Qdrant Vector Search
Orchestra-Research/AI-Research-SKILLs
Explains how to run Qdrant, a Rust vector database, for RAG and semantic search, covering collections, points, distance metrics and filtered or batched queries.
Guides Qdrant search strategy selection. An agent skill from qdrant/skills.
Install Qdrant Search Strategies
$ npx skills add qdrant/skills --skill qdrant-search-strategies -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qdrant/skills qdrant-search-strategies --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/qdrant/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/qdrant-search-quality/search-strategies .claude/skills/qdrant-search-strategies && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "qdrant-search-strategies" agent skill from https://github.com/qdrant/skills/tree/main/skills/qdrant-search-quality/search-strategies into .claude/skills/qdrant-search-strategies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qdrant-search-strategies", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/qdrant/skills/tree/main/skills/qdrant-search-quality/search-strategiesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add qdrant/skills --skill qdrant-search-strategies -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qdrant/skills qdrant-search-strategies --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qdrant/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/qdrant-search-quality/search-strategies .agents/skills/qdrant-search-strategies && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "qdrant-search-strategies" agent skill from https://github.com/qdrant/skills/tree/main/skills/qdrant-search-quality/search-strategies into .agents/skills/qdrant-search-strategies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qdrant-search-strategies", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add qdrant/skills --skill qdrant-search-strategies -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qdrant/skills qdrant-search-strategies --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qdrant/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/qdrant-search-quality/search-strategies .cursor/skills/qdrant-search-strategies && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "qdrant-search-strategies" agent skill from https://github.com/qdrant/skills/tree/main/skills/qdrant-search-quality/search-strategies into .cursor/skills/qdrant-search-strategies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qdrant-search-strategies", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/qdrant/skills.git --path skills/qdrant-search-quality/search-strategies--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add qdrant/skills --skill qdrant-search-strategies -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qdrant/skills qdrant-search-strategies --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qdrant/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/qdrant-search-quality/search-strategies .gemini/skills/qdrant-search-strategies && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "qdrant-search-strategies" agent skill from https://github.com/qdrant/skills/tree/main/skills/qdrant-search-quality/search-strategies into .gemini/skills/qdrant-search-strategies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qdrant-search-strategies", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install qdrant/skills qdrant-search-strategiesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add qdrant/skills --skill qdrant-search-strategies -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/qdrant/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/qdrant-search-quality/search-strategies .github/skills/qdrant-search-strategies && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "qdrant-search-strategies" agent skill from https://github.com/qdrant/skills/tree/main/skills/qdrant-search-quality/search-strategies into .github/skills/qdrant-search-strategies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qdrant-search-strategies", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add qdrant/skills --skill qdrant-search-strategies -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install qdrant/skills qdrant-search-strategies --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qdrant/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/qdrant-search-quality/search-strategies .opencode/skills/qdrant-search-strategies && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "qdrant-search-strategies" agent skill from https://github.com/qdrant/skills/tree/main/skills/qdrant-search-quality/search-strategies into .opencode/skills/qdrant-search-strategies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qdrant-search-strategies", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
qdrant-search-strategies- GitHub stars
- 254
- Token cost
- ~1.4k tokens
- SKILL.md length
- 614 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Guides Qdrant search strategy selection. An agent skill from qdrant/skills.
- Someone asks should I use hybrid search?
- SKILL.md covers Missing Keyword Matches or…, Right Documents Found But Not…, Dense Retriever Misses… and Results Too Similar, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Results are not relevant
What it does
Qdrant Search Strategies is an agent skill from qdrant/skills, published by the product's own GitHub organization. Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from my dataset but they're there', 'retrieval quality is not good enough', 'results too similar', 'need diversity', 'MMR', 'relevance feedback', 'recommendation API', 'discovery API', or 'missing keyword matches'
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Databases, covering Vector databases and Retrieval-augmented generation. It works with Qdrant. The repository describes itself as: Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python…. The licence is Apache-2.0.
When your agent uses it
- Someone asks should I use hybrid search?
- Results are not relevant
- I dont get needed results from my dataset but theyre there
- Retrieval quality is not good enough
Example prompts
- “should I use hybrid search?”
- “how to rerank?”
