惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

L
LINUX DO - 热门话题
T
The Blog of Author Tim Ferriss
WordPress大学
WordPress大学
酷 壳 – CoolShell
酷 壳 – CoolShell
美团技术团队
博客园 - 叶小钗
李成银的技术随笔
V
Visual Studio Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Apple Machine Learning Research
Apple Machine Learning Research
Hugging Face - Blog
Hugging Face - Blog
V
V2EX
博客园 - 司徒正美
Blog — PlanetScale
Blog — PlanetScale
大猫的无限游戏
大猫的无限游戏
T
Tailwind CSS Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
aimingoo的专栏
aimingoo的专栏
人人都是产品经理
人人都是产品经理
GbyAI
GbyAI
A
About on SuperTechFans
罗磊的独立博客
W
WeLiveSecurity
L
LINUX DO - 最新话题
M
MIT News - Artificial intelligence
Hacker News: Ask HN
Hacker News: Ask HN
Application and Cybersecurity Blog
Application and Cybersecurity Blog
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
P
Proofpoint News Feed
Microsoft Security Blog
Microsoft Security Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
H
Help Net Security
Martin Fowler
Martin Fowler
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
www.infosecurity-magazine.com
www.infosecurity-magazine.com
The Register - Security
The Register - Security
M
Microsoft Research Blog - Microsoft Research
Hacker News - Newest:
Hacker News - Newest: "LLM"
博客园 - Franky
The Cloudflare Blog
C
Cisco Blogs
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Google Online Security Blog
Google Online Security Blog
有赞技术团队
有赞技术团队
AWS News Blog
AWS News Blog
C
Cybersecurity and Infrastructure Security Agency CISA
小众软件
小众软件
I
Intezer
N
Netflix TechBlog - Medium
N
News and Events Feed by Topic

