Communitygithub.com

verification-loop

Um sistema de verificação abrangente para sessões do Claude Code. Use ao verificar uma sessão do Claude Code.

O que é verification-loop?

Esta skill implementa um loop de verificação sistemático para sessões do Claude Code, garantindo que alterações de código atendam a rigorosos padrões de qualidade antes da integração. Ela consiste em seis fases distintas: verificação de build, checagem de tipos, linting, execução de testes, varredura de segurança e revisão de diff. Ao executar esses comandos sequencialmente, a skill fornece um relatório de verificação consolidado com status de aprovação/reprovação para cada fase, além de uma avaliação geral de prontidão para Pull Requests. Útil para desenvolvedores que desejam evitar regressões e garantir que commits estejam limpos, a skill pode ser invocada manualmente após mudanças significativas ou executada em modo contínuo a cada 15 minutos. Ela complementa os hooks PostToolUse do Claude Code, oferecendo uma camada mais profunda de análise e detecção de problemas.

Funciona com✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/verification-loop

Perguntar na sua IA favorita

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

Documentação

Skill de Loop de Verificação

Um sistema de verificação abrangente para sessões do Claude Code.

Quando Usar

Invoque esta skill:

  • Após concluir uma funcionalidade ou mudança significativa no código
  • Antes de criar um Pull Request
  • Quando quiser garantir que os portões de qualidade sejam aprovados
  • Após refatoração

Fases de Verificação

Fase 1: Verificação de Build

# Verifique se o projeto compila
npm run build 2>&1 | tail -20
# OU
pnpm build 2>&1 | tail -20

Se o build falhar, PARE e corrija antes de continuar.

Fase 2: Checagem de Tipos

set -o pipefail
# Projetos TypeScript
npx --no-install tsc --noEmit 2>&1 | head -30

# Projetos Python
pyright . 2>&1 | head -30

Relate todos os erros de tipo. Corrija os críticos antes de continuar.

Fase 3: Verificação de Lint

# JavaScript/TypeScript
npm run lint 2>&1 | head -30

# Python
ruff check . 2>&1 | head -30

Fase 4: Suite de Testes

# Execute testes com cobertura
npm run test -- --coverage 2>&1 | tail -50

# Verifique o limite de cobertura
# Alvo: mínimo de 80%

Relate:

  • Total de testes: X
  • Passaram: X
  • Falharam: X
  • Cobertura: X%

Fase 5: Varredura de Segurança

# Verifique segredos
grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10

# Verifique console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10

Fase 6: Revisão de Diff

# Mostre o que mudou
git diff --stat
git diff HEAD~1 --name-only

Revise cada arquivo alterado para:

  • Mudanças não intencionais
  • Tratamento de erro ausente
  • Casos extremos potenciais

Formato de Saída

Após executar todas as fases, produza um relatório de verificação:

RELATÓRIO DE VERIFICAÇÃO
=========================

Build:      [APROVADO/REPROVADO]
Tipos:      [APROVADO/REPROVADO] (X erros)
Lint:       [APROVADO/REPROVADO] (X avisos)
Testes:     [APROVADO/REPROVADO] (X/Y passaram, Z% cobertura)
Segurança:  [APROVADO/REPROVADO] (X problemas)
Diff:       [X arquivos alterados]

Geral:      [PRONTO/NÃO PRONTO] para PR

Problemas a Corrigir:
1. ...
2. ...

Modo Contínuo

Para sessões longas, execute a verificação a cada 15 minutos ou após mudanças importantes:

Defina um ponto de verificação mental:
- Após completar cada função
- Após finalizar um componente
- Antes de passar para a próxima tarefa

Execute: /verify

Integração com Hooks

Esta skill complementa os hooks PostToolUse, mas fornece uma verificação mais profunda. Os hooks detectam problemas imediatamente; esta skill oferece uma revisão abrangente.

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/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

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.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

Habilidades Relacionadas