Desenvolvimento

Assistente OpenTelemetry para engenheiros. Use quando solicitado a adicionar instrumentação OTel ao código da aplicação, procurar documentação ou exemplos do SDK por linguagem, ou avaliar e pontuar a qualidade da instrumentação existente contra a especificação Instrumentation Score.

Use para escrever ou converter testes JUnit em Java ou Kotlin com a biblioteca TableTest. Ativa ao testar múltiplos cenários com a mesma lógica de asserção, converter métodos @Test repetitivos, iniciar um novo @TableTest, ou ao discutir a sintaxe do TableTest ou escrever testes para uma funcionalidade.

Pesquisa, extrai e refina automaticamente o conteúdo de um artigo a partir de um link do arXiv ou título, oferecendo uma explicação estruturada e simplificada para iniciantes.

Audits a working feature for the gap between "happy path passes" and "production-ready" — edge cases, error handling, loading/empty/error states, a11y, responsive, i18n, observability, ops hooks. Use when a feature works but needs polish, for "완성도 높여줘", "production ready로", "edge case 검토", "polish this feature", "is this ready to ship?", "엣지 케이스 다 챙겼나", "PR 전 점검", "빠진 상태 없나", or before shipping an

Trigger on "consult integrity", "integrity gate", "integrity check", "verify proposal claims", "hallucination check proposal", "cos integrity". Seven-mode failure checklist at gates 3.5 and 5.5. Uses timeln-quickly and timeln-shipped to verify quotes and proof claims. NOT lint (use consult-consistency-lint), NOT red team (use consult-red-team).

Use esta skill ao configurar ferramentas de qualidade de código (formatadores, linters, verificadores de tipo, scanners de dependência) para um repositório, ou ao adicionar automação de acessibilidade visual ou varredura de linha de base de segurança. Não a utilize para codificação geral ou quando as ferramentas já estiverem configuradas.

Run a code review using Cursor Agent with Gemini

Manage the macOS notification that fires when a Claude Code tab has been waiting on the user for more than N minutes. Use when the user types /headsup-notifications, asks to enable/disable the "Claude is waiting" notification, wants to change how long it waits before notifying, or wants to test that notifications are working. Accepts on/off, a numeric threshold (minutes), "test" to fire a one-off

Review and refactor implemented code with quality checklist

Side-by-side comparison of 2-4 business ideas on 8 weighted dimensions. Produces a ranked matrix with scores, trade-off analysis, and a clear recommendation of which idea to pursue first. Use when user runs `/idea-comparison`, asks to "compare these ideas", "which idea should I pursue", "rank my ideas", "prioritize between ideas", or has multiple business concepts and needs to choose.

Reviews a SKILL.md file or skill directory for quality, correctness, and alignment with Claude Code skill conventions. Use when you've written a new skill and want to check it before committing, or when evaluating an existing skill for improvements.

Build the world before you write the story. Advanced context engineering for deep research, foundational research, and evidence-first planning before coding. Use when the user asks for world building, deep research before building, foundational research, market mapping before coding, hands-off but non-generic results, pillar mapping, folder scaffolding, parallel research, layered synthesis, or evi