- “results are not relevant”
- “/qdrant-search-strategies”
Requirements
- Pre-approved tools (allowed-tools): Read, Grep, Glob
What it can do on your machine
Read from SKILL.md and the folder at commit 1780b6d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepGlob
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
skills.qdrant.tech
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Qdrant Search Strategies loads about 1.4k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 614 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from qdrant/skills at commit 1780b6d, republished under its Apache-2.0 licence (© qdrant). 614 words, ~1,401 tokens.
Download SKILL.mdSave it as
.claude/skills/qdrant-search-strategies/SKILL.md (or your agent's skills folder).- name
- qdrant-search-strategies
- description
- Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from my dataset but they're there', 'retrieval quality is not good enough', 'results too similar', 'need diversity', 'MMR', 'relevance feedback', 'recommendation API', 'discovery API', or 'missing keyword matches'
- allowed-tools
- Read, Grep, Glob
How to Improve Search Results with Advanced Strategies
These strategies complement basic vector search. Use them after confirming the embedding model is fitting the task and HNSW config is correct. If exact search returns bad results, verify the selection of the embedding model (retriever) first. If the user wants to use a weaker embedding model because it is small, fast, and cheap, use reranking or relevance feedback to improve search quality.
Each symptom may require a different strategy: diagnose and address them independently. A single project can have multiple symptoms at once, and fixing one (e.g. adding hybrid search for keyword misses) may not fix the others (e.g. redundant results may still need MMR; poor precision may still need reranking).
| Symptom | Strategy |
|---|---|
| Missing exact/keyword matches | Hybrid search |
| Right documents exist but rank low (good recall, poor precision) | Multistage queries / reranking |
| Dense retriever misses relevant items entirely, or reranking too costly | Relevance feedback |
| Results are redundant / near-duplicate | MMR |
| Need to steer with example points | Recommendation / Discovery API |
| Need business-logic-based ranking | Score boosting |
Missing Keyword Matches or Need to Combine Multiple Search Signals
Use when: pure vector search misses keyword/domain term matches, or the use case benefits from combining searches on multiple representations (including languages and modalities) of the same item.
See how to use hybrid search
Right Documents Found But Not in the Top Results
Use when: good recall but poor precision (right docs in top-100, not top-10).
- See how to use Multistage queries, for example with late interaction rerankers through Multivectors.
- Cross-encoder rerankers via FastEmbed Rerankers
- Before adding a ranking stage: score your candidate pool as if perfectly ordered and compare it to what you return today. A small gap means ranking is near its ceiling, so fix retrieval or candidate depth instead.
- See how to choose, test and size a reranker, and how to tell a real gain from a false one
Dense Retriever Misses Relevant Items or Reranking Is Too Costly
Use when: dense retriever misses relevant items you know exist in the collection; relevant documents lie outside the initial ANN retrieval pool; reranking a large candidate pool is too slow or expensive; using a small/cheap embedding model but need quality close to a larger model; or want to improve top-1/3 precision without the full cost of reranking.
Show full SKILL.md (229 more words)Show less
Results Too Similar
Use when: top results are redundant, near-duplicates, or lack diversity. Common in dense content domains (academic papers, product catalogs).
- Use MMR (v1.15+) as a query parameter with
diversityto balance relevance and diversity MMR - Start with
diversity=0.5, lower for more precision, higher for more exploration - MMR is slower than standard search. Only use when redundancy is an actual problem.
Want to improve search results based on examples (positive and negative)
Use when: you can provide positive and negative example points to steer search closer to positive and further from negative.
- Recommendation API: positive/negative examples to recommend fitting vectors Recommendation API
- Best score strategy: better for diverse examples, supports negative-only Best score
- Discovery API: context pairs (positive/negative) constrain the search region, either around a target (discovery search) or without one (context search) Discovery
Have Business Logic Behind Results Relevance
Use when: results should be additionally ranked according to some business logic based on data, like recency or distance.
Check how to set up in Score Boosting docs
What NOT to Do
- Use hybrid search before verifying pure vector search quality (adds complexity, may mask model issues)
- Apply one strategy (e.g. hybrid search) as a blanket fix for multiple distinct symptoms, diagnose and treat each symptom separately (see table above)
- Skip evaluation when adding relevance feedback: score the end-to-end pipeline to confirm it actually helps Pipeline Output Quality
© qdrant, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/qdrant-search-quality/search-strategies of qdrant/skills.
