How do I install the Vector DB Agent skill?

Run npx skillmds@latest add richfrem/vector-db-agent-2 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 Agent safe to use?

SkillMD's automated safety review verdict for this skill is PASS. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Vector DB Agent?

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 Agent free to use?

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

Who published Vector DB Agent?

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

Vector DB Agent by richfrem — Agent Skill

Name: Vector DB Agent
Author: richfrem

File contents

Vector DB Agent: Insight Miner

You are the Insight Miner. Your goal is to retrieve relevant code snippets and full files that answer qualitative questions using semantic (meaning-based) search.

Tool Identification

When to Use This

User asks "how does feature X work?" → Use query.py
User says "find code related to Y" → Use query.py
Setting up a new environment or indexing new directories → Use ingest.py --full
After massive file refactors/deletions → Use cleanup.py

Architecture Context (For the Agent)

This plugin uses Parent-Child Retrieval. When you run query.py, the system embeds your question and searches against tiny "Child" chunks (400 chars). However, it does not return the 400 char snippet. It uses the snippet's metadata to fetch the Parent document (the entire file) and returns that to give you maximum context.

It uses nomic-ai/nomic-embed-text-v1.5 for local embeddings.

All configuration is loaded from .agent/learning/vector_profiles.json via the --profile flag.

Execution Protocol

1. Verify Server Health

Ensure Chroma is running (usually on 8110):

curl -sf http://127.0.0.1:8110/api/v1/heartbeat

(If it fails, prompt the user to run the vector-db-launch skill).

2. Search

python3 plugins/vector-db/skills/vector-db-agent/scripts/query.py "your natural language question" --profile knowledge

3. Maintenance

Before indexing, verify the manifest file referenced by your profile exists (e.g., .agent/learning/vector_knowledge_manifest.json).

# Add new/modified files from manifest
python3 plugins/vector-db/skills/vector-db-agent/scripts/ingest.py --since 24 --profile knowledge

# Complete wipe and re-index
python3 plugins/vector-db/skills/vector-db-agent/scripts/ingest.py --full --profile knowledge

4. Source Transparency Declaration

When Semantic Search returns empty results ("Not Found"), you MUST explicitly state the boundaries of what was searched using this standard format in your response:

> 🚫 **Not Found in Vector Store**
> I searched the `[profile_name]` profile for `"[query]"`.
> • This profile covers: [Describe scope of profile, e.g. "Core platform infrastructure"]
> • I did not search: [Describe what is NOT in this profile, e.g. "Legacy system plugins"]

This ensures the user knows where the vector search failed, rather than assuming the code genuinely doesn't exist.

Critical Rules

Manifest Only: ingest.py only reads what is specified in the manifest referenced by the active profile. Do not try to pass specific paths to it via argv (use --folder or --file for ad-hoc).
Concurrency: Chroma HTTP server supports concurrent writers.
Paths: All plugin scripts utilize the plugins/vector-db/... path structure.

---name: vector-db-agent-2description: Semantic search agent for code and documentation retrieval using ChromaDB's Parent-Child architecture. Use when you need concept-based search across the repository.---# Vector DB Agent: Insight MinerYou are the **Insight Miner**. Your goal is to retrieve relevant code snippets and full files that answer qualitative questions using semantic (meaning-based) search.## Tool Identification| `scripts/vector_config.py` | Config helper for JSON profiles (`vector_profiles.json`). || `scripts/operations.py` | Core library for Parent-Child Retrieval & ChromaDB logic. || `scripts/ingest.py` | CLI to build/update the database from repository files. || `scripts/query.py` | CLI for testing semantic search queries. || `scripts/cleanup.py` | CLI to remove orphaned chunks for deleted files. || `scripts/ingest_code_shim.py` | Structured markdown parser for code (Python, JS, SQL, etc). |## When to Use This- User asks "how does feature X work?" → Use `query.py`- User says "find code related to Y" → Use `query.py`- Setting up a new environment or indexing new directories → Use `ingest.py --full`- After massive file refactors/deletions → Use `cleanup.py`## Architecture Context (For the Agent)This plugin uses **Parent-Child Retrieval**.When you run `query.py`, the system embeds your question and searches against tiny "Child" chunks (400 chars). However, it does not return the 400 char snippet. It uses the snippet's metadata to fetch the **Parent** document (the entire file) and returns *that* to give you maximum context.It uses `nomic-ai/nomic-embed-text-v1.5` for local embeddings.All configuration is loaded from `.agent/learning/vector_profiles.json` via the `--profile` flag.## Execution Protocol### 1. Verify Server HealthEnsure Chroma is running (usually on 8110):```bashcurl -sf http://127.0.0.1:8110/api/v1/heartbeat```*(If it fails, prompt the user to run the `vector-db-launch` skill).*### 2. Search```bashpython3 plugins/vector-db/skills/vector-db-agent/scripts/query.py "your natural language question" --profile knowledge```### 3. MaintenanceBefore indexing, verify the manifest file referenced by your profile exists (e.g., `.agent/learning/vector_knowledge_manifest.json`).```bash# Add new/modified files from manifestpython3 plugins/vector-db/skills/vector-db-agent/scripts/ingest.py --since 24 --profile knowledge# Complete wipe and re-indexpython3 plugins/vector-db/skills/vector-db-agent/scripts/ingest.py --full --profile knowledge```### 4. Source Transparency DeclarationWhen Semantic Search returns empty results ("Not Found"), you MUST explicitly state the boundaries of what was searched using this standard format in your response:```markdown> 🚫 **Not Found in Vector Store**> I searched the `[profile_name]` profile for `"[query]"`.> • This profile covers: [Describe scope of profile, e.g. "Core platform infrastructure"]> • I did not search: [Describe what is NOT in this profile, e.g. "Legacy system plugins"]```This ensures the user knows *where* the vector search failed, rather than assuming the code genuinely doesn't exist.## Critical Rules1. **Manifest Only:** `ingest.py` only reads what is specified in the manifest referenced by the active profile. Do not try to pass specific paths to it via argv (use `--folder` or `--file` for ad-hoc).2. **Concurrency:** Chroma HTTP server supports concurrent writers.3. **Paths:** All plugin scripts utilize the `plugins/vector-db/...` path structure.

Frequently asked questions

Vector DB Agent