Agent skill
react-project-scaffolder
Use PROACTIVELY when creating new React projects requiring modern tooling and best practices. Provides three modes - sandbox (Vite + React for quick experiments), enterprise (Next.js with testing and CI/CD), and mobile (Expo + React Native). Enforces TypeScript strict mode, Testing Trophy approach, and 80% coverage. Not for non-React projects or modifying existing applications.
Install this agent skill to your Project
npx add-skill https://github.com/cskiro/claudex/tree/main/plugins/react-project-scaffolder/skills/react-project-scaffolder
SKILL.md
React Project Scaffolder
Overview
This skill automates the creation of React projects with three distinct modes tailored to different use cases. Each mode provides a complete, production-ready project structure with modern tooling and best practices.
Three Modes:
- Sandbox - Vite + React + TypeScript (~15s setup)
- Enterprise - Next.js + Testing + CI/CD (~60s setup)
- Mobile - Expo + React Native (~60s setup)
All modes follow Connor's standards: TypeScript strict mode, Testing Trophy approach, 80% coverage, conventional commits.
When to Use This Skill
Trigger Phrases:
- "create a React project"
- "scaffold a new React app"
- "set up a React sandbox"
- "create an enterprise React project"
- "build a mobile React app"
Use Cases:
- Quick React experiments without framework overhead
- Enterprise web applications with industry-standard tooling
- Cross-platform mobile apps with React Native
- Establishing consistent project structure across teams
NOT for:
- Non-React projects (Vue, Angular, Svelte)
- Backend-only projects
- Modifying existing React projects
- Ejected Expo projects (bare workflow)
Response Style
- Efficient: Minimize questions, maximize automation
- Guided: Clear mode selection with pros/cons
- Standards-driven: Apply Connor's standards automatically
- Transparent: Explain what's being set up and why
Mode Selection
| User Request | Mode | Framework | Time |
|---|---|---|---|
| "quick React test" | Sandbox | Vite | ~15s |
| "React sandbox" | Sandbox | Vite | ~15s |
| "production React app" | Enterprise | Next.js | ~60s |
| "enterprise React" | Enterprise | Next.js | ~60s |
| "mobile app" | Mobile | Expo | ~60s |
| "React Native project" | Mobile | Expo | ~60s |
Mode Overview
Sandbox Mode
Lightning-fast Vite + React + TypeScript for quick experiments.
→ Details: modes/sandbox.md
Enterprise Mode
Production-ready Next.js with testing, linting, and CI/CD.
→ Details: modes/enterprise.md
Mobile Mode
Cross-platform Expo + React Native with enterprise standards.
→ Details: modes/mobile.md
Workflow
Phase 1: Mode Selection & Prerequisites
-
Detect mode from user request
-
If ambiguous, ask which type:
- Sandbox: Quick experiments, minimal setup
- Enterprise: Production web apps, full tooling
- Mobile: Cross-platform iOS/Android apps
-
Validate prerequisites:
bashnode --version # >= 18.x npm --version # >= 9.x -
Get project name and validate:
- Valid directory name
- No conflicts with existing directories
Phase 2: Mode-Specific Setup
Execute the selected mode's workflow (see mode files for details).
Important Reminders
- Sandbox is for experiments: Don't add testing/CI to sandbox mode
- Enterprise defaults to yes: Testing and CI/CD are included by default
- Mobile uses managed workflow: For ejected/bare workflow, provide manual guidance
- Always strict TypeScript: All modes use strict mode
- 80% coverage threshold: Enterprise and mobile enforce this
Limitations
- Requires Node.js >= 18 and npm >= 9
- Enterprise mode creates Next.js App Router projects only
- Mobile mode uses Expo managed workflow only
- Cannot scaffold into existing directories
Reference Materials
| Resource | Purpose |
|---|---|
modes/sandbox.md |
Vite + React setup details |
modes/enterprise.md |
Next.js + full tooling details |
modes/mobile.md |
Expo + React Native details |
Success Criteria
- Prerequisites validated (Node.js, npm)
- Project directory created
- Framework scaffolded (Vite/Next.js/Expo)
- TypeScript strict mode configured
- Linting and formatting set up
- Testing configured (enterprise/mobile)
- Git initialized with initial commit
- Next steps provided to user
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
e2e-testing
Use PROACTIVELY when setting up end-to-end testing, debugging UI issues, creating visual regression suites, or automating browser testing. Uses Playwright with LLM-powered visual analysis, screenshot capture, and fix recommendations. Zero-setup for React, Next.js, Vue, Node.js, and static sites. Not for unit testing, API-only testing, or mobile native apps.
github-repo-setup
Use PROACTIVELY when user needs to create a new GitHub repository or set up a project with best practices. Automates repository creation with four modes - quick public repos (~30s), enterprise-grade with security and CI/CD (~120s), open-source community standards (~90s), and private team collaboration with governance (~90s). Not for existing repo configuration or GitHub Actions workflow debugging.
sub-agent-creator
Use PROACTIVELY when creating specialized Claude Code sub-agents for task delegation. Automates agent creation following Anthropic's official patterns with proper frontmatter, tool configuration, and system prompts. Generates domain-specific agents, proactive auto-triggering agents, and security-sensitive agents with limited tools. Not for modifying existing agents or general prompt engineering.
accessibility-audit
Use PROACTIVELY when user asks for accessibility review, a11y audit, WCAG compliance check, screen reader testing, keyboard navigation validation, or color contrast analysis. Audits React/TypeScript applications for WCAG 2.2 Level AA compliance with risk-based severity scoring. Includes MUI framework awareness to avoid false positives. Not for runtime accessibility testing in production, automated remediation, or non-React frameworks.
otel-monitoring-setup
Use PROACTIVELY when setting up OpenTelemetry monitoring for Claude Code usage tracking, cost analysis, or productivity metrics. Provides local PoC mode (full Docker stack with Grafana) and enterprise mode (centralized infrastructure). Configures telemetry collection, imports dashboards, and verifies data flow. Not for non-Claude telemetry or custom metric definitions.
json-outputs-implementer
Use PROACTIVELY when extracting structured data from text/images, classifying content, or formatting API responses with guaranteed schema compliance. Implements Anthropic's JSON outputs mode with Pydantic/Zod SDK integration. Covers schema design, validation, testing, and production optimization. Not for tool parameter validation or agentic workflows (use strict-tool-implementer instead).
Didn't find tool you were looking for?