Create and update ai-context.md files that document modules for AI assistants. Use when adding documentation for packages, apps, or external references that should be discoverable via /modules commands.
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.
Take a ScienceWorld action in the active session. Returns observation, reward, done. No session_id needed - uses active session from executive_node.
Perform security audits on Agent Skills from a given path. Use when the user asks to audit, review, check security, or verify a skill for security issues.
LiteLLM-RS A2A Protocol Architecture. Covers Agent-to-Agent communication, JSON-RPC 2.0 messaging, multi-provider orchestration, agent registry, and task state management.
Search past Claude Code conversations. Use when user says "search conversations", "find that chat", "what did we discuss", "where did we talk about", "look up past session", "find conversation about X", "search history", "what did I ask about", "remember when we", "that discussion about". Also triggers on past-tense questions referencing prior work or possessives without context.
LiteLLM-RS Configuration Architecture. Covers YAML loading, environment variable override, validation patterns, type-safe config models, and hot reloading.
LiteLLM-RS Provider 开发与架构指南。用于添加新 provider、迁移错误处理、维护 66+ provider 的一致性。包含架构对比分析和最佳实践。
Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.
LiteLLM-RS Routing Architecture. Covers 7 routing strategies, lock-free design with DashMap, health-aware selection, fallback chains, and load balancing.
Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.
Configure and compose AI provider layers using @effect/ai packages. Covers Anthropic, OpenAI, OpenRouter, Google, and Amazon Bedrock providers with config management, model abstraction, and runtime overrides for language model integration.
LiteLLM-RS Error Handling Architecture. Covers two-tier error hierarchy, ProviderError factory methods, HTTP status mapping, retry logic, and error context preservation.
Implements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling interrupts, or creating multi-agent systems with LangGraph.
LiteLLM-RS Provider Architecture Guide. Covers 66+ provider integration, trait object design, unified error handling, connection pooling, and LLMProvider trait implementation patterns.
A simple example skill that demonstrates Claude Code skill structure
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.
Defines the shared role, responsibilities, and operating principles for an Executive agent in the b00t hive. This skill uses Rhai scripting to provide model-specific directives.
Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Apply Tit for Tat strategy for negotiations, relationships, and repeated interactions. Use when navigating workplace dynamics, building partnerships, handling conflicts, or designing systems with reciprocal interactions.
