Explorar skills

Mantine v7 component library — theming, styling, hooks, forms, notifications

Generates strategic attack trees and kill chains from reconnaissance data or domain input. Maps MITRE ATT&CK TTPs, identifies chaining opportunities, trust relationships, and prioritizes attack paths by feasibility and impact. Use when user asks for "attack path", "kill chain", "attack tree", "threat modeling from recon", "attack surface analysis", or "prioritize targets". Requires prior recon dat

Estime o trabalho e defina o escopo na era da codificação com IA, aplicando Boil the Lake, considerando taxas de compressão de IA e uma busca em três camadas antes de construir.

Apply operational controls to applications built on the Anthropic API or similar LLM SDKs. Maps the OWASP LLM Top 10 to practical controls, plus rate limiting, cost caps, PII scrubbing, audit logging, model-version pinning, and an AI-incident response playbook. Invoke when shipping an LLM feature to production, when handling an abuse complaint, or after a model-provider advisory.

NgRx SignalStore patterns for Angular state management. Use when managing client state with Angular Signals, composing store features, handling entities, or integrating RxJS effects.

Enforces strict test-driven development. Use when implementing ANY feature, bugfix, or refactor — before writing implementation code. Also use when someone says 'add tests', 'write tests', 'test this', 'TDD', or when you're about to write production code of any kind. If you're about to write code and there isn't a failing test for it yet, STOP and use this skill.

Scanner de segurança para skills de Agentes de IA, plugins e servidores MCP, usado para verificar a segurança, detectar código malicioso e garantir a proteção da cadeia de suprimentos.

Roast code with aggressive humor while preserving a factual staff review; --fix can apply selected CRITICAL/HIGH fixes.

Sync work between AI agents. Log actions, manage sessions, detect conflicts.

Execute qualquer pergunta, plano, PR ou código através de um conselho de Debate Multiagente Diverso (DMAD) composto por 5 consultores de IA com métodos de raciocínio distintos. Os consultores colaboram, revisam-se anonimamente e um presidente sintetiza um veredito, superando empiricamente o debate adversarial.

React Native mobile development patterns - New Architecture (Fabric, TurboModules, JSI), component architecture, React Navigation 7+, FlashList v2 optimization, gestures with Reanimated 4, platform-specific code, React 19 features

React Query server state, hey-api OpenAPI codegen, type-safe data fetching