New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Qdrant Hybrid Search Combining

by qdrant in qdrant/skills

Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion).

OfficialApache-2.0Auto-check passedAI & LLM Engineering

Install Qdrant Hybrid Search Combining

skills CLI
$ npx skills add qdrant/skills --skill qdrant-hybrid-search-combining -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install qdrant/skills qdrant-hybrid-search-combining --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ 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/hybrid-search/combining-searches .claude/skills/qdrant-hybrid-search-combining && rm -rf skills-src

Use ~/.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/

Facts

Skill name
qdrant-hybrid-search-combining
GitHub stars
254
Token cost
~1.6k tokens
SKILL.md length
711 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
Apache-2.0

At a glance

Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion).

  • Someone asks RRF
  • SKILL.md covers Scores Are Not Comparable…, Need Custom Fusion, Need Good Ranking of Fused… and What NOT to Do
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • How to combine sparse and dense

What it does

Qdrant Hybrid Search Combining is an agent skill from qdrant/skills, published by the product's own GitHub organization. Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Use when someone asks 'RRF or DBSF?', 'how to combine sparse and dense', 'how to combine scores from multiple searches?', 'custom fusion', 'fusion is not producing good results', 'how do I tune RRF', 'what k should I use', or 'how do I set fusion weights'

Its SKILL.md is about 1.6k 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 AI & LLM Engineering, 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 RRF
  • How to combine sparse and dense
  • How to combine scores from multiple searches?
  • Fusion is not producing good results

Example prompts

  • “RRF or DBSF?”
  • “how to combine sparse and dense”
  • “how to combine scores from multiple searches?”
  • “/qdrant-hybrid-search-combining”

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 nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    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 Hybrid Search Combining loads about 1.6k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 711 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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). 711 words, ~1,649 tokens.

Download SKILL.mdSave it as .claude/skills/qdrant-hybrid-search-combining/SKILL.md (or your agent's skills folder).
name
qdrant-hybrid-search-combining
description
Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Use when someone asks 'RRF or DBSF?', 'how to combine sparse and dense', 'how to combine scores from multiple searches?', 'custom fusion', 'fusion is not producing good results', 'how do I tune RRF', 'what k should I use', or 'how do I set fusion weights'

Combining Prefetch Results

The outer query fuses ranked candidate lists from all parallel prefetches into one ranked list of results. Fusion methods differ in whether they use rank, score or directly vector representations of candidates (their similarity to the outer query) and whether final score incorporates payload metadata. All methods support flat (one fusion step) and nested (multi-stage) prefetch structures.

Tune in this order, cheapest first: confirm fusion beats each prefetch alone on your labels, compare Qdrant's default RRF vs DBSF, if tuning RRF: settle k, then sweep weights at that k, and validate on held-out queries. A weight pair is only valid for the k it was tuned with Tune in this order

Scores Are Not Comparable Across Prefetches & You Want Some Easy Baseline

Use when: searches produce scores on different scales, like BM25 and cosine on dense embeddings.

RRF
DBSF
  • DBSF (Distribution-Based Score Fusion): normalizes score distributions per prefetch before fusing them, for that, instead of min-max, uses mean +- 3 deviations on prefetched list of scores. Avoid relying on resulting absolute scores, as scores in DBSF are normalized per prefetch (aka per a retrieved list of search results), and might be uncomparable across queries.
  • DBSF has no parameters to tune, so compare it before hand-tuning RRF k and weights. Confirm on your own labels Compare RRF and DBSF on your labels

Need Custom Fusion

Use when: recency, popularity or other payload values should affect the merged ranking alongside candidate scores or you need a custom fusion.

With formula query, access score of each prefetch and, if desired, payload field values.

If you want to implement custom fusion on score of each prefetch:

  • Use decay or any other available expressions for normalizing score distributions before fusing them.
  • Parameters of these expressions should be based on the collection & retriever score distributions (for example, adjusting these parameters on a subsample of real queries).
  • Formula query is unable to provide ranks for custom fusions

When using FormulaQuery over multiple prefetches (e.g. per-representation weighting):

  • $score[i] indexes prefetches in declaration order. Reordering the prefetch= list silently shifts which weight applies to which retriever.
  • Provide defaults for every $score[i] so the formula still evaluates for candidates that surfaced from only a subset of prefetches.
  • Start with RRF when scores are on incomparable scales (e.g. BM25 + cosine). Reach for FormulaQuery only when explicit per-representation weighting or payload-driven boosts are required, and normalize each $score[i] (decay or min-max on a sampled distribution) before combining linearly.
Show full SKILL.md (239 more words)Show less

Need Good Ranking of Fused Candidates and Ready To Spend More Resources

Use when: you want to use similarity between query and candidates' vector representations as the prefetches combiner and simultaneously ranker. More resource heavy than score/rank based fusions, but might be necessary due to use case requirements or need in a high top-K precision of results (when parallel prefetches have overall a good recall of retrieved candidates).

More candidates only help if the ranker can use them. Deeper prefetches can raise the best possible score

You can use any type of vector as an outer query over the prefetches, to perform the fusion on the server-side in one QueryAPI request: sparse, dense, multivector. For that, same type of vector representations for documents need to be stored as named vectors per point.

Instead of using client-side fusion through cross-encoders, a popular option is Late interaction models-based fusion, through reranking on multivectors (e.g. ColBERT for text, ColPali and ColQwen for images).

