Menü
Sistema de verificación completo para sesiones de Claude Code.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Use after a complex task, failure, or when reviewing what was learned. Teaches how to write growth logs that extract reusable patterns — not diary entries.
Design a goal-oriented agent loop, and review it for the ways loops go wrong — spinning and burning tokens, Goodhart-gaming the verifier, or running a wrong answer to completion. Two actions: (1) WRITE a loop — gate whether to build it, define a machine-decidable goal, pick the loop type, pick a skeleton; (2) REVIEW a loop — run it past five failure modes plus decidability, boundaries, fallback, judge independence, and keep-judgment-with-the-human red lines. Use when designing an autonomous agent loop, or when you already have one and worry it will spin, cheat, or run a wrong answer to the end. Complements the mechanism-layer loop skills (autonomous-loops, continuous-agent-loop) by covering the judgment layer they don't. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent a runaway loop, goal-oriented loop, decidable goal, plan/build/judge.
Stop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits.
React Native and Expo app patterns — Expo Router navigation, state separation (server/client/route/form), TanStack Query data fetching with Zod, performant lists, NativeWind/StyleSheet styling, native APIs, and secure storage. Use when building or editing React Native / Expo screens, components, navigation, or data layers.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
| name | verification-loop |
| description | Sistema de verificación completo para sesiones de Claude Code. |
| origin | ECC |
Sistema de verificación completo para sesiones de Claude Code.
Invocar este skill:
# Verificar si el proyecto compila
npm run build 2>&1 | tail -20
# O
pnpm build 2>&1 | tail -20
Si el build falla, DETENER y corregir antes de continuar.
# Proyectos TypeScript
npx tsc --noEmit 2>&1 | head -30
# Proyectos Python
pyright . 2>&1 | head -30
Reportar todos los errores de tipo. Corregir los críticos antes de continuar.
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
# Python
ruff check . 2>&1 | head -30
# Ejecutar pruebas con cobertura
npm run test -- --coverage 2>&1 | tail -50
# Verificar umbral de cobertura
# Objetivo: mínimo 80%
Reportar:
# Verificar 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
# Verificar console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
# Mostrar qué cambió
git diff --stat
git diff HEAD~1 --name-only
Revisar cada archivo modificado en busca de:
Después de ejecutar todas las fases, producir un reporte de verificación:
REPORTE DE VERIFICACIÓN
=======================
Build: [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. ...
Para sesiones largas, ejecutar la verificación cada 15 minutos o después de cambios importantes:
Establecer un checkpoint mental:
- Después de completar cada función
- Después de terminar un componente
- Antes de pasar a la siguiente tarea
Ejecutar: /verify
Este skill complementa los hooks PostToolUse pero proporciona una verificación más profunda. Los hooks detectan problemas de inmediato; este skill proporciona una revisión completa.