Automação

Step-by-step agent sequences for all six Lumen workflows (W1–W6). Reference when routing a workflow to understand which agents run, in what order, and what gates apply.

Coordinate multiple agents on complex game development features using battle-tested spawn recipes. Triggers on: "multi-agent coordination", "team orchestration", "feature handoff", "cross-domain collaboration", or when a task spans multiple specialist domains (combat system, narrative feature, UI overhaul, performance pass, launch prep). Do NOT invoke for single-domain tasks -- route directly to t

Orchestrator role in the Unfolding Specs process. Launches the PO, forwards unsolicited Sensei guidance, handles genuine commissioner issues, and resumes the workflow through the platform-specific live task mechanism.

Audita e otimiza artefatos de direcionamento do Claude conforme 189 regras da Anthropic em 11 dimensões, calibrado por modelo. Cada descoberta inclui citação exata e URL da fonte, preservando a voz autoral.

Scan Python projects for credential leaks, secrets in code, insecure patterns, LLM API key exposure, PII leakage to external AI services, and .env/.gitignore misconfigurations. Focused on data science pipelines handling API keys, tokens, and LLM integrations.

Knowledge Graph entity types and relationships (v2.2)

Step-by-step guide for building Web Audio processing pipelines — AudioWorklet processors, custom nodes, parameter automation, and WebMIDI integration. Use when the user asks how to build or wire up Web Audio code from scratch. Trigger on phrases like "build an AudioWorklet", "create a custom Web Audio effect", "how do I use WebMIDI", "how do I write an AudioWorkletProcessor", or "how do I connect

Hub orchestration patterns for multi-agent workflows. Use when processing delegation requests from agents, coordinating sequential/parallel agent execution, and aggregating results. Provides the protocol for agent-to-agent communication through the hub.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Apply these opinionated testing conventions when writing tests or test strategies: three modes (functional, performance, security), unit/integration/E2E patterns, coverage analysis, automation frameworks, defect tracking, accessibility and usability.

Esta skill oferece regras e exemplos para adicionar métricas Sentry corretamente, incluindo convenções de nomenclatura, práticas de tagging seguras, rastreamento de falhas com tipos de erro predefinidos e implementação de métricas para rotas HTTP, chamadas de API, etapas de fluxo de trabalho, retentativas e caminhos de fallback.

Invoque quando o usuário deseja prototipar rapidamente uma mecânica, testar uma prova de conceito, realizar desenvolvimento guiado por hipóteses ou validar uma ideia de jogo antes da produção completa.