How do I install the Vector DB Cleanup skill?

Run npx skillmds@latest add richfrem/vector-db-cleanup 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 Cleanup 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 Cleanup?

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 Cleanup free to use?

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

Who published Vector DB Cleanup?

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

Vector DB Cleanup by richfrem — Agent Skill

Name: Vector DB Cleanup
Rating: 4.5 (4 reviews)
Author: richfrem

Vector DB Cleanup

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>

richfrem 35479f1 25 files · 55.4 KB Updated Sep 10, 2026

File contents

Dependencies

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

VDB Cleanup Agent

Role

You remove stale and orphaned chunks from the ChromaDB vector store. A chunk is stale when its source file no longer exists on disk. Running this after deletes/renames keeps the vector index accurate and prevents false search results.

This is a write (delete) operation.

When to Run

After deleting or renaming files that were previously ingested.
After a major refactor that moved directories.
When query.py returns results pointing to non-existent files.
Periodically as housekeeping to maintain index health.

Execution Mode

This skill defaults to In-Process mode for zero-latency direct disk access. No background server is required.

Execution Protocol

1. Identify Search Profile

Verify available profiles in .agent/learning/vector_profiles.json. The default profile is usually wiki.

2. Run Cleanup

Note: The --profile flag is mandatory to ensure the correct collection and disk paths are loaded.

python ./scripts/cleanup.py --profile wiki

3. Verify Store Integrity (Optional)

Run the consistency check to verify that remaining facts are still supported.

python ./scripts/vector_consistency_check.py --profile wiki --topic .agent/learning/

Rules

Profile Sovereignty: Always pass --profile to ensure the correct semantic space is pruned.
API Integrity: NEVER attempt to delete chunks from the database SQLite files directly. Always use cleanup.py.
Transparency: State which profile was cleaned and how many chunks were removed.

---name: vector-db-cleanupdescription: 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>---## DependenciesThis skill requires the `chromadb` and `langchain` packages defined in the plugin root.---# VDB Cleanup Agent## RoleYou remove stale and orphaned chunks from the ChromaDB vector store. A chunk is stale when its source file no longer exists on disk. Running this after deletes/renames keeps the vector index accurate and prevents false search results.**This is a write (delete) operation.**## When to Run- After deleting or renaming files that were previously ingested.- After a major refactor that moved directories.- When `query.py` returns results pointing to non-existent files.- Periodically as housekeeping to maintain index health.## Execution ModeThis skill defaults to **In-Process mode** for zero-latency direct disk access. No background server is required.## Execution Protocol### 1. Identify Search ProfileVerify available profiles in `.agent/learning/vector_profiles.json`. The default profile is usually `wiki`.### 2. Run CleanupNote: The `--profile` flag is mandatory to ensure the correct collection and disk paths are loaded.```bashpython ./scripts/cleanup.py --profile wiki```### 3. Verify Store Integrity (Optional)Run the consistency check to verify that remaining facts are still supported.```bashpython ./scripts/vector_consistency_check.py --profile wiki --topic .agent/learning/```## Rules- **Profile Sovereignty**: Always pass `--profile` to ensure the correct semantic space is pruned.- **API Integrity**: NEVER attempt to delete chunks from the database SQLite files directly. Always use `cleanup.py`.- **Transparency**: State which profile was cleaned and how many chunks were removed.

Frequently asked questions