% | 1 | 1 | 0% | 2,777 | 2,793 | +1% | 0 | 0 | — |
case-09 | fail→pass | 15,735 | 3,316 | -79% | 1 | 1 | 0% | 2,954 | 1,661 | -44% | 0 | 0 | — |
case-10 | fail→pass | 8,763 | 8,357 | -5% | 1 | 1 | 0% | 1,531 | 1,750 | +14% | 0 | 0 | — |
case-11 | pass→pass | 16,178 | 15,262 | -6% | 1 | 1 | 0% | 1,926 | 2,927 | +52% | 0 | 0 | — |
case-12 | pass→pass | 9,227 | 12,576 | +36% | 1 | 1 | 0% | 1,575 | 2,368 | +50% | 0 | 0 | — |
case-13 | pass→pass | 13,134 | 18,063 | +38% | 1 | 1 | 0% | 2,429 | 3,479 | +43% | 0 | 0 | — |
case-14 | fail→pass | 21,068 | 12,132 | -42% | 1 | 1 | 0% | 2,645 | 2,443 | -8% | 0 | 0 | — |
case-16 | fail→pass | 7,723 | 3,135 | -59% | 1 | 1 | 0% | 1,171 | 1,690 | +44% | 0 | 0 | — |
case-17 | fail→pass | 7,779 | 2,297 | -70% | 1 | 1 | 0% | 1,107 | 1,494 | +35% | 0 | 0 | — |
case-18 | fail→pass | 11,572 | 1,971 | -83% | 1 | 1 | 0% | 1,033 | 1,424 | +38% | 0 | 0 | — |
case-19 | pass→pass | 12,097 | 9,113 | -25% | 1 | 1 | 0% | 1,185 | 2,519 | +113% | 0 | 0 | — |
case-20 | pass→pass | 10,736 | 11,234 | +5% | 1 | 1 | 0% | 1,094 | 2,187 | +100% | 0 | 0 | — |
case-21 | pass→pass | 12,768 | 20,155 | +58% | 1 | 1 | 0% | 2,472 | 4,027 | +63% | 0 | 0 | — |
case-22 | pass→pass | 10,926 | 16,046 | +47% | 1 | 1 | 0% | 2,078 | 3,184 | +53% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.