Explorar skills

PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on twelve classic engineering books. Triggers when: user asks to review code, check a PR, shares a diff or pastes code asking "does this look right?" / "any issues here?" / "ready to merge?", or asks for feedback on a function, class, or file.

Scaffold a new brooks-lint analysis skill so it passes `npm run validate` and `npm run evals` on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends paired eval scenarios. Triggers when the maintainer asks to "add a new skill",

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user wants to "fix everything", "sweep the codebase", "auto-fix all issues", "clean up th

Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests + README badge, write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release", "cut a release", "ship a new version", or "bump and publish" brooks-lint. Do NOT trigger for: propagating an already-decided version with

Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized, or asks "does this follow clean architecture?" or "why does everything depend on e

Combined codebase health dashboard that scores a project across all four quality dimensions — PR quality, architecture, tech debt, and test quality — in a single pass, drawing on twelve classic engineering books. Triggers when: user wants an overall quality assessment, asks "how healthy is this codebase?", "run all the checks", "I need a health score before the release", or wants to onboard a new

Implante, gerencie ou retire-se de um cofre de agente de IA na Versa, a arena de IA adversarial onchain na Base.

Gerencia máquinas virtuais AWS EC2, incluindo instâncias, grupos de segurança, pares de chaves, AMIs, volumes EBS, grupos de Auto Scaling, instâncias Spot, Session Manager, grupos de posicionamento e automação do ciclo de vida da instância.

Monitoramento AWS CloudWatch para logs, métricas, alarmes e painéis. Utilize ao configurar monitoramento, criar alarmes, consultar logs com Insights, configurar filtros de métricas, construir painéis ou solucionar problemas de aplicações.

Orquestração de contêineres AWS ECS para executar contêineres Docker. Utilize ao implantar aplicações conteinerizadas, configurar definições de tarefa, configurar serviços, gerenciar clusters ou solucionar problemas de contêineres.

AWS Identity and Access Management para usuários, funções, políticas e permissões. Use ao criar políticas IAM, configurar acesso entre contas, configurar funções de serviço, solucionar erros de permissão ou gerenciar controle de acesso.

AWS EventBridge é um barramento de eventos serverless para arquiteturas orientadas a eventos. Utilize-o para criar regras, configurar padrões de eventos, configurar eventos agendados, integrar com SaaS ou construir roteamento de eventos entre contas.