Explorar skills

Example project-specific skill template based on a real production application.

Network reconnaissance and security auditing using Nmap for port scanning, service enumeration, and vulnerability detection. Use when: (1) Conducting authorized network reconnaissance and asset discovery, (2) Enumerating network services and identifying running versions, (3) Detecting security vulnerabilities through NSE scripts, (4) Mapping network topology and firewall rules, (5) Performing comp

Generate professional documents in multiple formats (docx, pdf, html, md) from scratch or based on user files. Supports web search for up-to-date content. Use when the expected output is longer than a short answer and benefits from structure and formatting. Do NOT use for short plain-text answers, code files, or casual Q&A.

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, scree

MCP (Model Context Protocol) 2025-11-25 server standards — tool/resource/prompt primitives, capability negotiation, Streamable HTTP transport with Mcp-Session-Id, OAuth 2.1 + RFC 8707 resource indicators, tool annotations (readOnly/destructive/idempotent), structured output, JSON-RPC error mapping, prompt-injection and SSRF defenses, MCP Inspector testing. Python (FastMCP) and Go (official SDK) re

Implement user-friendly error handling with specific exception types, centralized error handling, graceful degradation, and proper resource cleanup. Use this skill when implementing error handling in controllers, services, or API endpoints, when creating custom exception classes, when writing try-catch blocks, when handling external service failures, when implementing retry strategies, when displa

O Azure Machine Learning SDK v2 para Python é usado para gerenciar workspaces de ML, trabalhos, modelos, conjuntos de dados, computação e pipelines.

Oferece melhores práticas, padrões e orientação de API para Redux-Saga, focando na construção, teste e depuração de middleware de efeitos colaterais baseados em geradores. Abrange criadores de efeitos, modelo fork, canais, testes, concorrência, cancelamento e integração com Redux Toolkit.

Create post-trade-show follow-up email sequences, lead nurture campaigns, and meeting recap emails. Use this skill when the user needs to follow up with leads after a trade show, exhibition, expo, or conference — including tiered email sequences (hot/warm/cold), thank-you emails, meeting recap emails, badge-scan follow-ups, or any post-event outreach. Triggers on phrases like 'follow up after the

Executa um teste A/B da mesma tarefa em múltiplos níveis de modelo (Haiku, Sonnet, opcionalmente Opus), capturando saídas, calculando diferenças estruturais e semânticas, pontuando a qualidade e gerando um relatório de comparação em markdown.

O outpainting de imagens no RunComfy via CLI `runcomfy` estende fotos além de sua tela original, preenchendo partes ausentes e alterando proporções (ex: quadrado para 16:9, retrato para paisagem) com preservação do conteúdo. Ele utiliza modelos como Nano Banana 2 Edit, GPT Image 2 Edit e FLUX Kontext Pro.

Gere vídeos com IA usando Google Veo, Seedance, Wan, Grok e mais de 40 outros modelos via CLI inference.sh. Esta ferramenta suporta texto-para-vídeo, imagem-para-vídeo, sincronização labial e animação de avatares, ideal para mídias sociais, marketing e demonstrações de produtos.