Explorar skills

Provides step-by-step templates and guidance for creating new AI agents in Unite-Hub with proper registration, testing, and governance

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Visualize datasets in 2D using embeddings with UMAP or t-SNE dimensionality reduction. Use when users want to explore dataset structure, find clusters in images, identify outliers, color samples by class or metadata, or understand data distribution. Requires FiftyOne MCP server with @voxel51/brain plugin installed.

Consulta o clima da China usando dados públicos nacionais de fontes oficiais como nmc.cn, weather.cma.cn e weather.com.cn. Oferece condições em tempo real, previsões, alertas e qualidade do ar, auxiliando usuários a avaliar riscos climáticos para viagens, deslocamentos e outras atividades.

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven workflow, step function, durable execution.

Implements code changes and creates commits. Triggered when: implementation tasks, code changes, feature additions, bug fixes.

Hreflang and international SEO audit, validation, and generation. Detects common mistakes, validates language/region codes, and generates correct hreflang implementations. Use when user says "hreflang", "i18n SEO", "international SEO", "multi-language", "multi-region", or "language tags".

Create clever, non-offensive trash talk. Rivalry-specific references, historical callbacks, memes. Fun, not mean.

Adiciona um novo projeto de código aberto ao pipeline de marketing. Pesquisa a dor real do usuário, detecta automaticamente o tipo de projeto e gera tudo.

Consensus cell type annotation: runs 10+ algorithms (KNN-Harmony/BBKNN/Scanorama/scVI, CellTypist, ONCLASS, Random Forest, SCANVI, SVM, XGBoost) on a labeled reference and transfers labels via majority voting. Outputs per-method labels, consensus, agreement score. Use when single-method annotation is insufficient or you need ensemble uncertainty for novel states.

Creates Claude Code hooks for automation and workflow customization. Guides through hook events, configuration, and script creation. Use when user wants to create a hook, automate Claude Code, or asks about hook events.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.