frontend-development
Use this skill for ANY work involving React, Next.js, TypeScript, or Tailwind in the browser layer. This includes building components and pages, but equally covers debugging and fixing frontend issues: CSS/Tailwind classes not applying, form validation behavior, hydration mismatches between server and client renders, styling bugs, layout shifts, and rendering problems. Also use for refactoring components (e.g., splitting Server vs Client Components), data fetching patterns, state management, bundle optimization, and frontend tooling. If the problem involves what users see or interact with in a web browser — whether building, fixing, or refactoring — use this skill. Not for backend APIs, databases, infrastructure, or DevOps.
git clone --depth 1 https://github.com/avibebuilder/claude-prime /tmp/frontend-development && cp -r /tmp/frontend-development/.claude/starter-skills/frontend-development ~/.claude/skills/frontend-developmentSKILL.md
# Frontend Development
Project-specific patterns for React/Next.js/TypeScript frontend work.
## Architecture Decisions
### Server-First Boundaries
Start with Server Components. Only add `'use client'` when you need interactivity, state, or browser APIs. Extract only the interactive leaf — not the entire page or section.
### Colocation Over Centralization
Types, hooks, and utilities that serve one feature live in that feature's directory. Only truly shared code goes in global directories.
### Composition Over Customization
Compose existing components rather than adding props/variants. shadcn/ui components are meant to be copied and modified. Build up from primitives.
### Data Flows Down, Events Flow Up
Server fetches data and passes it as props. Client components handle interactions and call server actions. Never fetch in client components what could be fetched on the server.
## Gotchas
- `'use client'` does NOT mean "runs only in the browser" — it runs on the server during SSR too. It means "include in the client bundle." Putting secrets or DB calls in a `'use client'` file will leak them.
- Importing a Server Component into a Client Component makes it a Client Component. The boundary propagates DOWN. Pass server content as `children` props instead.
- `useEffect` with empty deps fires AFTER paint — use `useLayoutEffect` for DOM measurements that affect layout, but never in Server Components.
- Next.js `fetch()` caches by default in App Router. Add `{ cache: 'no-store' }` or `revalidate: 0` for data that must be fresh. Forgetting this causes stale data bugs that only appear in production.
- Tailwind classes are purged at build time — dynamically constructed class names like `` bg-${color}-500 `` will be missing. Use complete class names or safelist them.
- `key` prop on mapped elements must be stable and unique. Using array index as key causes subtle bugs when list items are reordered, inserted, or deleted.
- `useSearchParams()` requires a `<Suspense>` boundary in Next.js App Router or the entire page becomes client-rendered.
- shadcn/ui components are source code, not a library. After `npx shadcn-ui add`, the component lives in YOUR codebase — modify it directly, don't wrap it.
- React Hook Form's `register()` returns a ref — don't also pass your own `ref` to the same input without merging them.
- `async` Server Components that throw `redirect()` or `notFound()` must NOT be wrapped in try/catch — these work by throwing special errors that Next.js catches upstream.
## Quick Start
1. **Check file structure** — App Router or plain React? Check references below.
2. **Identify the feature boundary** — What feature does this work belong to?
3. **Start with Server Component** — Only add `'use client'` when you hit a wall
4. **Name files specifically** — `login-form.tsx` not `form.tsx`. Must be grep-findable.
