Explorar skills

Captura uma captura de tela de uma câmera e a retorna como uma imagem para inspeção visual pelo LLM, usando a Câmera Principal se nenhuma for especificada.

Registro para LLMs, mas sem excessos. Um formato de log baseado em CSV otimizado para o uso de tokens de LLM.

Use vLLM for high-throughput production serving of self-hosted models with DSPy. Use when you want production LLM serving, tensor parallelism, multi-GPU inference, batch processing, or high-concurrency self-hosted models. Also used for vllm, vLLM, production serving, high throughput LLM, tensor parallelism, self-hosted production, PagedAttention, local production server, GPU serving, batch inferen

Este fluxo de trabalho completo de produção de vídeo com IA utiliza os modelos WAN 2.1 e Qwen Image Edit 2511 via ComfyUI para criar qualquer tipo de vídeo, de promocional a narrativo. Ele auxilia usuários na criação de vídeos com IA, storyboard, geração de keyframes e escrita de prompts, seguindo uma abordagem com foco na filosofia.

Tier-1 strategy-consultant analysis tailored for healthcare / hospital ops problems — readmissions, length of stay, access, outcomes, throughput. Same five frameworks as the generic master, with healthcare-aware MECE defaults, industry vocabulary, and common root-cause patterns. Use for clinical-operations problems.

Chain multiple AI steps into one reliable pipeline. Use when your AI task is too complex for one prompt, you need to break AI logic into stages, combine classification then generation, do multi-step reasoning, build a compound AI system, orchestrate multiple models, or wire AI components together. Also used for LangChain LCEL alternative, how to chain LLM calls together, one prompt is not enough,

Score, grade, or evaluate things using AI against a rubric. Use when grading essays, scoring code reviews, rating candidate responses, auditing support quality, evaluating compliance, building a quality rubric, running QA checks against criteria, assessing performance, rating content quality, or any task where you need numeric scores with justifications. Also use when building an LLM as a judge, a

Configura o motor e a versão do jogo do projeto, fixando-o em CLAUDE.md. Detecta lacunas de conhecimento e preenche a documentação de referência via WebSearch se a versão estiver fora dos dados de treinamento do LLM.

Categorize the factors of a problem so they don't overlap (Mutually Exclusive) and nothing is missed (Collectively Exhaustive). Outputs nested Markdown bullets. Use for problem structuring, "make sure I've thought of everything", or step 1 of a strategic analysis.

Guia para a criação de servidores MCP (Model Context Protocol) de alta qualidade que permitem que LLMs interajam com serviços externos através de ferramentas bem projetadas. Utilize ao construir servidores MCP para integrar APIs ou serviços externos, seja em Python (FastMCP) ou Node/TypeScript (MCP SDK).

State a falsifiable hypothesis, then build a Markdown table comparing what you'd Expect to see if it's true vs. the Actual data (or what data is needed). Use for designing analysis plans, pinpointing where reality diverges from expectation, or step 3 of a strategic analysis.

Um formato de registro baseado em CSV para LLMs, otimizado para o uso de tokens e sem excessos.