Agent skills for building with Qdrant vector search
Skills encode deep Qdrant knowledge so coding agents can make the engineering decisions that determine whether vector search works well: quantization, sharding, tenant isolation, hybrid search, model migration, and more.
Skills are not documentation. Qdrant already has docs in markdown. Skills answer "when?" and "why?", not "how?"
They are structured as the handbook of a Solutions Architect working on Qdrant: given a problem, navigate to the exact place in the documentation where the answer lives. No tutorials, no concept explanations. Only references and minimal snippets where absolutely necessary.
These skills are under active development. Skill content and structure may change between versions as Qdrant evolves.
Install using the npx skills CLI:
npx skills add qdrant/skillsAdd the marketplace, then install all Qdrant skills:
/plugin marketplace add qdrant/skills
/plugin install qdrant@qdrant
Install from the Cursor Marketplace or add manually via Settings > Rules > Add Rule > Remote Rule (GitHub) with qdrant/skills.
Clone this repo and copy the skill folders into the appropriate directory for your agent:
| Agent | Skill Directory | Docs |
|---|---|---|
| Claude Code | ~/.claude/skills/ |
docs |
| Cursor | .cursor/skills/ |
docs |
| OpenCode | ~/.config/opencode/skill/ |
docs |
| OpenAI Codex | ~/.codex/skills/ |
docs |
| Pi | ~/.pi/agent/skills/ |
docs |
After installing, just ask your agent about Qdrant. Skills are triggered automatically when your question matches their description.
"I have 50M vectors on a single node and search is slow, should I add more nodes?"
→ qdrant-scaling skill activates, recommends quantization and vertical scaling before adding nodes
"My search results are returning irrelevant matches"
→ qdrant-search-quality skill activates, walks through diagnosis and search strategy options
"How do I switch from OpenAI embeddings to Cohere without downtime?"
→ qdrant-model-migration skill activates, guides zero-downtime migration with dual vectors
Skills are triggered automatically when your question matches their description.
| Skill | Useful for |
|---|---|
| qdrant-clients-sdk | SDK setup, code examples, snippet search across Python, TypeScript, Rust, Go, .NET, Java |
| qdrant-scaling | Scaling decisions: data volume, QPS, latency, query volume, horizontal vs vertical |
| qdrant-performance-optimization | Search speed, memory usage, indexing performance |
| qdrant-search-quality | Diagnosing bad results, search strategies, hybrid search |
| qdrant-monitoring | Metrics, health checks, debugging optimizer and cluster issues |
| qdrant-deployment-options | Choosing between local, self-hosted, cloud, and hybrid |
| qdrant-model-migration | Switching embedding models without downtime |
| qdrant-version-upgrade | Safe upgrade paths, compatibility guarantees, rolling upgrades |
For additional Qdrant context, pair skills with these MCP servers:
| Server | Purpose |
|---|---|
| mcp-code-snippets | Search Qdrant docs and code examples across all SDKs |
| mcp-server-qdrant | Store and retrieve memories, manage collections directly |
Found a bug or wrong advice in a skill? Open an issue on GitHub and include:
- The skill name
- The prompt you gave your agent
- What the agent said vs what it should have said
If you are interested in contributing, follow the instructions in CONTRIBUTING.md.