Skip to content
Back to search

skills

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/qdrant/skills with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/qdrant/skills'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/qdrant--skills/badge.svg)](/listings/qdrant--skills)

HTML

<a href="/listings/qdrant--skills"><img src="/api/listings/qdrant--skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

With the **Qdrant Advisor** installed, just ask your agent about Qdrant. The Advisor triggers automatically and loads the matching guidance live:

"I have 50M vectors on a single node and search is slow, should I add more nodes?"
→ Advisor loads the scaling guidance, recommends quantization and vertical scaling before adding nodes

"My search results are returning irrelevant matches"
→ Advisor loads the search-quality guidance, walks through diagnosis and search strategy options

"How do I switch from OpenAI embeddings to Cohere without downtime?"
→ Advisor loads the model-migration guidance for a zero-downtime switch with dual vectors

Prefer the URL method? Add `Use skills.qdrant.tech` to the same prompts:

"I have 50M vectors on a single node and search is slow, should I add more nodes? Use skills.qdrant.tech"

"My search results are returning irrelevant matches. Use skills.qdrant.tech"

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 14 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "qdrant",
  3. "owner": {
  4. "name": "Qdrant",
  5. "url": "https://qdrant.tech"
  6. },
  7. "plugins": [
  8. {
  9. "name": "qdrant",
  10. "source": "./",
  11. "description": "Agent skills for Qdrant vector search"
  12. }
  13. ]
  14. }
README.md · README · 167 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Qdrant Skills - Agent Skills for Qdrant Vector Search
  2. <p align="center">
  3. <picture>
  4. <source media="(prefers-color-scheme: dark)" srcset="https://github.com/qdrant/qdrant/raw/master/docs/logo-dark.svg">
  5. <source media="(prefers-color-scheme: light)" srcset="https://github.com/qdrant/qdrant/raw/master/docs/logo-light.svg">
  6. <img height="100" alt="Qdrant" src="https://github.com/qdrant/qdrant/raw/master/docs/logo.svg">
  7. </picture>
  8. </p>
  9. <p align="center">
  10. <b>Agent skills for building with Qdrant vector search</b>
  11. </p>
  12. 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.
  13. ## Philosophy
  14. Skills are not documentation. Qdrant already has docs in markdown. Skills
  15. answer "when?" and "why?", not "how?"
  16. They are structured as the handbook of a Solutions Architect working on Qdrant:
  17. given a problem, navigate to the exact place in the documentation where the
  18. answer lives. No tutorials, no concept explanations. Only references and
  19. minimal snippets where absolutely necessary.
  20. ## Disclaimer
  21. These skills are under active development. Skill content and structure may change between versions as Qdrant evolves.
  22. ## Usage
  23. Qdrant maintains a growing set of skills, and their content changes as Qdrant evolves. There are a few ways to give your agent access to them.
  24. ### Recommended: install the Qdrant Advisor
  25. Install one skill — the **Qdrant Advisor** — and your agent always has the freshest, most relevant Qdrant guidance, with nothing to manage as the skills change:
  26. ```bash
  27. npx skills add qdrant/skills/meta/qdrant-advisor
  28. ```
  29. The Advisor ships no static content of its own. When you raise a Qdrant problem, it searches [skills.qdrant.tech](https://skills.qdrant.tech) live, traverses the skill hierarchy along the branch that matches your symptom, and grounds its diagnosis in the current, authoritative guidance, loading only the relevant context. Because it fetches fresh every session, you don't need to reinstall to stay current, and you don't have to remember a URL or hope the site is in the model's training data.
  30. > **Using the claude.ai web app?** The Advisor can't fetch `skills.qdrant.tech` on its own when you are using the web app. You need to add `Use skills.qdrant.tech` to your prompt (refer to [Pass the URL directly](#alternative-pass-the-url-directly)).
  31. ### Alternative: pass the URL directly
  32. If you'd rather not install anything, pass the URL of the skills site in your prompt. The agent fetches the skill relevant to your current problem:
  33. ```
  34. Use skills.qdrant.tech
  35. ```
  36. This keeps context focused, but you have to include the URL in every prompt.
  37. ### Offline: install the full skill set
  38. If you want the skills available offline, or triggered automatically without the Advisor, install the complete set locally. See the [Installation](#installation) section.
  39. ## Quick Start
  40. With the **Qdrant Advisor** installed, just ask your agent about Qdrant. The Advisor triggers automatically and loads the matching guidance live:
  41. ```
  42. "I have 50M vectors on a single node and search is slow, should I add more nodes?"
