agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when implementing translations in a React app (not Next.js) with react-i18next — useTranslation, namespaces, pluralization, Suspense.
$ npx -y skills add fusengine/agents --skill react-i18n --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/react-i18nContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when implementing translations in a React app (not Next.js) with react-i18next — useTranslation, namespaces, pluralization, Suspense.
name: react-i18n description: Use when implementing translations in a React app (not Next.js) with react-i18next — useTranslation, namespaces, pluralization, Suspense. version: 1.0.0 user-invocable: true references: references/i18next-basics.md, references/typescript-types.md, references/namespaces.md, references/pluralization.md, references/interpolation.md, references/lazy-loading.md, references/language-detection.md, references/react-19-integration.md, references/trans-component.md, references/testing.md, references/rtl-support.md, references/fallback-strategies.md, references/templates/basic-setup.md, references/templates/language-switcher.md, references/templates/typed-translations.md, references/templates/form-validation-i18n.md, references/templates/lazy-loading-routes.md, references/templates/date-number-formatter.md, references/templates/plural-interpolation.md, references/templates/trans-component-examples.md, references/templates/testing-i18n.md
<objective> Implements react-i18next in a React 19 app (Vite/CRA, not Next.js): `useTranslation()` hook usage, the TypeScript Selector API (i18next ≥25.4) for type-safe translation keys, namespace organization for code splitting, pluralization with ICU MessageFormat, interpolation (variables, dates, numbers, currency), lazy-loaded translations, and browser/URL/cookie language detection.
Also covers React 19 Suspense integration, the `Trans` component for JSX inside translations, RTL language support, fallback strategies for missing keys, and unit-testing i18n setups. This skill is explicitly for React apps without Next.js — for Next.js App Router i18n use nextjs-i18n, and for Astro use astro-i18n. </objective>
Before ANY implementation, spawn 3 agents in parallel, one `Agent` call each with a `name`:
1. **fuse-ai-pilot:explore-codebase** - Analyze existing i18n setup and translation patterns 2. **fuse-ai-pilot:research-expert** - Verify latest react-i18next/i18next docs via Context7/Exa 3. **mcp__context7__query-docs** - Check TypeScript Selector API and React 19 Suspense patterns
After implementation, run **fuse-ai-pilot:sniper** for validation.
---
**ALWAYS apply SOLID principles from `solid-react` skill.**
→ See `../solid-react/SKILL.md` for complete rules
**Key Rules:**
---
| Hook | Purpose | Guide | |------|---------|-------| | `useTranslation()` | Access translations and i18n instance | `references/i18next-basics.md` | | `useTranslation(ns)` | Load specific namespace | `references/namespaces.md` | | `useTranslation([ns])` | Load multiple namespaces | `references/namespaces.md` |
→ See `references/i18next-basics.md` for detailed usage
---
| Package | Purpose | Size | |---------|---------|------| | `i18next` | Core library | ~40KB | | `react-i18next` | React bindings | ~12KB | | `i18next-http-backend` | Lazy loading | ~5KB | | `i18next-browser-languagedetector` | Auto-detection | ~8KB |
---
Type-safe translations with autocompletion. → See `references/typescript-types.md`
Organize translations by feature for code splitting. → See `references/namespaces.md`
Count-based rules with ICU MessageFormat support. → See `references/pluralization.md`
Variables, dates, numbers, and currency formatting. → See `references/interpolation.md`
Load translations on-demand per route. → See `references/lazy-loading.md`
Auto-detect from browser, URL, cookie, localStorage. → See `references/language-detection.md`
Suspense, useTransition, Concurrent Rendering. → See `references/react-19-integration.md`
JSX elements inside translations. → See `references/trans-component.md`
Mock i18n for unit tests. → See `references/testing.md`
Right-to-left languages (Arabic, Hebrew). → See `references/rtl-support.md`
Handle missing keys gracefully. → See `references/fallback-strategies.md`
---
| Template | Use Case | |----------|----------| | `templates/basic-setup.md` | Configuration with React 19 | | `templates/language-switcher.md` | Dropdown component | | `templates/typed-translations.md` | TypeScript Selector API | | `templates/form-validation-i18n.md` | Translated form errors | | `templates/lazy-loading-routes.md` | Per-route loading | | `templates/date-number-formatter.md` | Intl formatting | | `templates/plural-interpolation.md` | Count-based messages | | `templates/trans-component-examples.md` | JSX in translations | | `templates/testing-i18n.md` | Unit test setup |
---
src/ ├── modules/cores/i18n/ │ ├── src/ │ │ ├── interfaces/ │ │ │ └── i18n.interface.ts │ │ ├── services/ │ │ │ └── i18n.service.ts │ │ ├── hooks/ │ │ │ └── useLanguage.ts │ │ └── config/ │ │ └── i18n.config.ts │ ├── components/ │ │ └── LanguageSwitcher.tsx │ └── locales/ │ ├── en/ │ │ └── translation.json │ └── fr/ │ └── translation.json └── main.tsx
---
1. **Suspense**: Wrap app with `<Suspense>` for loading states 2. **Namespaces**: One namespace per feature/module 3. **TypeScript**: Use Selector API for type-safe keys 4. **Lazy Loading**: Load namespaces on-demand 5. **Detection**: Configure language detection order 6. **Fallback**: Always set `fallbackLng`
---
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).