Explorar skills

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Exports approved outreach emails into the user's preferred format: sequencer CSV, plain text, or formatted for specific tools. Triggers: /push, "export emails", "push to instantly", "push to outreach". Reads: ./gtm/prospects.md, ./gtm/icp.md (for stack info). Writes: output files in ./gtm/export/. Standalone: yes.

Generates a human-readable architecture document for any codebase. Use when onboarding contributors, presenting to stakeholders, explaining how a system works to non-technical collaborators, or after a major architectural change. Outputs docs/ARCHITECTURE.md with a Mermaid system diagram, plain English narrative, data flow walkthrough, and tech stack rationale. Trigger on: "map the architecture",

Habilidade de ponto de verificação de continuidade v1 pública para revisão de contexto recente limitado. Utilize quando o usuário busca um julgamento conservador, focado em reinício, sobre o que deve ser mantido, o que deve permanecer visível de forma mais leve e o que não merece forte preservação—sem escritas de memória ocultas ou varredura ampla.

Google Ads AI Copiloto. Transforma a lógica de especialistas em fluxos de trabalho reutilizáveis para mineração de termos de pesquisa, filtragem de palavras-chave negativas, otimização de orçamento e diagnóstico de contas, eliminando a necessidade de Excel manual.

Use before committing or opening a pull request — reviews staged changes as a principal engineer for correctness, edge cases, and logic flaws. Always invoke this before creating a PR.

Use when converting wiki-exported requirement documents (containing docx, xlsx, md, images) into standardized templates (functional requirement docs + FAQ docs), with a gaps checklist for product managers to supplement missing information.

Review the current project state and continuously guide the project toward better Harness and Compound Engineering practices. Identify: - behaviors that align with best practices - anti-patterns or weak workflows - missing operational discipline, evals, harnesses, or feedback loops Then recommend the next highest-leverage step, including: - what to do next - why it matters now - what commands, too

Clinical Risk Management Plan (CRMP) creator for health IT systems. Produces a structured CRMP aligned with NHS England DCB0129/DCB0160 and the NHS Digital CRMP template. Covers scope, safety roles, risk management activities, tools and methods, documentation requirements, and review schedule.

Tool Discovery Skill

扫描代码仓库生成交互式架构地图，展示模块依赖、调用链、 核心入口点和代码热区。当用户提到"代码架构"、"项目结构"、 "依赖关系"、"代码地图"、"帮我看懂这个项目"时使用。 即使用户只是说"这个仓库好大我不知道从哪里看起"也应触发。

Esta Skill de Visibilidade do Agente ajuda seu criador a ser citado por ChatGPT, Claude, Perplexity e Gemini, medindo lacunas, produzindo artefatos e publicando resultados. Ela roda localmente com os próprios tokens do seu agente, garantindo que a Bloom nunca veja suas chaves ou raciocínio.