Qdrant Skills

A collection of Agent Skills for building with Qdrant vector search.

Installing

These skills work with any agent that supports the Agent Skills standard, including Claude Code, OpenCode, OpenAI Codex, and Pi.

Claude Code

Install using the plugin marketplace:

/plugin marketplace add qdrant/skills

npx skills

Install using the npx skills CLI:

npx skills add https://github.com/qdrant/skills

Clone / Copy

Clone this repo and copy the skill folders into the appropriate directory for your agent:

Agent	Skill Directory	Docs
Claude Code	~/.claude/skills/	docs
OpenCode	~/.config/opencode/skill/	docs
OpenAI Codex	~/.codex/skills/	docs
Pi	~/.pi/agent/skills/	docs

Commands

Commands are user-invocable slash commands that you explicitly call.

Command	Description
/qdrant:setup-collection	Create a collection with proper vector config, distance, and payload indexes
/qdrant:hybrid-search	Scaffold a dense+sparse prefetch query with RRF fusion
/qdrant:add-multitenancy	Add tenant isolation to an existing collection
/qdrant:migrate-search	Migrate deprecated client.search() calls to query_points
/qdrant:connect	Set up client connection for local or cloud

Skills

Skill	Useful for
qdrant-python	Python SDK best practices: search, filtering, hybrid search, multi-tenancy, gotchas
qdrant-rust	Rust client best practices: gRPC setup, builders, query, upsert, gotchas

Resources

• Qdrant Documentation
• mcp-code-snippets - MCP server for searching Qdrant docs and code examples
• mcp-server-qdrant - Official Qdrant MCP server