Explorar skills

Esta skill é acionada para criar vídeos curtos, conteúdo educacional, explicações de tópicos, demonstrações de produtos e clipes de estilo de vida, especialmente quando dublagem, imagens e síntese de vídeo vertical são necessários. Não lida com problemas de reprodução/codificação de vídeo, edição manual ou conteúdo puramente textual/visual.

Converte links de compartilhamento de conversas do ChatGPT, Gemini, Grok e Claude em transcrições limpas em Markdown + HTML. Esta CLI nativa do Bun preserva blocos de código com detecção de linguagem, permite nomes de arquivo determinísticos e suporta a publicação no GitHub Pages.

Um sistema de IA multiagente para assistência em pesquisa científica, automatizando fluxos de trabalho da análise de dados à publicação. Ele suporta pipelines de pesquisa completos, incluindo a geração de ideias, desenvolvimento de metodologias, execução de experimentos, buscas bibliográficas e a criação de artigos prontos para publicação em formato LaTeX.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.

Comprehensive code review workflow coordinating quality, security, performance, and documentation reviewers. 4-hour timeline for thorough multi-agent review.

Design AI-first interfaces that build ongoing relationships through memory, trust evolution, and collaborative planning. Use when designing agentic UX, memory-aware interfaces, or relationship-centric product experiences. NOT for general UI/UX tasks.

This skill should be used when extracting voice profiles from sample text, creating voice documentation, or matching a specific writing style. It applies when users provide sample text and want to capture the voice for future use.

Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.

Guide for writing effective log messages using wide events / canonical log lines. Use when writing logging code, adding instrumentation, improving observability, or reviewing log statements. Teaches high-cardinality, high-dimensionality structured logging that enables debugging.

Build identity-preserving professional headshot prompts and provider-ready generation payloads from a single photo input. Use when users ask to transform selfies into professional portraits, resume photos, or ID-style images with strict realism and safety constraints.

Use when creating, editing, formatting, exporting, or extracting LibreOffice Calc (.ods) spreadsheets via UNO, including session-based cell and range edits, sheets, named ranges, validation, charts, patch workflows, and snapshots.

Use when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or optimizing documentation for token-efficient AI consumption.