Communitygithub.com

Engenharia Primeiro-IA

Modelo operacional de engenharia para equipes onde agentes de IA geram grande parte da implementação. Use ao definir processos de equipe, portas de revisão ou regras de propriedade para uma base de código amplamente escrita por agentes.

O que é Engenharia Primeiro-IA?

Esta habilidade define um modelo operacional para equipes de engenharia que adotam geração de código assistida por IA, como com Claude Code, Cursor ou Codex. Ela enfatiza mudanças de processo — como focar na qualidade do planejamento em vez da velocidade de digitação, priorizar cobertura de avaliação sobre confiança anedótica e deslocar a revisão de sintaxe para comportamento do sistema. A habilidade recomenda arquiteturas amigáveis a agentes com limites explícitos, contratos estáveis, interfaces tipadas e testes determinísticos. Ela também define padrões de revisão de código, sinais de contratação para engenheiros fortes no paradigma primeiro-IA e uma barra elevada de testes para código gerado, incluindo cobertura de regressão, asserções de casos extremos e verificações de integração.

Funciona com~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/tree/main/skills/ai-first-engineering

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

O que Engenharia Primeiro-IA faz?

Use esta habilidade ao projetar processos, revisões e arquitetura para equipes que entregam com geração de código assistida por IA.

Mudanças de Processo

  1. A qualidade do planejamento importa mais do que a velocidade de digitação.
  2. A cobertura de avaliação importa mais do que a confiança anedótica.
  3. O foco da revisão muda de sintaxe para comportamento do sistema.

Requisitos de Arquitetura

Prefira arquiteturas que sejam amigáveis a agentes:

  • limites explícitos
  • contratos estáveis
  • interfaces tipadas
  • testes determinísticos

Evite comportamento implícito espalhado por convenções ocultas.

Revisão de Código em Equipes Primeiro-IA

Revise para:

  • regressões de comportamento
  • suposições de segurança
  • integridade dos dados
  • tratamento de falhas
  • segurança da implantação

Minimize o tempo gasto em questões de estilo já cobertas pela automação.

Sinais de Contratação e Avaliação

Engenheiros fortes no paradigma primeiro-IA:

  • decompõem trabalho ambíguo de forma limpa
  • definem critérios de aceitação mensuráveis
  • produzem prompts e avaliações de alto sinal
  • aplicam controles de risco sob pressão de entrega

Padrão de Testes

Eleve a barra de testes para código gerado:

  • cobertura de regressão obrigatória para domínios tocados
  • asserções explícitas de casos extremos
  • verificações de integração para limites de interface

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

Habilidades Relacionadas