Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计异常

frontendfrontend 开发

Agent Skill

用于辅助前端页面、组件、样式和交互逻辑的开发与维护。它适合让 Agent 生成或审查 React、Next.js、Vue、Tailwind、CSS 等相关代码,整理组件结构,或定位布局和性能问题。使用时需要结合项目现有设计系统、路由和构建方式,避免只生成孤立片段;涉及页面改动时,应配合本地预览和构建检查确认视觉效果。

总安装

714

周安装

34

GitHub Stars

5

下载量

280
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:frontend(frontend 开发)
来源仓库:https://github.com/vechain/vechain-ai-skills
仓库路径:skills/frontend
安装命令:
npx skills add https://github.com/vechain/vechain-ai-skills --skill frontend
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/vechain/vechain-ai-skills --skill frontend

简介

用于辅助前端页面、组件、样式和交互逻辑的开发与维护。它适合让 Agent 生成或审查 React、Next.js、Vue、Tailwind、CSS 等相关代码,整理组件结构,或定位布局和性能问题。

  • 适用于 Web 应用开发、用户界面优化或前端架构设计等场景。
  • 通过 GitHub 仓库安装,使用 npx skills add 命令添加指定技能。
  • 使用时需要结合项目现有设计系统、路由和构建方式,避免只生成孤立片段;涉及页面改动时,应配合本地预览和构建检查确认视觉效果。
  • frontend 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Frontend Skill

CRITICAL RULES

  1. Read reference files FIRST. When the user's request involves any topic in the reference table below, read those files before doing anything else — before writing code, before making decisions. Briefly mention which files you are reading so the user can confirm the skill is active (e.g., "Reading frontend patterns reference...").
  2. Information priority for VeChain topics: (a) Reference files in this skill — always the primary source. (b) VeChain MCP tools — use @vechain/mcp-server for on-chain data, transaction building, and live network queries; use Kapa AI MCP for VeChain documentation lookups. (c) Web search — only as a last resort, and only for topics NOT covered in the reference files.
  3. Prefer working directly in the main conversation for VeChain tasks. Plan mode and subagents do not inherit skill context and may fall back to web search instead of using reference files.
  4. After compaction or context loss, re-read this SKILL.md to restore awareness of the reference table and operating procedure before continuing work.

Scope

Use this Skill for generic frontend development patterns in VeChain dApps:

  • React Query (TanStack Query): query keys, cache invalidation, batch queries, loading states, anti-patterns
  • Turborepo monorepo architecture and conventions
  • State management (React Query for server state, Zustand for client state)
  • Chakra UI integration and responsive design
  • i18n with react-i18next
  • Transaction UX: loading states, confirmation patterns, error handling
  • Choosing between VeChain Kit and dapp-kit

For package-specific APIs (hooks, components, setup), see the vechain-kit skill. For core VeChain SDK, fee delegation, and multi-clause transactions, see the vechain-core skill.

Default stack

LayerDefaultAlternative
FrontendReact / Next.js (App Router)--
Data fetching@tanstack/react-query--
State managementZustand (client state only)--
UIChakra UI v2--
MonorepoTurborepo--
NodeNode 20 LTS (managed via nvm)--

Operating procedure

1. Check Node version

Before installing dependencies or running any command:

  • Check if .nvmrc exists in the project root. If yes, run nvm use.
  • If .nvmrc does not exist, create one with 20 (Node 20 LTS) and run nvm use.

2. Detect project structure

  • turbo.json present → follow Turborepo conventions (apps/frontend, packages/*)
  • Apply conditional patterns (Chakra UI, i18n, Zustand) only when the project uses them

3. Clarify before implementing

When the user's request is ambiguous or could be solved multiple ways, ask before building. Separate research from implementation.

4. Implement with correctness

  • Use React Query for all server state (contract reads, indexer data)
  • Never duplicate server state in Zustand — let React Query be the source of truth
  • Always use enabled guards on queries with dynamic params
  • Always show skeletons while loading — never render empty/zero states during loads
  • Invalidate affected caches after transactions

5. Verify and deliver

A task is not complete until all applicable gates pass:

  1. Code compiles — no build errors (npm run build or equivalent succeeds)
  2. Tests pass — existing tests still pass; new logic has test coverage
  3. Risk notes documented — any signing, fee, or token-transfer implications are called out

Reference files

Read the matching files BEFORE doing anything else. See Critical Rules above.

TopicFileRead when user mentions...
Frontend patternsreferences/frontend.mdfrontend, React Query, caching, query keys, loading, skeleton, Turborepo, Chakra, i18n, state management, transaction UX, VeChain Kit vs dapp-kit

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

32.22%
按下载量换算90

Claude

31.01%
按下载量换算87

Cursor

18.22%
按下载量换算51

Gemini CLI

8.62%
按下载量换算24

安全审计

Gen Agent Trust Hub

通过

Socket

未通过

Snyk

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills