Communitygithub.com

verification-loop

Un sistema de verificación integral para sesiones de Claude Code. Útil para verificar una sesión de Claude Code.

¿Qué es verification-loop?

Este skill, *verification-loop*, proporciona un sistema completo de verificación en múltiples fases para sesiones de Claude Code. Es útil para desarrolladores que usan Claude Code como asistente de programación, ya que guía la ejecución de controles de calidad clave (compilación, tipos, lint, pruebas, seguridad y revisión de cambios) antes de crear un Pull Request o después de refactorizaciones. El skill se ejecuta a través de comandos directos en la terminal dentro de la sesión, ofreciendo fases secuenciales que detienen el flujo si falla la compilación. Además, genera un informe estructurado con el estado de cada fase y una calificación general de preparación para el PR. Es compatible con el modo continuo, recomendando ejecutarlo cada 15 minutos o tras cambios mayores, y complementa los hooks PostToolUse con una revisión más profunda.

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

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

Habilidad de Bucle de Verificación

Un sistema de verificación integral para sesiones de Claude Code.

Cuándo Usarlo

Invoca esta habilidad:

  • Después de completar una funcionalidad o un cambio de código significativo
  • Antes de crear un PR
  • Cuando quieras asegurarte de que se superan las puertas de calidad
  • Después de refactorizar

Fases de Verificación

Fase 1: Verificación de Compilación

# Verifica si el proyecto compila
npm run build 2>&1 | tail -20
# O
pnpm build 2>&1 | tail -20

Si la compilación falla, DETENTE y corrige antes de continuar.

Fase 2: Verificación de Tipos

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

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

Informa todos los errores de tipo. Corrige los críticos antes de continuar.

Fase 3: Verificación con Linter

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

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

Fase 4: Suite de Pruebas

# Ejecuta pruebas con cobertura
npm run test -- --coverage 2>&1 | tail -50

# Verifica umbral de cobertura
# Objetivo: mínimo 80%

Informa:

  • Total de pruebas: X
  • Pasadas: X
  • Fallidas: X
  • Cobertura: X%

Fase 5: Escaneo de Seguridad

# Busca secretos
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

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

Fase 6: Revisión de Cambios (Diff)

# Muestra qué cambió
git diff --stat
git diff HEAD~1 --name-only

Revisa cada archivo modificado en busca de:

  • Cambios no intencionados
  • Falta de manejo de errores
  • Posibles casos extremos

Formato de Salida

Después de ejecutar todas las fases, produce un informe de verificación:

INFORME DE VERIFICACIÓN
=======================

Compilación: [PASS/FAIL]
Tipos:       [PASS/FAIL] (X errores)
Lint:        [PASS/FAIL] (X advertencias)
Pruebas:     [PASS/FAIL] (X/Y pasadas, Z% cobertura)
Seguridad:   [PASS/FAIL] (X problemas)
Diff:        [X archivos modificados]

General:     [LISTO/NO LISTO] para PR

Problemas a Corregir:
1. ...
2. ...

Modo Continuo

Para sesiones largas, ejecuta la verificación cada 15 minutos o después de cambios importantes:

Establece un punto de control mental:
- Después de completar cada función
- Después de terminar un componente
- Antes de pasar a la siguiente tarea

Ejecuta: /verificar

Integración con Hooks

Esta habilidad complementa los hooks PostToolUse, pero proporciona una verificación más profunda. Los hooks detectan problemas inmediatamente; esta habilidad ofrece una revisión exhaustiva.

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.

Skills relacionados