Open the folder on GitHubat commit 1780b6d
Compare with similar skills
Qdrant Search Strategies next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Qdrant Search Strategies this skillqdrant/skills | 254 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Qdrant Vector SearchOrchestra-Research/AI-Research-SKILLs | 13k | 4 repos | ~3.4k | Automated safety check: Pass | MIT | |
| Using Vector Databasesancoleman/ai-design-components | 525 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Qdrant Search Strategiesgithub/awesome-copilot | 40k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| RAG Implementationwshobson/agents | 40k | 9 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Hunt RAG Vectorelementalsouls/Claude-BugHunter | 4.8k | — | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Using Vector Databases
ancoleman/ai-design-components
Vector database implementation for AI/ML applications, semantic search, and RAG systems.
- Official
Qdrant Search Strategies
github/awesome-copilot
Guides Qdrant search strategy selection. An agent skill from github/awesome-copilot.
RAG Implementation
wshobson/agents
Build retrieval-augmented generation systems: pick a vector database and embedding model, choose retrieval and reranking strategies, and start from a LangGraph pipeline.
Hunt RAG Vector
elementalsouls/Claude-BugHunter
Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from…
- Official
Qdrant Search Quality
github/awesome-copilot
Diagnoses and improves Qdrant search relevance. An agent skill from github/awesome-copilot.
More from qdrant/skills
All 33 skills in this repo- Official
Qdrant Clients SDK
qdrant/skills
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
- Official
Qdrant Advisor
qdrant/skills
Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech.
- Official
Qdrant Deployment Options
qdrant/skills
Guides Qdrant deployment selection. An agent skill from qdrant/skills.
- Official
Qdrant Horizontal Scaling
qdrant/skills
Diagnoses and guides Qdrant horizontal scaling decisions. An agent skill from qdrant/skills.
- Official
Qdrant Indexing Performance Optimization
qdrant/skills
Diagnoses and fixes slow Qdrant indexing and data ingestion.
- Official
Qdrant Memory Usage Optimization
qdrant/skills
Diagnoses and reduces Qdrant memory usage. An agent skill from qdrant/skills.
Related
Works with
Categories
Questions about Qdrant Search Strategies
What does Qdrant Search Strategies do?
Guides Qdrant search strategy selection. An agent skill from qdrant/skills. Qdrant Search Strategies is an agent skill from qdrant/skills, published by the product's own GitHub organization. Guides Qdrant search strategy selection.
When should I use Qdrant Search Strategies?
Qdrant Search Strategies fits situations like: someone asks should I use hybrid search?; results are not relevant; I dont get needed results from my dataset but theyre there; retrieval quality is not good enough.
How do I install Qdrant Search Strategies in Claude Code?
Run `npx skills add qdrant/skills --skill qdrant-search-strategies -a claude-code`. Or copy the skill folder (skills/qdrant-search-quality/search-strategies in qdrant/skills) into .claude/skills/qdrant-search-strategies in your project. Claude Code loads it when a task matches its description.
How do I install Qdrant Search Strategies in Codex?
Run `npx skills add qdrant/skills --skill qdrant-search-strategies -a codex`. Or copy the skill folder (skills/qdrant-search-quality/search-strategies in qdrant/skills) into .agents/skills/qdrant-search-strategies in your project. Codex loads it when a task matches its description.
Can I use Qdrant Search Strategies in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qdrant/skills --skill qdrant-search-strategies -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qdrant-search-strategies, .gemini/skills/qdrant-search-strategies, .github/skills/qdrant-search-strategies and .opencode/skills/qdrant-search-strategies in your project.
What does Qdrant Search Strategies need to run?
SKILL.md names no scripts, command-line tools or credentials: Qdrant Search Strategies is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob.
Does Qdrant Search Strategies access the network?
SKILL.md names 1 domain. As links in the text: skills.qdrant.tech. This is read from the text; nothing was executed.
Is Qdrant Search Strategies safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Qdrant Search Strategies use?
Qdrant Search Strategies is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Qdrant Search Strategies use?
About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Qdrant Search Strategies?
Skills that share tags, products or a category with Qdrant Search Strategies: Qdrant Vector Search (Orchestra-Research/AI-Research-SKILLs, 13k stars), Using Vector Databases (ancoleman/ai-design-components, 525 stars), Qdrant Search Strategies (github/awesome-copilot, 40k stars) and RAG Implementation (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Qdrant Search Strategies?
qdrant (a GitHub organization, an official publisher) maintains it in qdrant/skills, which has 254 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 9, 2026.
Source: qdrant/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.