Claude Code skills for AI agent builders
Build agents that route work correctly, fall back gracefully, and don’t get locked into one harness.
Agent builders use Loreto skills to route queries to the right store, define fallback behavior when retrieval is empty, and route work across the right AI harness.
Skills to start with
Agentic RAG Fallback
Designs a Retrieve-Check-Route fallback pattern for agentic (multi-tool) RAG systems so that when every retriever tool…
Agentic RAG Routing
Designs an agentic RAG architecture where an LLM agent acts as a dynamic router, semantically selecting the correct dom…
Detecting Harness Lockin
Identifies and quantifies the compounding switching cost of an AI coding agent harness commitment before it becomes inv…
RAG Pipeline Vector DB
Designs a traditional RAG pipeline organized around the Query-Retrieve-Augment-Generate (QRAG) flow and its single-LLM-…
RAG Pipeline Vector Store
Designs a baseline single-hop RAG pipeline that grounds LLM answers in private or domain-specific documents via vector…
RAG Query Routing
Designs and implements LLM-backed query routing across multiple domain-specific vector stores using the retriever-tool…
RAG Relevance Fallback
Designs a conditional fallback branch in a single-store RAG pipeline so that when retrieved documents are irrelevant or…
Routing Work Across AI Harnesses
Designs hybrid agent workflows that route tasks intelligently between AI coding agent harnesses based on task character…
Your workflow, as a skill
Loreto turns what you already know into a Claude Code skill your agent can run on demand.