Explorar skills

Stress-test and improve implementation plans before execution. Researches alternatives, challenges complexity, checks modularity and feasibility, then delivers a full revised plan. Use whenever the user has a plan — any format (PLAN.md, inline, pasted, attached) — and wants it reviewed before starting. Trigger on 'review this plan', 'challenge this plan', 'stress test', 'is this plan good', 'befor

Utilize para executar agentes Claude Code durante a noite em lotes multitarefa, configurando turnos noturnos, arquivos de tarefas com pares de Implementação+Validação, ou loops de revisão de PR à prova de falhas.

Utilize para escrever testes, projetar cobertura de teste, corrigir defeitos, analisar causas-raiz, configurar verificação de CI ou hooks de commit. Também para criar matrizes de teste ou escolher entre testes unitários/de integração/E2E, mas não para desenvolvimento geral ou configuração de linting.

Use when Claude Code needs to get oriented in a SpecDD project before later work, while making no edits.

Use when you need to investigate an unfamiliar library, framework, architectural question, or technical decision — spawns the researcher agent which explores the codebase and searches external sources in parallel. Invoke before making technology choices or when the right approach is unclear.

Use this skill whenever a user asks for analyst calls, earnings call transcripts, or earnings webcasts for any of the top 100 Nasdaq-listed U.S. companies. Trigger for questions like "Show me the earnings call for Apple", "Where can I find NVIDIA's latest transcript?", "Do you have a webcast link for Microsoft's last earnings?", or any request to find or access earnings call recordings, transcript

Use Google's Deep Research API (Gemini) to conduct comprehensive, multi-source research that runs for 5-20 minutes server-side and produces detailed research reports. Use when the user asks for "deep research", thorough investigation of complex topics, market analysis, competitive landscaping, or any research requiring multiple web sources synthesized into comprehensive reports. This skill uses th

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when Claude Code needs to add SpecDD to a project or update SpecDD framework files through the CLI before normal SpecDD work begins.

Recommend what to do after an experiment based on the result quality, effect size, and business context. Use this skill when the user has a completed experiment and needs a practical product decision such as roll out, rerun, iterate, segment-rollout, or reject.

Use when Claude Code needs to write or update documentation from active SpecDD specs.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.