Explorar skills

Systematic root-cause analysis for build failures, test errors, and runtime issues. Use when: "error", "failed", "broken", "debug", "why did this fail", "root cause".

One-question-at-a-time interview to extract what the user wants — each question carries a best-guess + structured options; stop at ~95% confidence. Use when the user says "interview me", "grill me", "I'm not sure what I want", or `/rite-spec` / `/rite-define` flags the ask as underspecified. Not for casual clarification or ideation (use `rite-pressure-test`).

Minimize Claude token and cost waste across ALL surfaces — Claude Code subagents, API calls in code, and artifacts. Routes subagent model selection via the Agent tool's model parameter. Recommends /model switches when the current model is overkill or underpowered. Applies to any code importing anthropic or calling /v1/messages. Trigger on: "API call", "artifact", "pipeline", "multi-agent", "LangGr

Set up local Git hooks for pre-commit validation (lint, format, tests, secrets). Integrates with mern-scaffold, nean-scaffold, and iOS projects.

Habilidade em engenharia de acessibilidade para produtos web com testes JAWS e NVDA, além de orientação sobre conformidade Espanha/UE. Utilize quando a tarefa envolver implementação WCAG 2.2, comportamento ARIA, problemas de teclado/foco, regressões de leitores de tela, auditorias de acessibilidade, planos de remediação ou verificações de escopo legal para a Lei 11/2023, RD 1112/2018, EAA e EN 301 549.

Use when a user asks to grill, pressure-test, or stress-test a plan against a project's domain language, glossary, CONTEXT.md, ADRs, documented decisions, code behavior, or overloaded terminology.

Grelha o usuário em Patois jamaicano, interrogando suposições e trade-offs de planos ou designs com atitude e rigor técnico. Ideal para sessões de teste de estresse com uma vibe única.

Use quando arquivos de teste se acumulam em projetos, suítes de teste se tornam difíceis de gerenciar, testes intermitentes surgem, a execução de testes é lenta, usuários questionam sobre limpeza ou arquivamento de testes, ou ao organizar testes após fluxos de trabalho gerados por skills como bkit ou ciclos TDD de superpowers.

Lightweight session initialization. Reads latest manifests and handoffs to resume context. Loads only what the current task needs. Trigger on session start, "resume", "pick up where I left off", "continue from last session", "init".

Use when the user names a TS/JS/Python/Java/C#/PHP/Kotlin/Dart/Swift file or function and asks what design pattern fits, asks to compare which pattern (and why/how it fits), to refactor to a pattern, to make new code match existing patterns ("match existing", "make this consistent"), or to implement new behavior with the right pattern. Recommends one of Strategy/Factory/Adapter/Repository/Observer

Use when planning, running, or learning from chaos engineering experiments. Triggers on "chaos experiment", "fault injection", "gameday", "resilience test", "blast radius", "steady state", "abort criteria", "Chaos Toolkit", "Chaos Mesh", "Litmus", "Gremlin", "AWS FIS", or any deliberate failure-injection question. Ships experiment designer, blast-radius calculator, and postmortem generator (all st

Revisão de documentos cega única e teste de estresse com advogado do diabo. Utilize ao analisar propostas, PRDs, especificações ou planos para identificar lacunas de expressão e falso consenso.