lima-sandbox-testing
Run Claude Code integration tests in isolated Lima VM sandboxes. Use for E2E testing, hook validation, session survival tests, and any scenario requiring isolated Claude execution.
Run Claude Code integration tests in isolated Lima VM sandboxes. Use for E2E testing, hook validation, session survival tests, and any scenario requiring isolated Claude execution.
Auxilia desenvolvimento do chat NathIA no projeto Nossa Maternidade. Conhece a arquitetura de agentes IA (MaternalChatAgent, EmotionAnalysisAgent), MCP servers (Supabase, GoogleAI, OpenAI, Anthropic), e prompts. Use ao trabalhar com chat, agentes IA, ou integracao Gemini.
Core skill activation protocol - establishes mandatory workflows for finding and applying skills before any task
Training data management including labeling strategies, data augmentation, handling imbalanced data, and data splitting best practices.
Implement agent memory - short-term, long-term, semantic storage, and retrieval
Agent memory architecture including working, short-term, long-term, and temporal knowledge graphs.
Defines behavioral standards for autonomous agents and enforces Uninterrupted Flow, Self-Verification, Auth-Gates, and Handoff protocols. PROACTIVELY Use when defining behavioral standards for autonomous agents or enforcing protocols. Internal-only reference for agent behavior.
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
Systematic vulnerability finding, threat modeling, and attack surface analysis for AI/LLM security assessments
Single-skill vs multi-skill subagent architectures. Use when designing subagents.
Activate the Recursive Thought Committee multi-persona framework.
Orchestrate end-to-end processing of D&D session videos from upload through knowledge extraction. Use when the user wants a complete automated workflow to process a new session recording.
Conversation phases, topic drift, and convo-exit protocols
GitHub Copilot Skill 與 Agent 設計指導技能,協助開發者設計與實作高品質的 Skill 和 Agent,包含架構設計、最佳實踐、工作流程規劃與常見反模式識別。
Design computational models for cognitive simulation and analysis.
Create skills using the agentskills.io framework with init, validate, and package scripts. Use when users want to create distributable .skill packages, use the init_skill.py scaffolding, or follow the agentskills.io workflow with scripts, references, and assets directories.
Use when facing 3+ independent tasks that can be completed without shared state or dependencies - dispatches multiple agents to work concurrently on summarization, investigation, implementation, or analysis
指南:创建高质量的 MCP(模型上下文协议)服务器,使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用,无论是 Python(FastMCP)还是 Node/TypeScript(MCP SDK)。
Create and scaffold new agent skills with proper structure, validation, and spec compliance. Use when building new skills from scratch.
Foundational Cypher (Neo4j) patterns covering graph pattern matching, MATCH/CREATE/MERGE/DELETE operations, relationships, path patterns, aggregation, filtering, and common graph query patterns. Use when writing Cypher queries, modeling graph data, or needing guidance on graph database operations. This is the entry point for Cypher development.
Deploy ML models to production - APIs, containerization, monitoring, and MLOps
Expert knowledge for Technology Layer modeling in Documentation Robotics