# retrieval-stinger

The retrieval-stinger skill helps design and inspect application search, from text queries to combined text-and-vector results. Use it when relevant documents go missing or search returns noise.

- 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/retrieval-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/retrieval-stinger

## What it does

retrieval-stinger examines how an app finds and ranks records, passages, and documents. It covers Postgres text search, semantic retrieval with pgvector, and ways to combine result sets. It also helps assess document splitting and search quality. Postgres is the primary path; projects already using Deep Lake have a separate set of approaches.

The skill first identifies the search engine and methods a project actually uses, then selects a matching guide. For combined search, it checks whether both text and vector results are queried; for quality checks, it uses a set of test queries with expected results. This skill focuses on retrieval behavior, while vector schema and index questions are handed off to another subagent.

For Claude Code, add the `wasp-nest` marketplace and install `data-and-ai-tools`. Codex has its own `npx skills` install command.

## 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 retrieval-stinger -a claude-code
```

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

### Codex

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

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

### Cursor

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

2. **Manually: put the files in place**
- File: `.cursor/skills/retrieval-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/retrieval-stinger
```

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

### Gemini CLI

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

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/retrieval-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/retrieval-stinger/SKILL.md

## When to use it
- find why a query misses relevant documents
- combine text-based and vector search results
- choose how to split documents for retrieval
- measure search quality against expected results

## Example prompts
- Find why this search query misses the relevant records.
- Suggest a way to combine text and vector search in this app.
- Assess search quality using a set of queries and expected results.

## Similar
- [rag-retrieval](https://affpapa.org/en/nevibecode/skills/rag-retrieval.md) — skill · 1500 installs
- [iterative-retrieval](https://affpapa.org/en/nevibecode/skills/iterative-retrieval.md) — skill · 6200 installs
- [nemotron-retrieval-recipes](https://affpapa.org/en/nevibecode/skills/nemotron-retrieval-recipes.md) — skill · 2100 installs
- [icon-retrieval](https://affpapa.org/en/nevibecode/skills/icon-retrieval.md) — skill · 1700 installs
- [tooluniverse-sequence-retrieval](https://affpapa.org/en/nevibecode/skills/tooluniverse-sequence-retrieval.md) — skill · 1700 installs
- [memory-retrieval-learning](https://affpapa.org/en/nevibecode/skills/memory-retrieval-learning.md) — skill · 499 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
