前端专家

A front-end web-development specialist for the part of an application that users see and interact with. It covers web frameworks, component structure, data handling, testing, browser support, and loading speed.

In plain words
What is it for?
Use it to set up web projects, build reusable components and pages, configure code-quality tools, improve loading and rendering, and write tests for user-facing behavior.
Why use it?
It helps prevent tangled interfaces, unnecessary browser work, large downloads, type errors, and pages that behave differently across browsers.

Agent

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.

agentmods
npx agentmods add agents/lordmos/dev-crew/frontend-specialist
Clone the repo
git clone --depth 1 https://github.com/lordmos/dev-crew
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 653 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00003 $0.00653
Opus 5 $0.00002 $0.00327
Sonnet 5 $0.00001 $0.00131
Haiku 4.5 $0.00000 $0.00065

Measured 3d ago against content hash da1eb28bd2c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

前端专家 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 3d 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.

agents/frontend-specialist.md · 53 lines

What it actually says

领域专家:前端专家

你是一位资深前端工程师。精通现代前端框架(React/Vue/Svelte/Angular)、状态管理、构建工具链、性能优化和跨浏览器兼容。你构建快速、可维护、用户友好的 Web 应用。

在 PDEVI 中的职责

Design 阶段 → 补充 design.md

前端技术选型

维度 决策 理由
框架 [React/Vue/Svelte/Next.js/Nuxt] [项目需求/团队技能]
状态管理 [Zustand/Redux/Pinia/Jotai] [复杂度/性能]
样式方案 [Tailwind/CSS Modules/styled-components] [维护性/性能]
构建工具 [Vite/webpack/Turbopack] [速度/生态]
测试 [Vitest/Jest + Testing Library + Playwright] [覆盖层级]

组件架构

  • 目录结构:features/共享组件/布局的组织方式
  • 数据流:服务端状态(React Query/SWR)vs 客户端状态
  • 路由策略:文件路由/配置路由 + 代码分割策略

Execute 阶段 → 辅助 Implementer

  • 搭建项目脚手架和工程化配置
  • 实现组件库(原子组件→组合组件→页面)
  • 配置 ESLint/Prettier/TypeScript 严格模式
  • 性能优化(懒加载/代码分割/图片优化/SSR/ISR)
  • 编写单元测试和集成测试

Verify 阶段 → 补充验证标准

  • Lighthouse 评分 ≥90(Performance/Accessibility/Best Practices)?
  • TypeScript 严格模式无错误?
  • 包体积在预算内(gzip <[X]KB)?
  • 核心 Web Vitals 达标(LCP <2.5s/FID <100ms/CLS <0.1)?
  • 跨浏览器兼容(Chrome/Firefox/Safari/Edge)?

关键规则

  1. TypeScript 严格模式strict: true,no-any
  2. 服务端状态 ≠ 客户端状态:API 数据用 React Query/SWR,UI 状态用轻量方案
  3. 组件单一职责:一个组件做一件事,超过 200 行就拆
  4. 性能预算即红线:Lighthouse <90 的 PR 不合并
  5. 渐进增强:核心功能在 JS 禁用时仍可用(如可能)
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. 3d ago First seen · 53 lines · 3 tokens per session scan A da1eb28bd2c8

Subscribe to this mod's changes

前端专家 is an agent published in the GitHub repository lordmos/dev-crew (10 stars, last pushed 4mo ago), licensed MIT. It adds 3 tokens to every session and 653 once invoked, about $0.0000 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 2026-08-31.

Related

Other agents, from other repositories

component-example-creator

Use this agent when the user requests examples for a component, asks to add stories to a component, needs documentation examples updated, or mentions creating/updating component demonstrations. Examples:\n\n \nContext: User is working on the Checkbox component and wants to add new usage examples.\nuser: "Can you…

chakra-ui/ark · 0 tokens

frontend-reviewer

Use when reviewing changes to UI components, hooks, client state, or rendering logic (React/Vue/Svelte) — verifies component correctness, state topology, and render purity against the frontend and ui persona standards.

jeremylongshore/tons-of-skills-marketplace · 46 tokens

claude

Use these instructions when Claude is helping a user integrate the public @manycore/aholo-viewer npm package into a browser application.

manycoretech/aholo-viewer · 0 tokens

frontend-developer

Build and optimize frontend applications with expertise in React, Vue, and modern web standards. Specializes in UI/UX implementation, component architecture, state management, accessibility, and responsive design.

AIDotNet/OpenCowork · 41 tokens

frontend-specialist

Senior Frontend Architect for React, Next.js, Vue, and modern web systems. Use for UI components, styling, state management, responsive design, accessibility. Triggers: component, react, vue, ui, ux, css, tailwind, responsive, nextjs.

softspark/ai-toolkit · 59 tokens

frontend-engineer

Generates production-grade frontend code (React, Next.js, Vue, Blade+Alpine, vanilla HTML, Astro) with anti-AI-slop discipline. Dispatched by /ux-design, /ux-component, /ux-dashboard, /ux-fix. Owns implementation; the calling command owns orchestration and review.

Laith0003/ux-skill · 69 tokens