Explorar skills

Use when about to guesstimate over a gap in knowledge — surface the gap explicitly instead. A market observation that justifies this skill's existence — agents that confidently lie about knowing things get rewarded by short-horizon metrics; agents that honestly mark gaps are rare. Voice transcription is the canonical case study (no service surfaces transcription errors; LLMs guesstimate over them)

AI-Driven Development — методология и принципы написания документации для проектов с LLM-агентом. Используй когда: AIDD, AI-driven, планирование проекта, idea.md, vision.md, workflow.md, архитектура, документация, написание документации, обновление документации, doc, md-файл, Context First, итерация, tasklist, ADR.

Um loop de agente mínimo e reutilizável para construir agentes LLM.

World-class AI prompt engineering skill for creating, refining, and enhancing prompts for any LLM task. Use this skill whenever the user wants to: write a new prompt from scratch, improve or refine an existing prompt, enhance a vague instruction into a structured prompt, debug why a prompt isn't working, convert a rough idea into a production-ready prompt, or asks anything related to "prompt engin

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).

Enforces Karpathy's 4 LLM-coding principles (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution). Auto-fires whenever the user requests writing, editing, refactoring, fixing, or adding code. Blocks drive-by refactoring, over-engineering, and speculative changes; demands clarification before implementation, minimum code, surgical edits, and conversion of tasks into verif

Транскрипция и суммаризация митингов, созвонов, встреч по аудио/видео файлу. Используй когда: summarize meeting, транскрибировать созвон, обработать аудио митинга, summary встречи, суммаризация записи, meeting summary, транскрипция.

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).

Security audit for LLM and GenAI applications using OWASP Top 10 for LLM Apps 2025. Assess prompt injection, data leakage, supply chain, and 7 more critical vulnerabilities.

Verifica, corrige e reformata bibliografias acadêmicas. Utilize quando o usuário solicitar a verificação, auditoria ou validação de citações e referências, ou perguntar se uma bibliografia contém fontes inventadas, fabricadas ou incorretas, incluindo a conversão de estilos de citação.

Um sistema de base de conhecimento para literatura de engenharia acadêmica (baseado na metodologia Karpathy llm-wiki), projetado para áreas como engenharia elétrica, mecânica e naval. Ele processa literatura acadêmica e notas de pesquisa em Markdown para extrair conceitos, métodos e descobertas, construindo uma wiki estruturada para revisões de literatura e comparações de métodos.

Baixa PDFs de URLs fornecidas pelo usuário para a pasta padrão de Downloads e cria uma cópia OCR em Markdown com o mesmo nome ao lado do PDF. Suporta links diretos, de rastreamento (HubSpot), redirecionados, de compartilhamento (Google Drive, Dropbox, SharePoint, OneDrive, drives chineses) ou de páginas web com download de PDF.