Desenvolvimento

Use when the user asks about token usage, session cost, or wants to check optimization effectiveness.

Use when starting a new session, the project has changed significantly, or you need a fresh context summary.

Use when the user asks to create, refine, evaluate, or optimize an LLM prompt. Do NOT trigger for Claude Code skills (use skill-creator) or when rewriting an existing skill (use transformer). Example triggers - "write a prompt for my summarizer", "tighten this system prompt", "evaluate this agent prompt".

Open multi-AI conversation — all buddies think together on a topic, no competition, just talk

内容校准统一入口，自动判断意图+状态路由到对应动作。支持 OpenClaw（完整管线）和独立模式（打分+预测）。Use when 用户说"校准""打分""预测""复盘""状态""下一步""到哪了"或提到内容质量评估/评分/校准相关的任何意图。

Gerencie Google Docs e Google Drive com operações completas de documentos e gerenciamento de arquivos. Oferece suporte a Markdown para criar documentos formatados e inclui operações do Drive como upload, download, compartilhamento e busca.

Um enxame autônomo de engenharia de qualidade que gera código pronto para produção através de verificação comportamental contínua, testes E2E exaustivos e ciclos de correção auto-reparáveis. Ele integra DDD+ADR+TDD com especificações BDD/Gherkin, 7 portões de qualidade, previsão de defeitos, testes de caos e consciência de dependência entre contextos, suportando diversas arquiteturas.

Use when the user asks to rebase the current branch onto another branch or update branch history without merging.

Assess Active Directory identity attack paths including roasting, relay, and delegation abuse.

Run controlled exploitation against confirmed vulnerabilities while enforcing scope and authorization gates.

Aggregate findings and generate multi-format pentest reports with remediation roadmap and risk scoring.

Use when the user wants to change optimization aggressiveness, switch between aggressive/balanced/thorough modes, or adjust token-saving behavior.