# vector-store-stinger

vector-store-stinger is a skill for choosing pgvector, Deep Lake, or Qdrant, configuring indexes, and planning migrations for projects storing embeddings.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 96 repo stars
- Author: Legion Code Inc.
- License: AGPL-3.0-or-later · policy=link-only · description only; the file stays with the author
- Source: https://github.com/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/data-and-ai-tools/skills/vector-store-stinger/SKILL.md
- Updated: 2026-10-18
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/vector-store-stinger

## What it does

vector-store-stinger covers the full lifecycle of vector data: greenfield store selection, schema design, index tuning, and migration planning. The skill references guides for pgvector with Drizzle (the default for this repository), Deep Lake as an option for existing projects, and Qdrant or managed services like Pinecone.

It enforces hard rules that prevent common mistakes: embedding dimension is a schema constraint, not a runtime detail; operator class must match the distance metric; every migration is broken into steps. For pgvector, separate guides cover Drizzle schemas, indexing, hybrid search (vector plus full-text), and migrations.

The skill does not handle security audits, credential storage, or embedding generation—those are delegated to other skills. PostgreSQL with the `pgvector` extension or your chosen alternative store is required to function.

## Requirements
- Works with: PostgreSQL

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add legioncodeinc/vibe-coding-tools
```
In the agent chat (not a shell):
```text
/plugin install data-and-ai-tools@wasp-nest
```
This installs the whole data-and-ai-tools plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill vector-store-stinger -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/vector-store-stinger/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/vector-store-stinger/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill vector-store-stinger -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/vector-store-stinger/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill vector-store-stinger -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/vector-store-stinger/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install legioncodeinc/vibe-coding-tools plugins/data-and-ai-tools/skills/vector-store-stinger
```

2. **Manually: put the files in place**
- File: `.github/skills/vector-store-stinger/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill vector-store-stinger -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/legioncodeinc/vibe-coding-tools --path plugins/data-and-ai-tools/skills/vector-store-stinger
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/vector-store-stinger/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/data-and-ai-tools/skills/vector-store-stinger/SKILL.md

## When to use it
- select a vector store for a new project with embeddings
- design a Drizzle schema with a vector column in PostgreSQL
- choose and configure HNSW or IVFFlat indexes
- plan and execute a migration when dimension or index type changes
- build hybrid search combining full-text and vector queries

## Example prompts
- Help me pick a vector store: my project runs Postgres already, but I'm not sure whether pgvector or Qdrant fits better.
- Design a `documents` table with a 1536-dimensional vector column and recommend an index for fast retrieval.
- Write a migration that adds hybrid search using both `tsvector` and vector columns with fusion ranking.

## Similar
- [langchain4j-vector-stores-configuration](https://affpapa.org/en/nevibecode/skills/langchain4j-vector-stores-configuration.md) — skill · 3900 installs
- [vector-database-ops](https://affpapa.org/en/nevibecode/skills/vector-database-ops.md) — skill · 345 installs
- [vector-database-engineer](https://affpapa.org/en/nevibecode/skills/vector-database-engineer.md) — skill · ★ 50109 repo stars
- [hunt-rag-vector](https://affpapa.org/en/nevibecode/skills/hunt-rag-vector.md) — skill · ★ 16193 repo stars
- [postgres](https://affpapa.org/en/nevibecode/skills/postgres.md) — skill · 1500 installs
- [pgvector-semantic-search](https://affpapa.org/en/nevibecode/skills/pgvector-semantic-search.md) — skill · 1000 installs

From the same set: [legioncodeinc/vibe-coding-tools](https://affpapa.org/en/nevibecode/by/legioncodeinc/vibe-coding-tools.md) — 172 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