DEV Community

Google Antigravity 1.0 to 2.0/IDE Quick Migration Guide Don't Make the Agent Re-Run the Test Suite to Find the Failure Assembly Code to Machine Code (ARM) Spring boot Interview Questions LambdaTest vs BrowserStack : Detail Comparison in 2026 Track YC Demo Day Companies in Real Time (with code) I Got Tired of Passing --profile on Every OCI CLI Command Running Flux Schnell (12B) + LLMs on a Legacy AMD RX 580 (8GB) via Native Vulkan — Full Architecture Guide [2026] Investigation Reports: When Monitors Get Smarter Semantic Layer Best Practices: 7 Mistakes to Avoid I Run MCP Servers. Here's What the Recent Vulnerabilities Actually Mean for Me Phive v1.1.1 — automatic port conflict handling for local VS Code environments Building a SQL-like Relational Database Engine in C++ From Scratch How a Self-Documenting Semantic Layer Reduces Data Team Toil The Adopter: Advocating for OSS You Use (But Don't Own) Optimizing Vite Build Output: A Practical Guide to Tree-Shaking I built a free audit tool that runs 12 checks in parallel against any domain. Here is the architecture. I made a free 7-video series to prep for the new GH-600 (GitHub Agentic AI Developer) cert Why One Model Is Never Enough: Routing Incident Analysis With cascadeflow Forecast Cone: A Grand Theorem for Computable Software Evolution Choosing the Right Treasure Map to Avoid Data Decay in Veltrix Migrating to Apache Iceberg: Strategies for Every Source System Stop Reviewing Every Line of AI Code - Build the Trust Stack Instead Implementation of AI in mobile applications: Comparative analysis of On-Device and On-Server approaches on Native Android and Flutter Should you use Gemma 4 for your Development? A Multiversal Analysis to Determine if Gemma 4 is Right for You! The Rising Trend of Creative Interview Questions in Tech I Spent Hours Fighting a Silent Subnet Conflict to Build an Isolated ICS Security Lab (And What It Taught Me About the Linux Kernel) It Worked When I Closed the Laptop. I Swear. We Built an Agent That Flags Fake Internships #kryx Your Personal AI Stack Is the New Dotfiles Your LLM Bill Is Exploding Because of Architecture, Not Pricing -- Here's the Fix How We Prevent Attendance Fraud Using GPS Verification AI Code Review in 2026: How the Tools Actually Differ (A Builder's Field Guide) From Problems to Patterns: Generative AI in .Net (C#) GemmaOps Edge: From 373 Alarms to 1 Root Cause Using Local AI (Gemma 4) Building an Amazon EKS Security Baseline Hands-On with Apache Iceberg Using Dremio Cloud 🤫 Firebase Is Quietly Preparing for an Offline-First AI Future Should Angular Apps Still Rely on RxJS in 2025? Gaslighting Gemma 4: Can Open-Weight Reasoning Models Withstand a Confident Liar? AI Workflow Automation Needs More Than Another Script Reviving Cineverse: From Local Storage to Firebase 🚀 Approaches to Streaming Data into Apache Iceberg Tables How to Add Rounded Corners to an Image Online The subtle impact of AI (&amp; IT) on jobs Made a Rust based AI agent Your AI is not bad, your instructions are What Clicked for Me After Building on Solana for a Few Days WhatsApp's Encryption Stack: What It Covers, What It Doesn't, and What a Federal Agent Spent 10 Months Investigating Building CogniPlan: A Local-First Task Planning System Using Apache Iceberg with Python and MPP Query Engines How I Built AegisDesk: A Zero-Token Semantic IT Agent with <5ms Latency I built CodeArchy: an open-source that turns any codebase into a visual, explainable architectural experience, powered by Gemma 4. The Day Our Bot Ran Out of Money How we're using Gemini Embeddings to build a smarter, community-driven feed on DEV The Speculative Decoding Pattern The PKCE "Gotcha" in Expo’s exchangeCodeAsync TharVA : Keeping India's Desert Heritage Alive with Offline AI (Gemma4) n8n for Healthcare: 5 Automations for Clinics, Practices, and Health Tech Teams (Free Workflow JSON) How I Built an OWASP Memory Guard for AI Agents (ASI06) Condition-Based vs Time-Based Maintenance: Making the Switch I Tested Spam Protection on Formspree vs Formgrid. The Results Were Surprising. May 27 - Video Understanding Workshop Beyond Keywords: How Google's 2026 Algorithms are Redefining SEO From Click to Cart: Ensuring an Accessible Customer Journey in WooCommerce Your company won't replace you with good AI. They'll replace you with bad AI. How to Use an SVG Icon Search Engine as a Claude Custom Connector O fim do “modelo que faz tudo”? Conheça o Conductor, a IA que orquestra outras IAs 10 First-Principles Strategies to Learn Any Programming Language Deeply 10 First-Principles Strategies to Learn Any Programming Language Deeply Understanding Embeddings easily. The Hidden Cost of “Move Fast and Break Things” Why Your Logs Are Useless Without Traces DressCode: Your AI Stylist for Tomorrow The Documented Shortcoming of Our Production Treasure Hunt Engine I'm 16, and I Built an AI Tool That Audits Your Technical Debt Without Ever Touching code Building Your Own Crypto Poker Bot: A Developer's Guide to Blockchain Gaming Logic Apache Iceberg Metadata Tables: Querying the Internals Hermes, The Self-Improving Agent You Can Actually Run Yourself Unity vs Unreal: 5 Things I Had to Relearn the Hard Way Building Agentic Commerce Infrastructure: Overcoming SQLite Concurrency for Autonomous Procurement Agents Solana Accounts vs Databases HTML Table Borders I built a skill that makes AI-generated AWS diagrams actually usable My first post! I'm kinda excited The Page Root Was the Wrong Unit How to audit what your IDE extension actually sends to the cloud I Migrated 23 Make.com Scenarios to n8n and Cut My Bill by 60% — Complete Migration Guide (2026) Solving a Logistics Problem Using Genetic Algorithms Claude Code Skills Explained: What They Are & When to Use Them (2026) Maintaining Apache Iceberg Tables: Compaction, Expiry, and Cleanup Zero-Idle Local LLMs: Running Llama 3 in AWS Lambda Containers We scanned 8 B2B SaaS companies across 5 categories. ChatGPT named the same 12 brands in every answer. How To "Market" Yourself As A Tech Pro We scanned 500 MCP servers on Smithery. Here is what we found. HTML Basics for Beginners – Markup Language, Elements and Types of CSS DiffWhisperer: How I Turned Cryptic Git Diffs into Architectural Stories with Gemma 4 I built a version manager for llama.cpp using nothing but vibe coding. Unit Testing vs System Testing: Key Differences, Use Cases, and Best Practices for 2026 A game design textbook explains why products with fewer features win
Como eu acelerei o desenvolvimento frontend utilizando ferramentas de IA e o MCP do Figma
Danilo Itagy · 2026-05-23 · via DEV Community

Ferramentas de IA aceleram muito o desenvolvimento frontend, mas só funcionam bem quando recebem contexto, limites e validação.

