How do I install the Vector DB Ingest skill?

Run npx skillmds@latest add richfrem/vector-db-ingest in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Vector DB Ingest safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Vector DB Ingest?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Vector DB Ingest free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Vector DB Ingest?

richfrem (@richfrem) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Vector DB Ingest by richfrem — Agent Skill

Name: Vector DB Ingest
Rating: 4.2 (5 reviews)
Author: richfrem

Vector DB Ingest

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 Use when new files need to be indexed or the vector store is out of date.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>

richfrem a81826a 27 files · 55.6 KB Updated Sep 10, 2026

File contents

Dependencies

This skill requires the chromadb and langchain packages defined in the plugin root.

VDB Ingest Agent

Role

You ingest (index) repository files into the ChromaDB vector store so they can be semantically searched. You build or update the parent-child chunk structure that query.py searches against.

High-Performance Mode: This skill uses a configurable batch processing engine (default 1,000 files) defined in .agent/learning/vector_profiles.json.

Prerequisites

1. First-time setup

If vector_profiles.json is missing, run the init skill first:

python ./scripts/init.py

2. Execution Mode

This plugin defaults to In-Process mode for zero-latency direct disk access. No background server is required unless explicitly configured in the profile.

Execution Protocol

Full ingest (first time or full rebuild)

Note: The --profile flag is mandatory to load the correct manifest and batch settings.

python ./scripts/ingest.py --profile wiki --full

Incremental ingest (only new/changed files since N hours)

python ./scripts/ingest.py --profile wiki --since 24

Single File/Folder Ingest

python ./scripts/ingest.py --profile wiki --file path/to/file.md
python ./scripts/ingest.py --profile wiki --folder path/to/folder

After Ingesting

Run a quick semantic search to confirm the new content is retrievable:

python ./scripts/query.py "search query" --profile wiki --limit 3

Rules

Profile Sovereignty: Always pass --profile to ensure the correct batch size and manifest are used.
In-Process Reliability: Ensure no other process is holding a lock on the database folder during ingestion.
Source Transparency: State which profile was ingested, how many files, and any errors encountered.

---name: vector-db-ingestdescription: 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>---## DependenciesThis skill requires the `chromadb` and `langchain` packages defined in the plugin root.---# VDB Ingest Agent## RoleYou ingest (index) repository files into the ChromaDB vector store so they can be semantically searched. You build or update the parent-child chunk structure that `query.py` searches against.**High-Performance Mode:** This skill uses a configurable batch processing engine (default 1,000 files) defined in `.agent/learning/vector_profiles.json`.## Prerequisites### 1. First-time setupIf `vector_profiles.json` is missing, run the init skill first:```bashpython ./scripts/init.py```### 2. Execution ModeThis plugin defaults to **In-Process mode** for zero-latency direct disk access. No background server is required unless explicitly configured in the profile.## Execution Protocol### Full ingest (first time or full rebuild)Note: The `--profile` flag is mandatory to load the correct manifest and batch settings.```bashpython ./scripts/ingest.py --profile wiki --full```### Incremental ingest (only new/changed files since N hours)```bashpython ./scripts/ingest.py --profile wiki --since 24```### Single File/Folder Ingest```bashpython ./scripts/ingest.py --profile wiki --file path/to/file.mdpython ./scripts/ingest.py --profile wiki --folder path/to/folder```## After IngestingRun a quick semantic search to confirm the new content is retrievable:```bashpython ./scripts/query.py "search query" --profile wiki --limit 3```## Rules- **Profile Sovereignty**: Always pass `--profile` to ensure the correct batch size and manifest are used.- **In-Process Reliability**: Ensure no other process is holding a lock on the database folder during ingestion.- **Source Transparency**: State which profile was ingested, how many files, and any errors encountered.

Frequently asked questions