Explorar skills

Autonomous penetration testing coordinator using ReAct methodology. Automatically activates when user provides a target IP or asks to start penetration testing. Orchestrates reconnaissance, exploitation, and privilege escalation until both user and root flags are captured. (project)

Um framework de agente de IA biomédico autônomo para executar tarefas de pesquisa complexas em genômica, descoberta de medicamentos, biologia molecular e análise clínica. Use esta skill para pesquisa biomédica multi-etapas, incluindo design de triagem CRISPR, análise de RNA-seq de célula única, previsão ADMET e otimização de protocolo de laboratório, aproveitando o raciocínio de LLM.

Interpretabilidade e explicabilidade de modelos usando SHAP (SHapley Additive exPlanations). Use esta skill para explicar previsões de modelos de machine learning, calcular a importância de features, gerar gráficos SHAP, depurar modelos, analisar viés ou justiça, comparar modelos e implementar IA explicável. É compatível com modelos baseados em árvores.

Pre-build decision intelligence. Produces opinionated decision brief — the senior- consultant week-1 output before scope, stack, or approach are locked. Surfaces traps and edges, calibrated to project scope (prototype vs production vs enterprise). Use when user says '/recon', 'what to watch out for building X', 'where's the edge', 'common mistakes with X', starts a new project, or hits domain unce

Eliminate AI-generated writing patterns that erode reader trust. Activate when writing articles, documentation, press releases, or any content where AI patterns would undermine credibility. For journalists using AI assistance who need human-sounding output.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

· Build/critique frontend UIs with taste, rejecting AI design tells. Mobile-first, touch-aware, dark+light. Triggers: 'frontend', 'ui', 'ux', 'css', 'tailwind', 'landing page', 'design review'. Not for code logic (code-review).

When the user needs to design or evaluate system architecture — service boundaries, data models, API contracts, infrastructure topology, database selection, or dependency analysis. Also activate for "design the system", "how should I architect this", "monolith vs microservices", or architecture decision records.

Expert SQL query generation for DBX Studio. Use when writing, optimizing, or debugging SQL queries against user database connections.

No ambiente de desenvolvimento de código, explore, leia e crie, aplicando a disciplina de contexto que prioriza o esboço.

AWS and infrastructure-as-code expert for Python/FastAPI full-stack apps. Use this when you need cloud architecture design, infrastructure review, Terraform/CDK implementation, cost optimization, or deployment strategy. Covers Lambda, ECS, RDS, VPC, IAM, networking, and production AWS patterns. Triggers on: AWS, Terraform, CDK, cloud architecture, infrastructure, Lambda, ECS, RDS, Aurora, deployme

Lightweight web fuzzing via ffuf — directory discovery, parameter testing, subdomain enumeration.