O ganho real não veio de pedir “crie uma tela”. Veio de organizar o fluxo:

  • instruções claras para o agente
  • integração com design via Figma MCP
  • mudanças pequenas
  • revisão humana
  • testes automatizados
  • validação visual com Playwright

O problema: IA sem contexto gera ruído

Um prompt assim normalmente gera dívida técnica:

Crie essa tela em React.

Enter fullscreen mode Exit fullscreen mode

O resultado tende a vir com:

  • componentes grandes
  • CSS fora do padrão
  • nomes genéricos
  • regra de negócio misturada com UI
  • poucos testes
  • layout quebrando em estados reais

O que funcionou melhor foi tratar a IA como parte do fluxo de engenharia.


Codex com instruções do projeto

No Codex, usei um AGENTS.md para definir como o agente deve trabalhar no repositório.

Em vez de repetir regras em todo prompt, deixei o projeto explicar:

  • stack
  • estrutura de pastas
  • padrão de testes
  • comandos principais
  • regras de TypeScript
  • cuidados com integração
  • checklist antes de finalizar

No corpo do artigo, deixo só a ideia. O exemplo completo está no final: AGENTS.md exemplo.

Um prompt melhor para Codex fica assim:

Refatore este componente seguindo o AGENTS.md.
Mantenha o comportamento visual.
Adicione testes relevantes.
Rode lint e testes.

Enter fullscreen mode Exit fullscreen mode

Isso muda bastante o resultado. O agente passa a respeitar o projeto em vez de inventar um padrão novo.

O mesmo conceito pode ser aplicado a outras ferramentas, como Claude, com alguns ajustes no arquivo de instruções. No Claude, por exemplo, eu usaria um CLAUDE.md mais focado em análise, revisão e tomada de decisão, enquanto no Codex o AGENTS.md fica mais direcionado à execução dentro do repositório.


Figma MCP no fluxo frontend

O MCP do Figma aproxima design e implementação.

Ele permite que o agente leia contexto do Figma, como:

  • estrutura da tela
  • nomes de layers
  • textos
  • medidas
  • componentes
  • variáveis
  • estilos

Isso ajuda muito em tarefas como:

Use o frame selecionado no Figma como referência e implemente a tela usando os componentes existentes do projeto.

Enter fullscreen mode Exit fullscreen mode

O ponto importante: o MCP não substitui engenharia frontend. Ele reduz o atrito entre design e código.

Ainda é necessário:

  • adaptar ao design system do projeto
  • reaproveitar componentes existentes
  • validar responsividade
  • revisar acessibilidade
  • testar estados reais

Como configurar o MCP do Figma

A forma exata muda conforme o cliente, mas o fluxo geral é:

  1. Instalar e abrir o Figma Desktop.
  2. Abrir o arquivo de design.
  3. Entrar em Dev Mode.
  4. Ativar o Dev Mode MCP Server.
  5. Configurar o cliente MCP para apontar para o servidor local.

O servidor local oficial do Figma usa HTTP, normalmente em:

http://127.0.0.1:3845/mcp

Enter fullscreen mode Exit fullscreen mode

Exemplo genérico de configuração MCP:

{
  "mcpServers": {
    "figma-desktop": {
      "transport": "http",
      "url": "http://127.0.0.1:3845/mcp"
    }
  }
}

Enter fullscreen mode Exit fullscreen mode

Depois disso, o agente pode receber prompts como:

Leia o frame selecionado no Figma e compare com a implementação atual.

Enter fullscreen mode Exit fullscreen mode

ou:

Use o design selecionado como referência e implemente a tela mantendo os padrões do projeto.

Enter fullscreen mode Exit fullscreen mode


Fluxo prático com Codex

O fluxo que mais funcionou foi:

1. Ler instruções do projeto
2. Inspecionar arquivos relevantes
3. Fazer mudança pequena
4. Adicionar ou ajustar testes
5. Rodar lint, testes e build
6. Revisar diff
7. Só então finalizar

Enter fullscreen mode Exit fullscreen mode

IA acelera, mas testes e revisão seguram a qualidade.


Testes são o contrato

Sem testes, a IA acelera a entrega e também acelera regressões.

Usei diferentes camadas de teste.


