# Qdrant hybrid search prefetches

> Qdrant hybrid search prefetches is an open-source agent skill for knowledge and memory. Constructing prefetch queries for hybrid retrieval, including BM25/dense and multi-field setups, and choosing a lexical retrieval method. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/qdrant/skills/tree/main/skills/qdrant-search-quality/search-strategies/hybrid-search/search-types
- **Repository:** https://github.com/qdrant/skills
- **GitHub stars:** 269
- **License:** Apache-2.0
- **Skill name:** qdrant-hybrid-search-prefetches
- **Collection:** https://github.com/qdrant/skills
- **Categories:** [knowledge and memory](https://ai-powered.com/categories/knowledge-and-memory)
- **Listing updated:** 2026-11-17

## About

Constructing prefetch queries for hybrid retrieval, including BM25/dense and multi-field setups, and choosing a lexical retrieval method. Use when someone asks 'dense and sparse in one search?', 'how to combine multiple fields for retrieval?', 'payloads or sparse vectors for lexical?', 'BM25 on a full-text index or sparse vectors?', 'which sparse embedding model to use?', 'BM25 vs SPLADE?', or 'how to migrate BM25 sparse vectors to a text index?'

## When your agent uses it

> Constructing prefetch queries for hybrid retrieval, including BM25/dense and multi-field setups, and choosing a lexical retrieval method. Use when someone asks 'dense and sparse in one search?', 'how to combine multiple fields for retrieval?', 'payloads or sparse vectors for lexical?', 'BM25 on a full-text index or sparse vectors?', 'which sparse embedding model to use?', 'BM25 vs SPLADE?', or 'how to migrate BM25 sparse vectors to a text index?'

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/qdrant/skills/tree/HEAD/skills/qdrant-search-quality/search-strategies/hybrid-search/search-types)
- [License: Apache-2.0](https://github.com/qdrant/skills/tree/HEAD/skills/qdrant-search-quality/search-strategies/hybrid-search/search-types)

## Install

### Claude Code

This skill ships in the `qdrant` plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):

```sh
/plugin marketplace add qdrant/skills
/plugin install qdrant@qdrant
```

Or copy only this skill to `~/.claude/skills/qdrant-hybrid-search-prefetches`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/qdrant/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/qdrant-hybrid-search-prefetches &&
cp -R "$tmp/skills/qdrant-search-quality/search-strategies/hybrid-search/search-types" ~/.claude/skills/qdrant-hybrid-search-prefetches &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/qdrant-hybrid-search-prefetches` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/qdrant-hybrid-search-prefetches` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/qdrant/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/qdrant-hybrid-search-prefetches &&
cp -R "$tmp/skills/qdrant-search-quality/search-strategies/hybrid-search/search-types" ~/.agents/skills/qdrant-hybrid-search-prefetches &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/qdrant-hybrid-search-prefetches` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/qdrant-hybrid-search-prefetches` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/qdrant/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/qdrant-hybrid-search-prefetches &&
cp -R "$tmp/skills/qdrant-search-quality/search-strategies/hybrid-search/search-types" ~/.cursor/skills/qdrant-hybrid-search-prefetches &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/qdrant-hybrid-search-prefetches` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/qdrant/skills.git --path skills/qdrant-search-quality/search-strategies/hybrid-search/search-types
```

Or copy the folder to `~/.gemini/skills/qdrant-hybrid-search-prefetches` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/qdrant-hybrid-search-prefetches`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/qdrant/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/qdrant-hybrid-search-prefetches &&
cp -R "$tmp/skills/qdrant-search-quality/search-strategies/hybrid-search/search-types" ~/.copilot/skills/qdrant-hybrid-search-prefetches &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/qdrant-hybrid-search-prefetches` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/qdrant/skills.git
```

Then copy `skills/skills/qdrant-search-quality/search-strategies/hybrid-search/search-types` into your agent's skills folder as `qdrant-hybrid-search-prefetches`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Qdrant hybrid search prefetches in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/qdrant-hybrid-search-prefetches to use it in all your projects, or to .claude/skills/qdrant-hybrid-search-prefetches in one project. Or install the qdrant plugin, which includes it: /plugin marketplace add qdrant/skills, then /plugin install qdrant@qdrant.

### Does Qdrant hybrid search prefetches run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Qdrant hybrid search prefetches?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to Qdrant hybrid search prefetches?

The closest alternatives to Qdrant hybrid search prefetches are Qdrant search strategies, Qdrant search quality diagnosis, Qdrant model migration, Qdrant search quality and Qdrant scaling query volume.

## Where this comes from

- Description: from the skill's own SKILL.md.

## Alternatives

- [Qdrant search strategies](https://ai-powered.com/skills/qdrant-search-strategies): Qdrant search strategies is an open-source agent skill for knowledge and memory.
- [Qdrant search quality diagnosis](https://ai-powered.com/skills/qdrant-search-quality-diagnosis): Qdrant search quality diagnosis is an open-source agent skill for knowledge and memory.
- [Qdrant model migration](https://ai-powered.com/skills/qdrant-model-migration): Qdrant model migration is an open-source agent skill for knowledge and memory.
- [Qdrant search quality](https://ai-powered.com/skills/qdrant-search-quality): Qdrant search quality is an open-source agent skill for knowledge and memory.
- [Qdrant scaling query volume](https://ai-powered.com/skills/qdrant-scaling-query-volume): Qdrant scaling query volume is an open-source agent skill for knowledge and memory.
- [Qdrant performance optimization](https://ai-powered.com/skills/qdrant-performance-optimization): Qdrant performance optimization is an open-source agent skill for knowledge and memory.
- [Qdrant scaling data volume](https://ai-powered.com/skills/qdrant-scaling-data-volume): Qdrant scaling data volume is an open-source agent skill for knowledge and memory.

---
Source: https://ai-powered.com/skills/qdrant-hybrid-search-prefetches
