Optimize ElevenLabs conversational AI agents for real estate applications. Use when creating new agents, improving conversation quality, selecting voices, engineering system prompts, configuring agent parameters, or analyzing agent performance metrics. Includes voice selection, model tuning, prompt engineering, and A/B testing strategies.
Offline Claude Code documentation fallback. Use when the user asks about Claude Code features, capabilities, or configuration and the built-in claude-code-guide subagent fails due to network issues or proxy blocking.
Coordinate multiple AI agents and skills for complex workflows
GitHub CLI commands optimized for AI agent workflows with JSON output and deterministic execution patterns.
Expert backend development guidance covering Node.js, Python, Java, Go, API design (REST/GraphQL/gRPC), database patterns, authentication, caching, message queues, microservices, and testing. Produces production-ready, scalable, and secure backend code with industry best practices. Use when building APIs, implementing business logic, designing data models, integrating services, or when users mention backend development, server-side code, APIs, databases, or microservices.
Analyzes recent conversation history using chat tools to identify recurring workflow patterns and generate Custom Skills recommendations with statistical rigor. Use when users request workflow analysis, pattern identification, skill generation suggestions, or automation opportunities based on their AI usage patterns without requiring conversation exports.
Workflow patterns and gotchas for OpenAI Agents SDK. Directs to RAG for implementation.
Use when creating specialized sub-agents with domain expertise, proper YAML formatting, and clear scope boundaries. Follows Guild system's dynamic specialist creation patterns.
Domain knowledge for Physical AI, ROS 2, and Humanoid Robotics.
Enterprise Alfred Proactive Suggestions with AI-powered intelligent assistance, Context7 integration, and intelligent recommendation orchestration for enhanced productivity
Guide AI agents through Dify tool plugin development with mandatory documentation loading and direct CLI usage. Use when creating Dify tool plugins or extending Dify with custom tools.
This skill should be used when users want to build LLM-powered applications using LangChain. It provides patterns for initializing any LLM provider (OpenAI, Anthropic, Google, xAI), building agent loops with tools, and implementing structured output. Use this skill when users ask to create chatbots, AI agents, or applications that need LLM integration with tool calling or structured responses.
This skill should be used when the user asks about "visual builder", "no-code agent builder", "drag and drop", "ThinkingConfig", "extended thinking", "chain of thought", "reasoning", or needs guidance on using ADK's visual development tools or configuring advanced reasoning capabilities.
MANDATORY invocation for ALL LLM-related work. Invoke immediately when: - ANY mention of model names, IDs, or versions - ANY configuration of AI providers or APIs - ANY defaults/constants for LLM settings - ANY prompt engineering or modification - ANY discussion of model capabilities or features - ANY changes to AI-related dependencies - Reading/writing .env files with AI config - Modifying aiProviders.ts, prompts.ts, or similar - Reviewing AI-related pull requests - Debugging LLM integration issues CRITICAL: Training data lags reality by months. ALWAYS research first. Use WebSearch, Exa MCP, or Gemini CLI before making ANY LLM decisions.
Multi-level caching strategies for LLM applications - semantic caching (Redis), prompt caching (Claude/OpenAI native), cache hierarchies, cost optimization, and Langfuse cost tracking with hierarchical trace rollup for 70-95% cost reduction
Multi-Agent Orchestration skill for coordinating AI agents across channels, managing sessions, distributing tasks, and leveraging distributed compute resources.
