react-init-skill

react-init-skill is a skill for Claude Code, Codex from jiushiwon/wg-skills. It costs 144 tokens per session (3,736 once invoked), scanned A, original, Apache-2.0.

A guided generator for React 18, TypeScript, Vite, and Zustand projects. It plans the application, creates its project structure and configuration, and sets up themes, layouts, assets, and development standards.

In plain words
What is it for?
Use it to start a React single-page application, create its initial files, configure Vite and TypeScript, set up authentication and HTTP request patterns, design core pages, and verify the project.
Why use it?
It turns a broad React idea into a consistent starting application and provides prescribed patterns for requests, authentication, errors, and API responses.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it to start a React single-page application, create its initial files, configure Vite and TypeScript, set up authentication and HTTP request patterns, design core pages, and verify the project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jiushiwon/wg-skills/react-generate-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add jiushiwon/wg-skills --skill react-generate-skill
Clone the repo
git clone --depth 1 https://github.com/jiushiwon/wg-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for react-init-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/jiushiwon/wg-skills/react-generate-skill/github.svg)](https://agentmods.dev/skills/jiushiwon/wg-skills/react-generate-skill)
Your own site
<a href="https://agentmods.dev/skills/jiushiwon/wg-skills/react-generate-skill"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/react-generate-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for react-init-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/jiushiwon/wg-skills/react-generate-skill"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/react-generate-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,736 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00144 $0.03736
Opus 5 $0.00072 $0.01868
Sonnet 5 $0.00029 $0.00747
Haiku 4.5 $0.00014 $0.00374

Measured 9d ago against content hash 2df459be7130, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

react-init-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

vibeCoding/frontend/react/react-generate-skill/SKILL.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React Generate Skill

⚠️ 重要:本 Skill 严格依赖 frontend-request-skill

本 Skill 不重新发明请求层。所有 HTTP / 错误处理 / 鉴权相关代码必须复用 frontend-request-skill 的标准实现:

react-init-skill 输出 对应 frontend-request-skill 标准
src/api/request.ts references/frontend-spec.md(fetch 标准实现)
src/services/auth.service.ts references/auth-patterns.md(Token 刷新队列)
src/utils/{error,toast,auth}.ts references/error-handling.md + auth-patterns.md
src/config/{api,error}.config.ts references/frontend-spec.md(BASE_URL + ERROR_CODE_MAP)
src/hooks/useAuth.ts references/auth-patterns.md
响应信封 { code, message, data } backend-convention-skill/references/response-format.md 一致

接入本 Skill 前,请先阅读 frontend-request-skill 的 SKILL.md 与核心 reference。


Overview

This skill transforms a vague React project idea into a production-ready React 18 + TypeScript SPA with consistent architecture, design tokens, static assets, and coding standards.

  1. Pre-development: brainstorm, scope, and produce a detailed specification.
  2. Project initialization: scaffold the project, directory structure, CLAUDE.md, AGENTS.md, tsconfig.json, vite.config.ts.
  3. Development: install frontend-request-skill's request layer, set up theme system, design the layout, and build core pages.
  4. Post-development: lint, type-check (tsc --noEmit), verify the build.

When to Use

Invoke this skill when the user asks for:

  • "帮我做一个 React 项目"
  • "初始化一个 React + TypeScript 模板"
  • "做一个 React 后台管理系统"
  • "用 React 搭一个 xxx 网站"
  • "帮我生成一个标准的 React 项目结构"
  • Any request that involves creating a new React SPA from scratch (H5 / 后台 / 文档站)

Not for: React Native / 小程序 / Taro / 移动端 hybrid — use react-native-init-skill instead.

Workflow Summary

Phase 1: Pre-development
  → Ask 3-5 clarifying questions
  → Write spec.md (scope, pages, data model, API outline)

Phase 2: Project Initialization
  → npm create vite@latest scaffold
  → Replace placeholders
  → Create standard directory structure (including src/api/, src/services/, src/config/)
  → Generate CLAUDE.md (≤ 50 lines, references frontend-request-skill)
  → Generate AGENTS.md (≤ 400 lines, on-demand references)
  → Apply tsconfig.json strict template
  → Apply vite.config.ts template (path alias + auto-import)
  → Copy code-examples/ (types / stores / components / pages)

Phase 3: Development
  → Install frontend-request-skill's request layer (copy from references/)
  → Configure src/config/api.config.ts (BASE_URL / PREFIX / SUCCESS_CODES)
  → Configure src/config/error.config.ts (ERROR_CODE_MAP)
  → Set up src/styles/globals.css theme variables
  → Implement core pages using code-examples/ as template
  → Write hooks (useAuth, useFetch, ...)

Phase 4: Post-development
  → npm run lint           # ESLint must pass
  → npm run type-check     # tsc --noEmit must pass
  → npm run build          # Must build successfully
  → Summarize deliverables

Read the full file on GitHub · 408 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 408 lines · 144 tokens per session scan A 2df459be7130

Subscribe to this mod's changes

react-init-skill is a skill published in the GitHub repository jiushiwon/wg-skills (97 stars, last pushed 2d ago), licensed Apache-2.0. It adds 144 tokens to every session and 3,736 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

frontend-conventions

Coding conventions, architecture patterns, and testing rules for the SkillHub React frontend. Ensures agents follow Feature-Sliced Design and use the generated OpenAPI types.

iflytek/skillhub · 36 tokens

fast-typescript-check

Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…

internet-development/www-sacred · 84 tokens

typescript-react

Apply, review, and explain React conventions from the TypeScript Style Guide. Use automatically for TypeScript and TSX tasks involving prop-derived state, prop typing, component responsibilities, data flow, compound components, or client and server state.

mkosir/typescript-style-guide · 50 tokens

electron-dev

Electron desktop apps with React, TypeScript, and Vite. Use for IPC, window/tray, PTY terminals, WebRTC, and packaging.

jamditis/claude-skills-journalism · 34 tokens

coding-standards

A set of general coding standards and practical patterns for TypeScript, JavaScript, React, and Node.js. It covers readable naming, simple designs, avoiding repetition, and delaying unnecessary features.

loulanyue/awesome-claude-notes · 41 tokens

typescript-rules

React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.

shinpr/claude-code-workflows · 39 tokens