mosaic-ai-agent
Expert guidance for building production-ready tool-calling agents with Databricks Mosaic AI Agent Framework. Use when users need to create agents that orchestrate multiple data sources or APIs, implement LangChain-based agentic workflows, design Foundation Model-powered tool selection, optimize agent prompts and decision-making, or architect multi-tool agent systems. Covers agent architecture patterns, tool design best practices, Foundation Model integration, and common pitfalls.
npx skills add majiayu000/claude-skill-registry --skill mosaic-ai-agent --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Mosaic AI Agent Builder Build production-ready tool-calling agents that intelligently orchestrate data sources and APIs using Databricks Foundation Models and LangChain. ## Core Concepts ### What is a Tool-Calling Agent? A tool-calling agent uses an LLM to: 1. Understand user intent 2. Decide which tool(s) to call 3. Execute selected tools 4. Synthesize results into a response **Key advantage:** Dynamic routing - the LLM adapts to each query instead of following rigid logic. ### When to Use Agents vs. Direct LLM Calls **Use agents when:** - Query complexity varies (some need 1 tool, others need 3+) - Tool selection depends on nuanced intent - You need multi-step reasoning - Tools can be composed in different ways **Use direct LLM calls when:** - Single, predictable tool usage - Deterministic routing logic - Low latency is critical - Cost optimization is paramount ## Problem-Solution Patterns ### Problem 1: Agent Calls Wrong Tools **Symptoms:** - Agent uses web search instead of internal data source - Calls inventory tool for customer behavior questions - Skips relevant tools entirely **Root causes:** - Vague tool descriptions - Overlapping tool responsibilities - Insufficient exa
- Core Concepts
- What is a Tool-Calling Agent?
- When to Use Agents vs. Direct LLM Calls
- Problem-Solution Patterns
- Problem 1: Agent Calls Wrong Tools
- Problem 2: Agent Gets Stuck in Loops
- Problem 3: Poor Multi-Tool Synthesis
- Problem 4: Slow Agent Response Times
- Agent Architecture Patterns
- Pattern 1: Single-Domain Agent
- Pattern 2: Multi-Domain Agent
- Pattern 3: Specialized Sub-Agents
- Foundation Model Selection
- Model Comparison for Agents
What does the mosaic-ai-agent skill do?
Expert guidance for building production-ready tool-calling agents with Databricks Mosaic AI Agent Framework. Use when users need to create agents that orchestrate multiple data sources or APIs, implement LangChain-based agentic workflows, design Foundation Model-powered tool selection, optimize agent prompts and decision-making, or architect multi-tool agent systems. Covers agent architecture patterns, tool design best practices, Foundation Model integration, and common pitfalls.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill mosaic-ai-agent --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.