Explorar skills

Pesquise no GitHub por skills, plugins e agentes do Claude Code. Use quando o usuário pedir para encontrar ou listar skills da comunidade, ou perguntar "quais skills existem para X" (ex: SEO, testes, deploy, conteúdo).

Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.

Parallel multi-agent code review using Agent Teams with 4 specialized reviewers. Spawns a coordinated team of security, performance, test coverage, and code quality agents. Teammates can share findings with each other for cross-domain insights. Produces unified report with severity-ranked findings saved to /output/. Requires Claude Code with Agent Teams support (TeamCreate, TaskCreate, SendMessage

Multi-machine fleet operations — SSH key management, cross-host syncing, Ansible playbook execution, fleet health checks, and inventory management. Trigger on: "fleet", "SSH to", "sync to node_gpu", "sync to node_primary", "cross-host", "deploy to", "rsync", "fleet health", "all machines", "inventory", or any task involving coordination between node_primary, node_gpu, node_miner, or future hosts.

数仓自测流程，适用于通过 data-quality-checker subagent 执行 23 项标准自测并只返回摘要。直接调用命令：/dw-self-test。

Cross-functional what-if modeling for cascading multi-variable scenarios. Unlike single-assumption stress testing, this models compound adversity across all business functions simultaneously. Use when facing complex risk scenarios, strategic decisions with major downside, or when the user asks 'what if X AND Y both happen?'

Distributed Claude Code coordination v2 — autonomous multi-instance orchestration via NFS + git. Agent registry with heartbeat, priority work queue with capability matching, event bus for cross-agent context, auto git sync, GPU slot management, session lifecycle protocol. Replaces OpenClaw for self-hosted agent coordination.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Integra o QPay, o principal sistema de pagamento QR da Mongólia, em projetos de desenvolvedores para aceitar pagamentos MNT via Khan Bank, Golomt, State Bank, Xac Bank e outros bancos mongóis.

Gera cartas comerciais em PDF, compatíveis com a norma DIN 5008. Opcionalmente, envia via API LetterXpress Print-and-Mail (modo de teste).

TDD knowledge base — testing practices, coding practices, and implementation patterns. Loaded by SDM workflow agents (sw-engineer, test-agent, developer) for behavioral testing guidance and production-grade coding standards.

Esta skill é uma camada de adaptação para operações de navegador MCP, fornecendo configurações e playbooks. Ela permite que Claude use ferramentas mcp__playwright__browser_* para abrir o navegador, interagir e tirar screenshots, sendo ativada por solicitações do usuário ou outras skills para verificação.