  43. → Advisor loads the scaling guidance, recommends quantization and vertical scaling before adding nodes
  44. "My search results are returning irrelevant matches"
  45. → Advisor loads the search-quality guidance, walks through diagnosis and search strategy options
  46. "How do I switch from OpenAI embeddings to Cohere without downtime?"
  47. → Advisor loads the model-migration guidance for a zero-downtime switch with dual vectors
  48. ```
  49. Prefer the URL method? Add `Use skills.qdrant.tech` to the same prompts:
  50. ```
  51. "I have 50M vectors on a single node and search is slow, should I add more nodes? Use skills.qdrant.tech"
  52. "My search results are returning irrelevant matches. Use skills.qdrant.tech"
  53. ```
  54. ## Skills
  55. | Skill | Useful for |
  56. |-------|------------|
  57. | qdrant-clients-sdk | SDK setup, code examples, snippet search across Python, TypeScript, Rust, Go, .NET, Java |
  58. | qdrant-scaling | Scaling decisions: data volume, QPS, latency, query volume, horizontal vs vertical |
  59. | qdrant-sizing | Sizing RAM, disk, CPU, and node count before a deployment is provisioned.
  60. | qdrant-performance-optimization | Search speed, memory usage, indexing performance |
  61. | qdrant-search-quality | Diagnosing bad results, search strategies, hybrid search |
  62. | qdrant-monitoring | Metrics, health checks, debugging optimizer and cluster issues |
  63. | qdrant-multitenancy | Isolating multiple tenants within a Qdrant deployment: payload partitioning, tiered multitenancy, and region-based data isolation |
  64. | qdrant-deployment-options | Choosing between local, self-hosted, cloud, and hybrid |
  65. | qdrant-managed-cloud-quickstart | Getting a first Managed Cloud cluster running and connected: free vs standard, API keys, strict mode, Cloud Inference, and choices you can't undo |
  66. | qdrant-hybrid-cloud-setup | Setting up Hybrid Cloud on your own Kubernetes: prerequisites, storage/CSI, agent/operator install, exposure, and pitfalls |
  67. | qdrant-edge | Building on the embedded shard: server sync, on-device BM25, snapshots, reuse vs reimplement |
  68. | qdrant-migration-tool | Using the Qdrant Migration Tool CLI to move data from another vector database into Qdrant |
  69. | qdrant-model-migration | Switching embedding models without downtime |
  70. | qdrant-version-upgrade | Safe upgrade paths, compatibility guarantees, rolling upgrades |
  71. ## Installation
  72. ### Qdrant Advisor (recommended)
  73. If you want a single, always-current skill instead of the full set, install only the **Qdrant Advisor**:
  74. ```bash
  75. npx skills add qdrant/skills/meta/qdrant-advisor
  76. ```
  77. This installs just the `qdrant-advisor` meta-skill. It ships no static content of its own, it loads the relevant Qdrant skills live from [skills.qdrant.tech](https://skills.qdrant.tech) on demand, so you always get the latest guidance without reinstalling. It is not part of the `npx skills add qdrant/skills` bundle.
  78. ### npx skills
  79. Install using the [`npx skills`](https://skills.sh) CLI:
  80. ```bash
  81. npx skills add qdrant/skills
  82. ```
  83. ### Claude Code
  84. Add the marketplace, then install all Qdrant skills:
  85. ```
  86. /plugin marketplace add qdrant/skills
  87. /plugin install qdrant@qdrant
  88. ```
  89. ### Cursor
  90. Install from the Cursor Marketplace or add manually via **Settings > Rules > Add Rule > Remote Rule (GitHub)** with `qdrant/skills`.
  91. ### Clone / Copy
  92. Clone this repo and copy the skill folders into the appropriate directory for your agent:
  93. | Agent | Skill Directory | Docs |
  94. |-------|-----------------|------|
  95. | Claude Code | `~/.claude/skills/` | [docs](https://code.claude.com/docs/en/skills) |
  96. | Cursor | `.cursor/skills/` | [docs](https://docs.cursor.com/context/skills) |
  97. | OpenCode | `~/.config/opencode/skill/` | [docs](https://opencode.ai/docs/skills/) |
  98. | OpenAI Codex | `~/.codex/skills/` | [docs](https://developers.openai.com/codex/skills/) |
  99. | Pi | `~/.pi/agent/skills/` | [docs](https://github.com/badlogic/pi-mono/tree/main/packages/coding-agent#skills) |
  100. ## MCP Servers
  101. For additional Qdrant context, pair skills with these MCP servers:
  102. | Server | Purpose |
  103. |--------|---------|
  104. | [mcp-code-snippets](https://github.com/qdrant/mcp-code-snippets) | Search Qdrant docs and code examples across all SDKs |
  105. | [mcp-server-qdrant](https://github.com/qdrant/mcp-server-qdrant) | Store and retrieve memories, manage collections directly |
  106. ## Getting Help
  107. Found a bug or wrong advice in a skill? [Open an issue](https://github.com/qdrant/skills/issues/new) on GitHub and include:
  108. - The skill name
  109. - The prompt you gave your agent
  110. - What the agent said vs what it should have said
  111. ## Contributing
  112. If you are interested in contributing, follow the instructions in [CONTRIBUTING.md](./CONTRIBUTING.md).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.