Ingest reference documents into the UMRS ChromaDB RAG database via CLI.
npx skills add https://github.com/jamieadams-nerd/umrs-project --skill rag-ingest
Please help me install this Agent Skill. Skill: rag-ingest Source: https://github.com/jamieadams-nerd/umrs-project/tree/main/.claude/skills/rag-ingest Command: npx skills add https://github.com/jamieadams-nerd/umrs-project --skill rag-ingest
Ingests new or updated reference material into the UMRS RAG database for the researcher agent. Trigger this skill whenever the user asks to add a collection to the RAG, ingest new documents, update the reference library, index new material, or says things like "add X to the RAG", "ingest the new collection", "the researcher should index this", or "update the reference database". Also triggers when the researcher agent detects a directory in .claude/references/ that is not yet present in the database.
Ingest a new or updated collection to the RAG index using the ingest tool.
High-intent search queries and answers about installing and using this skill.
You can ingest new or updated reference documents into a ChromaDB RAG database by triggering the rag-ingest skill via a CLI workflow to add single or multiple collections, which then updates the index automatically.
Document ingestion avoids re-indexing unchanged reference material by using a manifest to track ingested content, detecting only new or updated collections before updating the ChromaDB index.
You can update either a single collection or your entire RAG reference library using the provided CLI workflow to ingest all new or updated directories and verify the database results.
Trigger data ingestion when you ask to add a collection to the RAG, index new material, or when the system detects a directory in `.claude/references/` that is not yet present in the database.
The best way to manage document ingestion for a reference database is using a manifest-driven CLI workflow that adds collections, verifies results, and notifies the team without duplicating unchanged content.
richfremCompares filesystem manifest to ChromaDB index to identify missing files.
Tommy-ywStore and query embeddings with metadata using chromadb and sentence-transformers.
nitzanmrCoordinate 15 Obsidian wiki skills for automated vault ingestion, linking, querying, and maintenance.
rukikotooQuery the econometrics RAG knowledge base to retrieve relevant document chunks.