5. **Match existing patterns** — Read 2-3 similar files before creating new ones
## References
| When you need... | Read |
|------------------|------|
| File naming, imports, exports | [conventions.md](./references/conventions.md) |
| Next.js App Router patterns | [overview.md](./references/nextjs/overview.md) |
| React component patterns | [overview.md](./references/react/overview.md) |
| TypeScript project patterns | [typescript.md](./references/typescript.md) |
| shadcn/ui + Dice UI usage | [shadcn.md](./references/shadcn.md) |
| Tailwind configuration | [tailwind.md](./references/tailwind.md) |
| Data fetching (tRPC, TanStack, axios) | [overview.md](./references/data-fetching/overview.md) |
| Biome/linter config | [biome.md](./references/biome.md) |
## Official Resources
For general framework docs beyond project-specific patterns, consult:
| Framework | URL |
|-----------|-----|
| Next.js | https://nextjs.org/docs |
| React | https://react.dev |
| TypeScript | https://www.typescriptlang.org/docs |
| Tailwind CSS | https://tailwindcss.com/docs |
| shadcn/ui | https://ui.shadcn.com/docs |
| Dice UI | https://www.diceui.com/docs |
| TanStack Query | https://tanstack.com/query/latest/docs |
| tRPC | https://trpc.io/docs |
| Zustand | https://zustand.docs.pmnd.rs |
| React Hook Form | https://react-hook-form.com |
| Zod | https://zod.dev |
| Biome | https://biomejs.dev |
| nuqs | https://nuqs.47ng.com |Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Answer questions about code, architecture, and technical decisions — no implementation. Trigger on questions asking 'why', 'what does this do', 'what is the purpose of', 'explain', 'what's the difference', 'compare', or 'what are the tradeoffs' — even when referencing specific files, code snippets, or inline code. The key signal is the user wants to UNDERSTAND something, not change it. Do NOT trigger for requests to build, fix, plan, review, research, or add/modify code.
Implement, build, create, or add any feature, endpoint, page, component, or functionality. Use this skill whenever the user asks you to write new code or make code changes — whether it's adding an API endpoint, building a UI page, creating an export feature, wiring up a webhook, implementing a search/filter, or any other hands-on coding task. This is the default skill for all 'build this', 'add this', 'create this', 'wire up', 'implement' requests. Covers the full cycle: clarify requirements, plan if needed, write code, verify, and review. Do NOT use for pure research, debugging, documentation, or explanation — only when the user wants working code delivered.
Use when the user wants to save knowledge as a file so others don't have to rediscover it — \"turn this into a doc\", \"write this up\", \"document how X works\", \"we figured this out and want to capture it\", \"nobody should have to figure this out again\". Covers any request to create or update durable written artifacts: onboarding guides, runbooks, ADRs, API docs, architecture notes, postmortems, changelogs, setup guides. The trigger: user wants knowledge captured in a file for future reference, not just a conversation. Do NOT use when still making decisions (→ give-plan), just asking for explanation without a file (→ ask), or writing code (→ cook).
Investigate unexpected behavior and mysterious bugs. Use when the cause of a problem is unknown and the user needs to understand WHY something is happening — symptoms like: sudden unexplained changes in metrics or behavior, works locally but not in staging/production, inconsistent or intermittent failures, correct code producing wrong results, operations succeeding but having no effect, environment-specific failures, duplicate executions, stale data, or any \"why did this change?\" or \"why is this happening?\" situation. Covers infrastructure anomalies (cache hit rates dropping, latency spikes, queue behavior shifts) as well as code bugs. The key signal is confusion about root cause, not a request to implement a known fix. Do NOT use for feature requests, known fixes, planning, or documentation tasks.
Brainstorms and debates approaches, then drives toward an actionable decision. Use whenever someone needs a thinking partner for a decision they're facing: 'discuss', 'debate', 'brainstorm', 'weigh options', 'tradeoffs', 'should I do X or Y', 'help me decide', 'I'm torn between', 'sanity check my thinking', or 'what do you think about'. The user must be asking for help reasoning through a choice — not asking to build, fix, evaluate, plan, or modify something (even if the topic involves this skill itself). Picks the right decision lens, surfaces tradeoffs and blind spots, pushes back when reasoning is genuinely weak, and never implements.
Fetch up-to-date documentation for any library, framework, API, or service into context. Use when the user wants to look up API references, check function signatures or required fields, find feature-specific docs, or verify how an external tool actually works. Triggers for queries about third-party libraries like Stripe, SQLAlchemy, Tailwind, FastAPI, shadcn, Drizzle, Hono, Better Auth — any time the answer lives in official docs rather than in the project codebase. Use this instead of guessing from trained knowledge, which is stale.
Fix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, or a prior diagnosis to implement. Do NOT use for new features, pure explanation, architecture discussion, broad research, or bug reports where the main need is figuring out why the behavior happens — use diagnose for that.