vector-db

Remove stale chunks from deleted or renamed files in the vector database

Ingest repository files into the local ChromaDB vector store for semantic search

Search the vector database for semantically relevant code and documentation

../skills/vector-db-init/SKILL.md

../skills/vector-db-launch/SKILL.md

../skills/vector-db-search/SKILL.md

../skills/vector-db-cleanup/SKILL.md

../skills/vector-db-ingest/SKILL.md

Removes stale and orphaned chunks from the ChromaDB vector store for files that have been deleted or renamed. Use after files are removed or moved to keep the vector index in sync with the filesystem. <example> user: "Clean up the vector store after I deleted some files" assistant: "I'll use vector-db-cleanup to remove orphaned chunks." </example> <example> user: "The vector database has chunks for files that no longer exist" assistant: "I'll run vector-db-cleanup to prune them." </example>

Ingests repository files into the ChromaDB vector store. Builds or updates the vector index from a manifest or directory scan using ingest.py. Use when new files need to be indexed or the vector store is out of date. <example> user: "Index these new plugin files into the vector database" assistant: "I'll use vector-db-ingest to add them to the vector store." </example> <example> user: "The vector store is missing recent files -- update it" assistant: "I'll use vector-db-ingest to re-index the changes." </example>

Interactively initializes the Vector DB plugin. Installs the required pip dependencies (chromadb, langchain wrappers) and configures the vector_profiles.json for Native Python Server connections. Run this before attempting to use the vector-db-search or vector-db-launch skills.

Start the Native Python ChromaDB background server. Use when semantic search returns connection refused on port 8110, or when the user wants to enable concurrent agent read/writes.

Semantic search skill for retrieving code and documentation from the ChromaDB vector store. Use when you need concept-based search across the repository (Phase 2 of the 3-phase search protocol). V2 includes L4/L5 retrieval constraints.