Testing & Debugging Skills

Use when working in monorepos with multiple apps/packages, when CLAUDE.md or AGENTS.md files need validation, when detecting broken links, redundant or conflicting instructions, vague instructions, incomplete coverage, or inconsistent formatting - validates structure, links, and instruction quality with interactive correction…

Use when the user asks to "find duplicated code", "map responsibilities", "consolidate code", "find code sprawl", "analyze duplication", "create consolidation plan", or mentions "código duplicado", "responsabilidades espalhadas", "consolidar". Analyzes codebases to identify scattered responsibilities that should be centralized.

Use when starting a session on a project with memory files or AGENTS.md after a gap, after changing backend services or API configurations, after adding features or packages, or when the user says "check maintenance", "atualizar contexto", "context fresh", "memory audit". Also trigger proactively when you notice a discrepancy between memory files and actual code.

Validate coverage thresholds and PR gates, flagging critical low-coverage files. Use when enforcing a minimum coverage bar. Triggers on: checar cobertura, threshold de cobertura, gate de cobertura, minimo de cobertura, arquivos sem teste, coverage gate, coverage check.

Run test coverage across local stacks (Vitest, Playwright, pytest). Use when you want to measure how much of the code the tests cover. Triggers on: rodar cobertura, cobertura de testes, gerar coverage, quanto de cobertura, run coverage, test coverage.

Designer senior extremamente critico. Analisa aplicacao web em 5 pilares (Visual Consistency, Information Hierarchy, Interaction Quality, Spatial Design, Polish & Craft), captura screenshots via Playwright, gera relatorio com score, e aplica auto-fix em todos os findings. Triggers on: design audit, design review, visual audit, auditoria design, design critic, critica visual, design quality, review visual, UI review, UX review, modernizar, modernize, refinar visual, polish UI, design consistency, consistencia visual.

Use when analyzing user journeys, auditing UX quality, prototyping flows, or designing new pages/features from a product perspective. Triggers on: jornada do usuario, fluxo de agendamento, prototipo, prototipar, experiencia do usuario, UX audit, usabilidade, melhorar conversao, nova pagina, nova feature, redesign, agendamento, checkout, onboarding, cadastro, landing page, flow, wireframe, mockup, prototipacao. Runs BEFORE implementation — analyzes the PRODUCT experience, not the code.

Analyze E2E test failures with timeline reconstruction, code correlation, and history lookup. Use after running tests: 'analyze e2e', 'e2e failures', 'diagnose tests'.

Plan, audit or debug end-to-end (E2E) test coverage, flows and fixtures (Playwright). Use when designing or improving an E2E test suite. Triggers on: planejar testes e2e, arquitetura de testes e2e, cobertura e2e, estrategia de e2e, fixtures e2e, e2e architect, end-to-end test plan.

Visual smoke test using Chrome DevTools MCP against a running web app (local or production). Navigates key pages, captures screenshots, inspects console errors, network failures, runs Lighthouse audits, tests mobile/dark-mode emulation, and traces performance. Use this skill whenever the user says "smoke test", "visual test with chrome", "chrome devtools test", "visual QA", "devtools smoke", "visual e2e", "test with real browser", "test no chrome", "teste visual", "smoke visual", or wants to audit a running app through the real Chrome browser (not Playwright). Also use when the user asks to check console errors, network failures, or Lighthouse scores on a live page via Chrome DevTools MCP.

Automated E2E test-fix cycle. Runs tests, analyzes failures, applies fixes in batches, re-runs until pass. Use for full automation: 'fix e2e', 'e2e cycle', 'auto-fix tests'.

Smart E2E test runner with auto-detection of Playwright project and wait strategies. Use when running E2E tests: 'run e2e', 'e2e admin', 'test admin-tests', 'run creator tests'.

Use when setting up GitHub repositories, workflows, issue templates, or project organization - enforces best practices for .github folder structure, reusable workflows, branch protection, CODEOWNERS, labels, and GitHub Projects. Triggers on: GitHub, repository setup, workflow, Actions, issue template, PR template, CODEOWNERS, labels, branch protection.

Run a comprehensive pre-launch quality audit on any web application. Explores the codebase first, then generates project-specific audit prompts that reference the actual files, routes, hooks, and functions found. Covers 7 areas: security, functionality, domain data coherence, visual consistency, performance, test coverage, and UX polish. Produces per-area audit reports and a final scorecard with 0-10 grades and launch readiness verdict. Use this skill whenever someone says "audit", "launch readiness", "pre-launch review", "quality check", "is this ready to ship", "review before launch", "pente fino", "revisão pré-lançamento", "está pronto pra lançar", "qa completa", "score the codebase", or any variation of checking whether a project is ready for production. Also triggers for deep-dive flow audits: "audita o wizard", "deep dive no checkout", "rastreia os dados do fluxo X", or any request to audit a specific multi-step flow in detail. Works with any web stack (React, Next.js, Vue, Svelte, etc + any backend).

Use when analyzing error logs, production failures, or recurring log patterns from Railway, files, or console output.

Design e implementação de logging estruturado com distributed tracing. Enforça schema rígido, correlation IDs, sanitização de PII e boas práticas de observabilidade. Multi-stack (Node.js, Python, Go, Frontend). Triggers on: log, logging, logger, trace, tracing, observability, correlation, span, structured log.

Investigate why a Maestro mobile test on the iOS Simulator failed. Use after a mobile/simulator test fails and you need the cause. Triggers on: teste mobile falhou, porque o teste do app quebrou, analisar falha mobile, maestro falhou, mobile test failed, ios simulator error.

Capture iOS Simulator screens via Maestro to compare the app against design references. Use when you want screenshots of the mobile app. Triggers on: screenshot do app, capturar telas do simulador, comparar com o design mobile, telas do app mobile, maestro capture, ios simulator screenshot.

Auto-repair loop for failing Maestro mobile tests on the iOS Simulator, one flow at a time. Use when you want mobile/simulator tests fixed automatically. Triggers on: conserta os testes mobile, arruma o teste do simulador, loop de correcao mobile, fix mobile tests, auto fix ios tests.

Run the app's mobile UI tests on the iOS Simulator with Maestro. Use when you want to run mobile tests on a simulator. Triggers on: teste mobile, testar no simulador, rodar app no simulador iOS, teste de app mobile, maestro, mobile test, ios simulator test.

Persistent project documentation system that maintains context across sessions. Creates structured Memory Bank files to preserve project knowledge, decisions, and progress.

Build or review React Native / Expo code for architecture, UX, performance and native best practices. Use when writing or reviewing a React Native / Expo app. Triggers on: react native, expo, app nativo, boas praticas mobile nativo, arquitetura react native, performance no app nativo, react native review.

Use when building or modifying React/Next.js components, pages, layouts, PWA configurations, or CSS/Tailwind files - enforces mobile usability standards with mandatory checks for critical issues (touch targets, viewport, safe areas, accessibility) and recommendations for PWA optimization (manifest, service worker, offline…

Create comprehensive technical documentation following Obsidian conventions with bidirectional linking, proper folder structure, templates, and developer-focused content. Use when creating documentation, READMEs, wikis, knowledge bases, ADRs, runbooks, or any technical writing. Triggers on: documentation, docs, README, wiki, knowledge base, ADR, runbook, technical writing, Obsidian.