Teste unitário

Para função pura:

it('formats currency', () => {
  expect(formatCurrency('10.5')).toBe('R$ 10,50')
})

Enter fullscreen mode Exit fullscreen mode


Teste de componente

Para comportamento visível:

it('increments quantity', async () => {
  render(<QuantityStepper />)
  await user.click(screen.getByRole('button', { name: /aumentar/i }))
  expect(screen.getByRole('textbox')).toHaveValue('2')
})

Enter fullscreen mode Exit fullscreen mode


Teste de hook

Para estado reutilizável:

it('loads data', async () => {
  const { result } = renderHook(() => useItems())
  await waitFor(() => expect(result.current.isLoading).toBe(false))
})

Enter fullscreen mode Exit fullscreen mode


Teste de API

Para contrato com backend:

it('parses response', async () => {
  mockFetch({ success: true, data: { id: '1' } })
  await expect(fetchItem('1')).resolves.toEqual({ id: '1' })
})

Enter fullscreen mode Exit fullscreen mode


E2E com Playwright

Para fluxo real:

test('opens product detail', async ({ page }) => {
  await page.goto('/app')
  await page.getByRole('textbox', { name: /referência/i }).fill('ABC')
  await page.getByRole('button', { name: /realizar leitura/i }).click()
  await expect(page.getByRole('region', { name: /dados/i })).toBeVisible()
})

Enter fullscreen mode Exit fullscreen mode


Teste de layout

Para proteger alinhamento e scroll:

const box = await page.locator('.content').evaluate((el) => ({
  clientHeight: el.clientHeight,
  scrollHeight: el.scrollHeight,
}))

expect(box.scrollHeight).toBeLessThanOrEqual(box.clientHeight + 1)

Enter fullscreen mode Exit fullscreen mode


Teste de screenshot

Para telas visualmente sensíveis:

test('matches open form layout', async ({ page }) => {
  await page.setViewportSize({ width: 1456, height: 793 })
  await page.goto('/app')
  await page.getByRole('button', { name: /verificar/i }).click()
  await expect(page).toHaveScreenshot('form-open.png')
})

Enter fullscreen mode Exit fullscreen mode

Esse teste pega regressões difíceis de cobrir só com assertions:

  • botão quebrando linha
  • texto saindo do container
  • painel desalinhado
  • scroll inesperado
  • espaçamento quebrado

O que mudou na prática

Com esse fluxo, o Codex virou uma ferramenta de engenharia, não só geração de código.

Ganhos principais:

  • menos tempo em boilerplate
  • refactors mais rápidos
  • testes criados junto com a alteração
  • design mais próximo da implementação
  • regressões visuais detectadas cedo
  • revisão mais objetiva
  • padrões documentados no repositório

Conclusão

Codex e MCP do Figma ajudam muito no desenvolvimento frontend.

Mas a aceleração sustentável vem da combinação:

  • contexto claro
  • instruções versionadas
  • mudanças pequenas
  • testes automatizados
  • validação visual
  • revisão humana

IA boa não substitui engenharia. Ela aumenta a velocidade de quem sabe definir limites e validar resultado.


AGENTS.md exemplo

# AGENTS.md

## Purpose

This project uses React, Vite and TypeScript with a focus on predictable, typed, testable and maintainable code.

## Language Rule

- All source code must be written in English.
- Use English for identifiers, file names, comments, constants and test names.
- User-facing UI copy may follow product requirements.

## Stack

- React
- Vite
- TypeScript
- ESLint
- Vitest + Testing Library
- Playwright

## Main Commands

- `npm run dev`
- `npm run build`
- `npm run lint`
- `npm run test`
- `npm run test:e2e`

Before closing a meaningful change, run at least `npm run lint` and the relevant test suite.

## Project Structure

- `src/app`: app composition and providers
- `src/pages`: route-level pages
- `src/features`: domain-specific modules
- `src/shared`: reusable UI, styles, config and utilities
- `src/test`: Vitest setup and helpers
- `e2e`: Playwright specs and page objects

## Core Conventions

- Prefer small, local and predictable changes.
- Prefer composition over premature abstraction.
- Keep business logic out of purely visual components.
- Avoid generic `utils.ts` dumping grounds.
- Use explicit names for files, functions, props and types.
- Do not introduce `any` unless there is a strong reason.

## React and TypeScript

- Use functional components.
- Keep components focused on one responsibility.
- Derive values from props and state instead of duplicating state.
- Use `useEffect` only for real side effects.
- Do not add `useMemo` or `useCallback` by default.

## Testing

- Test user-visible behavior, not implementation details.
- Prefer Testing Library queries by role, text or label.
- Add tests when fixing bugs or introducing meaningful flows.
- Keep unit, integration and E2E scopes separate.

## Checklist

- The change respects project boundaries.
- Types are clear.
- No redundant state was introduced.
- Relevant linting and tests were executed.

Enter fullscreen mode Exit fullscreen mode


Referências