Explorar skills

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Pack entire codebases into AI-friendly files for LLM analysis. Use when consolidating code for AI review, generating codebase summaries, or preparing context for ChatGPT, Claude, or other AI tools.

Install and connect the Azure Cost Management App (by Microsoft Corporation) in Power BI Service via browser automation. Use this skill whenever the user mentions installing, deploying, connecting, or configuring the Azure Cost Management template app in Power BI, or when they want to connect Power BI to their EA (Enterprise Agreement) enrollment for cost visibility. Also triggers when the user sa

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati

Esta skill é para salvar, consultar e manter artigos em uma base de conhecimento, suportando fontes como URLs de WeChat, páginas web, repositórios GitHub e arquivos locais. Não se aplica a bases de conhecimento .omc/wiki internas ou downloads simples de arquivos.

Controle um Xiaomi Robot Vacuum X20+ via CLI xiao. Pronto para agentes: AGENTS.md, llms.txt, SKILL.md, saída --json, códigos de saída canônicos.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

Transforme prompts/ideias iniciais em prompts de LLM prontos para produção. Use ao criar, refinar ou otimizar prompts para qualquer modelo de IA (Claude, GPT, Llama, etc.) com técnicas avançadas como CoT, IA constitucional e otimização RAG.

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

Transforme gravações de áudio em documentação profissional em Markdown com resumos inteligentes usando integração LLM.

Executa uma sessão do PRISM College — revisão por pares multi-LLM para decisões de arquitetura de porta única. Acionado por /prism, /prism prepare, /prism refract, /prism inspect, /prism sync, /prism settle, /prism memorialize.