Explorar skills

Guides Claude to help B2B marketers build, maintain, and activate segmented email lists — covering exclusion logic, engagement monitoring, personalization, and list hygiene. Trigger when a user asks about segmenting email audiences, managing list health, or improving email relevance.

Generate a comprehensive HTML training dashboard showing progress toward half marathon training goals. Outputs a single self-contained HTML file with retro styling, ASCII charts, weekly mileage tracking, session completion rates, pace adherence, phase progress, and coaching commentary. Use when the athlete wants to see their training progress, check if they're on track, view their training statist

Esta skill realiza auditorias de SEO, GEO e AEO para qualquer site, mapeando cada verificação às melhores práticas do Google para Busca, Visões Gerais de IA, Core Web Vitals, dados estruturados e camadas de recuperação cross-LLM. Cada achado cita sua documentação do Google ou do provedor.

Generate integration tests for APIs, databases, and external services. Auto-detects backend stack (Express, Fastify, NestJS, Django, FastAPI, Rails, Go), ORM (Prisma, TypeORM, SQLAlchemy, GORM), and database (PostgreSQL, MongoDB, Firestore), then creates tests covering endpoint CRUD, auth flows, DB transactions, and external service failures with proper fixtures and mocks. Self-heals failing tests

Feature discovery agent — mines project docs, memory, user feedback, and competitor gaps to surface the highest-leverage features to build next. Outputs a prioritized feature backlog.

Activates PodcastProducer — a full-stack podcast creation agent. Use when you need to plan a podcast series, write episode scripts, create show notes, design interview questions, write ad copy, produce episode titles and descriptions for SEO, or build a content calendar for a podcast with consistent voice and structure.

Atua como revisor por pares, focando na contribuição científica e honestidade. Verifica a adequação do escopo às alegações, a divulgação de falhas e o exagero nas afirmações, para uso na fase de revisão por pares.

Diagnose NaN losses, out-of-memory errors, and shape mismatches in deep learning or ML pipelines.

Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Activates SupplyChainOptimizer for advanced supply chain network design and operational efficiency. Use when you need network optimization modeling (warehouse location, distribution routes), last-mile delivery cost analysis, multi-tier supplier risk assessment, supply chain digital twin design, or trade compliance and customs optimization.

Run independent work in parallel with explicit wave boundaries, lightweight coordination, and bounded verification. Use when latency matters and the work does not need a persistent completion loop.