Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Frontend development for React, Next.js, TypeScript, and Tailwind CSS. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding projects, implementing accessibility, or reviewing frontend code.
.claude/skills/borghei-senior-frontend/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 131% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 52% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 71% | 0% |
Frontend development patterns, performance optimization, and automation tools for React/Next.js applications. Scaffold projects, generate components and hooks, analyze bundle sizes, and apply React/Next.js patterns with accessibility and testing built in.
package.json + import scanning that scores bundle health and flags heavy dependencies with lighter alternatives.Before scaffolding or generating, confirm these inputs. If any is unknown or vague, ASK — do not assume:
--template; produces a different project structure)--features; decides what gets generated)frontend_scaffolder vs component_generator)Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
| Tool | Purpose | Command | |------|---------|---------| | frontend_scaffolder.py | Scaffold a Next.js or React project with TypeScript + Tailwind + optional features | python scripts/frontend_scaffolder.py my-app --template nextjs --features auth,api | | component_generator.py | Generate a component/hook with optional test and Storybook story | python scripts/component_generator.py ProductCard --type client --with-test --with-story | | bundle_analyzer.py | Score bundle health and flag heavy dependencies from package.json + imports | python scripts/bundle_analyzer.py /path/to/project --verbose |
Load the reference that matches the task — keep this file lean and pull detail on demand:
What this skill covers:
package.json dependency inspection and import pattern scanningWhat this skill does NOT cover:
| Skill | Integration | Data Flow | |-------|-------------|-----------| | senior-fullstack | Scaffolded frontend projects connect to fullstack project scaffolder for API layer setup | Frontend project structure feeds into project_scaffolder.py which adds backend, Docker, and CI/CD layers | | senior-backend | Components consuming API data follow patterns defined by backend skill's REST/GraphQL conventions | Backend API response types imported into frontend types/ directory generated by this skill | | senior-qa | Generated test files (--with-test) use the same Testing Library conventions that the QA skill's test strategies build upon | Component test files hand off to QA skill for integration and E2E test coverage expansion | | senior-devops | Bundle analyzer output informs build pipeline optimization decisions | Bundle health score and dependency warnings feed into CI quality gates configured by DevOps skill | | senior-secops | Dependency analysis identifies packages that need security audit | Heavy/outdated dependency warnings from bundle_analyzer.py trigger security review workflows | | code-reviewer | Generated components follow patterns that the code reviewer skill validates | Code reviewer checks generated components against React/TypeScript best practices defined in this skill's references |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,397 | 4,052 | -72% | 1 | 1 | 0% | 2,252 | 1,973 | -12% | 0 | 0 | — |
case-02 | fail→fail | 25,624 | 49,892 | +95% | 1 | 1 | 0% | 5,234 | 6,085 | +16% | 0 | 0 | — |
case-03 | fail→pass | 14,821 | 22,313 | +51% | 1 | 1 | 0% | 2,190 | 5,061 | +131% | 0 | 0 | — |
case-04 | fail→pass | 17,917 | 12,350 | -31% | 1 | 1 | 0% | 3,428 | 3,441 | +0% | 0 | 0 | — |
case-05 | fail→fail | 15,298 | 21,402 | +40% | 1 | 1 | 0% | 2,814 | 5,681 | +102% | 0 | 0 | — |
case-06 | fail→pass | 16,447 | 19,788 | +20% | 1 | 1 | 0% | 3,354 | 5,091 | +52% | 0 | 0 | — |
case-07 | fail→fail | 18,909 | 20,668 | +9% | 1 | 1 | 0% | 2,786 | 3,454 | +24% | 0 | 0 | — |
case-08 | fail→pass | 7,015 | 4,056 | -42% | 1 | 1 | 0% | 1,152 | 1,966 | +71% | 0 | 0 | — |
case-09 | fail→fail | 10,661 | 5,449 | -49% | 1 | 1 | 0% | 1,904 | 2,337 | +23% | 0 | 0 | — |
case-10 | fail→pass | 10,063 | 3,077 | -69% | 1 | 1 | 0% | 1,592 | 1,870 | +17% | 0 | 0 | — |
case-11 | fail→pass | 10,939 | 3,329 | -70% | 1 | 1 | 0% | 1,621 | 1,865 | +15% | 0 | 0 | — |
case-12 | fail→pass | 5,219 | 2,492 | -52% | 1 | 1 | 0% | 749 | 1,737 | +132% | 0 | 0 | — |
case-13 | fail→pass | 11,294 | 3,673 | -67% | 1 | 1 | 0% | 1,799 | 2,015 | +12% | 0 | 0 | — |
case-14 | fail→pass | 15,620 | 3,546 | -77% | 1 | 1 | 0% | 2,606 | 1,903 | -27% | 0 | 0 | — |
case-15 | fail→pass | 15,955 | 2,984 | -81% | 1 | 1 | 0% | 2,341 | 1,813 | -23% | 0 | 0 | — |
case-16 | fail→pass | 10,727 | 3,111 | -71% | 1 | 1 | 0% | 1,735 | 1,822 | +5% | 0 | 0 | — |
case-17 | fail→pass | 12,244 | 15,526 | +27% | 1 | 1 | 0% | 2,523 | 4,433 | +76% | 0 | 0 | — |
case-18 | fail→pass | 18,614 | 14,357 | -23% | 1 | 1 | 0% | 2,559 | 3,644 | +42% | 0 | 0 | — |
case-19 | fail→pass | 18,134 | 13,887 | -23% | 1 | 1 | 0% | 2,570 | 3,682 | +43% | 0 | 0 | — |
case-20 | pass→pass | 15,505 | 12,128 | -22% | 1 | 1 | 0% | 2,226 | 3,087 | +39% | 0 | 0 | — |
case-21 | fail→pass | 15,067 | 9,676 | -36% | 1 | 1 | 0% | 2,023 | 2,616 | +29% | 0 | 0 | — |
case-22 | pass→pass | 15,778 | 8,797 | -44% | 1 | 1 | 0% | 2,226 | 2,650 | +19% | 0 | 0 | — |
case-23 | pass→pass | 19,177 | 13,650 | -29% | 1 | 1 | 0% | 2,612 | 3,300 | +26% | 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. 23 cases were attempted. The headline lift of +70 percentage points is the difference between those two pass rates over the 23 comparable cases.
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.