Explorar skills

Prepare release communication and check readiness. Main mode: notes with optional flags --changelog, --summary, --migration; range as v1->v2. Other modes: prepare (full pipeline: audit → all artifacts), audit (pre-release readiness: blockers, docs alignment, version consistency, CVEs), demo (story-telling release notebook in jupytext # %% format).

Use esta skill para revisar estaticamente implantações do Triton Inference Server, cobrindo o layout de `model_repository/`, arquivos `config.pbtxt`, configuração de batching dinâmico, pipelines de ensemble e BLS, postura de confiança de backends personalizados, autenticação de endpoints, cache de resposta, limite de taxa e exposição de métricas.

Esta skill revisa o OpenTelemetry Operator, cobrindo modos de implantação do OpenTelemetryCollector (Deployment, StatefulSet, DaemonSet, Sidecar), auto-instrumentação de CR em Java/Node/Python/.NET/Go, Target Allocator para scraping distribuído do Prometheus e correção de pipeline entre receptores, processadores e exportadores.

Esta skill permite construir, integrar e depurar aplicações da API Gemini na Google Cloud Agent Platform (anteriormente Vertex AI) usando o SDK unificado google-genai. Ela suporta funcionalidades como geração de texto, entradas multimodais, chamada de função e ajuste de modelo em Python, TypeScript/JavaScript, Go, Java e C#.

Implante qualquer projeto no xCloud hosting com detecção automática da stack (WordPress, Laravel, PHP, Node.js, Next.js, NestJS, Python, Go, Rust). A ferramenta direciona para implantação nativa ou Docker, gerando Dockerfile, docker-compose.yml, CI/CD do GitHub Actions e .env.example prontos para produção, mesmo sem configuração Docker prévia.

Generates professionally designed PDF audit reports. Activates when the user requests a PDF report, wants to export audit findings, asks for a printable report, or uses the generate-pdf or export-html commands. Produces a visually stunning HTML report with SVG gauge charts, color-coded severity cards, and professional tables, then converts to PDF. Uses Python script for reliable multi-engine PDF g

Read a CSV file from disk, compute per-column min/mean/max for every numeric column, emit the result as JSON. Stdlib-only Python; no pandas, no numpy. Demonstrates the simplest possible "give me a file path, get back structured analysis" skill — a deliberate baseline for any skill that processes tabular data locally without an LLM in the loop.

Verify that the geoai Python package is installed and functional. If not, provide installation instructions. Optionally check extra dependencies for deep learning models.

Routes engineering requests to the correct specialist based on technology domain, task type, and stack involved. Covers backend, frontend, mobile, fullstack, embedded, blockchain, ML/AI, QA, architecture, and technical documentation. Triggers: build feature, write code, implement, develop, api, component, mobile app, ios, android, react, vue, node, python, smart contract, machine learning, system

Create MCP servers — multi-tool services exposed via Model Context Protocol. Use this skill whenever users mention MCP servers, building servers, server scaffolding, tool registration, or want to package tools for distribution via uvx or npx. Also use when the conversation involves stdio transport, server lifecycle, or grouping multiple related tools into a service. Covers Python (FastMCP) and Typ

Componha sistemas multiagente com SequentialAgent, ParallelAgent e LoopAgent. Utilize ao construir pipelines de agentes, fluxos de trabalho paralelos ou loops iterativos.

Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.