agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when deciding Server vs Client Component boundaries in Next.js 16, fetching data directly in components, or streaming with Suspense.
$ npx -y skills add fusengine/agents --skill nextjs-server-components --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nextjs-server-componentsContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when deciding Server vs Client Component boundaries in Next.js 16, fetching data directly in components, or streaming with Suspense.
name: nextjs-server-components description: Use when deciding Server vs Client Component boundaries in Next.js 16, fetching data directly in components, or streaming with Suspense. versions: nextjs: 16 react: 19 user-invocable: true references: references/rsc-patterns.md, references/streaming.md related-skills: nextjs-16, nextjs-tanstack-query, react-19
<objective> Explains React Server Components as the default rendering model in Next.js 16 with React 19: when to add `'use client'` (hooks, events, browser APIs) versus staying server-only, async Server Components with direct database/file access (no API layer needed), serialization rules for props crossing the server/client boundary (no functions/classes/Dates), and streaming with Suspense boundaries.
Covers composition patterns (passing Server Components as `children` into Client Components), the `server-only` package to prevent accidental secret leakage, parallel data fetching with `Promise.all()`, and caching server computations with `use cache`. Does not cover Next.js routing/caching APIs generally (nextjs-16) or client-side data-fetching libraries (nextjs-tanstack-query) — this skill is specifically about the server/client component boundary itself. </objective>
Server Components are the default rendering model in Next.js 16 with React 19.
Before ANY implementation, spawn 3 agents in parallel, one `Agent` call each with a `name`:
1. **fuse-ai-pilot:explore-codebase** - Analyze existing component boundaries 2. **fuse-ai-pilot:research-expert** - Verify latest RSC docs via Context7/Exa 3. **mcp__context7__query-docs** - Check Next.js 16 RSC patterns
After implementation, run **fuse-ai-pilot:sniper** for validation.
---
| Feature | Benefit | |---------|---------| | Zero client JS | Components never ship to the browser bundle | | Direct data access | Query databases, read files without API layer | | Streaming | Progressive rendering with Suspense boundaries | | Automatic code splitting | Client Components are lazy-loaded by default | | SEO-friendly | Full HTML rendered on the server |
---
1. **Server Components are default** - No directive needed 2. **`'use client'` only when needed** - Hooks, events, browser APIs 3. **Never import server-only into client** - Use `server-only` package 4. **Props must be serializable** - No functions, classes, or Dates across boundary 5. **Async components are server-only** - Client Components cannot be async 6. **Colocate data fetching** - Fetch where the data is consumed
---
1. **Push client boundaries down** - Keep `'use client'` as deep as possible 2. **Composition pattern** - Pass Server Components as `children` to Client 3. **Use `server-only`** - Prevent accidental client imports of secrets 4. **Parallel fetching** - Use `Promise.all()` for independent data 5. **Cache with `use cache`** - Cache expensive server computations 6. **Stream with Suspense** - Wrap slow components for progressive loading
---
| Need | Reference | |------|-----------| | Server vs Client patterns | [rsc-patterns.md](references/rsc-patterns.md) | | Streaming and Suspense | [streaming.md](references/streaming.md) | | Data fetching in RSC | [rsc-patterns.md](references/rsc-patterns.md) | | Loading states | [streaming.md](references/streaming.md) |
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).