What NOT to Do

  • Use linear weighted fusion on incomparable score ranges. Why not.
  • Use "vibe" defined weights in weighted RRF. Weights should be fine-tuned per dataset and retrieval pipelines.
  • Pick any fusion type without comparative experiments.
  • Use late interaction multivectors for fusion without evaluating cheaper analogues, for example, MUVERA. More in multi-vector Qdrant search course

© 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/hybrid-search/combining-searches of qdrant/skills.

Open the folder on GitHubat commit 1780b6d

Compare with similar skills

Qdrant Hybrid Search Combining 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.

Qdrant Hybrid Search Combining compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Qdrant Hybrid Search Combining this skillqdrant/skills254—~1.6kAutomated safety check: PassApache-2.0
RAG Implementationwshobson/agents40k9 repos~1.1kAutomated safety check: PassMIT
Hunt RAG Vectorelementalsouls/Claude-BugHunter4.8k—~2.6kAutomated safety check: PassMIT
Qdrant Search Qualitygithub/awesome-copilot40k1 repos~336Automated safety check: PassMIT
QdrantLuciole-Studio/Misaka-Agent1711 repos~3.4kAutomated safety check: PassMIT
Building RAG Systemsaiskillstore/marketplace433—~2.7kAutomated safety check: PassNone

Similar skills

  • 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.

    40k GitHub starsUsed in 9 repos~1.1k tokens
    AI & LLM EngineeringAuto-check passed

  • 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…

    4.8k GitHub stars~2.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Qdrant Search Quality

    github/awesome-copilot

    Official

    Diagnoses and improves Qdrant search relevance. An agent skill from github/awesome-copilot.

    40k GitHub starsUsed in 1 repo~336 tokens
    AI & LLM EngineeringAuto-check passed

  • Qdrant

    Luciole-Studio/Misaka-Agent

    Vector search engine for production RAG systems. An agent skill from Luciole-Studio/Misaka-Agent.

    171 GitHub starsUsed in 1 repo~3.4k tokens
    AI & LLM EngineeringAuto-check passed

  • Building RAG Systems

    aiskillstore/marketplace

    Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval.

    433 GitHub stars~2.7k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • 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.

    13k GitHub starsUsed in 4 repos~3.4k tokens
    DatabasesAuto-check passed

More from qdrant/skills

All 33 skills in this repo

  • Qdrant Clients SDK

    qdrant/skills

    Official

    Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.

    254 GitHub starsUsed in 2 repos~752 tokens
    Auto-check: notes

  • Qdrant Advisor

    qdrant/skills

    Official

    Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech.

    254 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • Qdrant Deployment Options

    qdrant/skills

    Official

    Guides Qdrant deployment selection. An agent skill from qdrant/skills.

    254 GitHub starsUsed in 2 repos~976 tokens
    Auto-check passed

  • Qdrant Search Strategies

    qdrant/skills

    Official

    Guides Qdrant search strategy selection. An agent skill from qdrant/skills.

    254 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • Qdrant Horizontal Scaling

    qdrant/skills

    Official

    Diagnoses and guides Qdrant horizontal scaling decisions. An agent skill from qdrant/skills.

    254 GitHub starsUsed in 2 repos~833 tokens
    Auto-check passed

Works with

Categories

Questions about Qdrant Hybrid Search Combining

What does Qdrant Hybrid Search Combining do?

Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Qdrant Hybrid Search Combining is an agent skill from qdrant/skills, published by the product's own GitHub organization. Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion).

When should I use Qdrant Hybrid Search Combining?

Qdrant Hybrid Search Combining fits situations like: someone asks RRF; how to combine sparse and dense; how to combine scores from multiple searches?; fusion is not producing good results.

How do I install Qdrant Hybrid Search Combining in Claude Code?

Run `npx skills add qdrant/skills --skill qdrant-hybrid-search-combining -a claude-code`. Or copy the skill folder (skills/qdrant-search-quality/search-strategies/hybrid-search/combining-searches in qdrant/skills) into .claude/skills/qdrant-hybrid-search-combining in your project. Claude Code loads it when a task matches its description.

How do I install Qdrant Hybrid Search Combining in Codex?

Run `npx skills add qdrant/skills --skill qdrant-hybrid-search-combining -a codex`. Or copy the skill folder (skills/qdrant-search-quality/search-strategies/hybrid-search/combining-searches in qdrant/skills) into .agents/skills/qdrant-hybrid-search-combining in your project. Codex loads it when a task matches its description.

Can I use Qdrant Hybrid Search Combining 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-hybrid-search-combining -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-hybrid-search-combining, .gemini/skills/qdrant-hybrid-search-combining, .github/skills/qdrant-hybrid-search-combining and .opencode/skills/qdrant-hybrid-search-combining in your project.

What does Qdrant Hybrid Search Combining need to run?

SKILL.md names no scripts, command-line tools or credentials: Qdrant Hybrid Search Combining is instructions for the agent only.

Does Qdrant Hybrid Search Combining 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 Hybrid Search Combining 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 Hybrid Search Combining use?

Qdrant Hybrid Search Combining 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 Hybrid Search Combining use?

About 1.6k tokens (SKILL.md is roughly 6.6k 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 Hybrid Search Combining?

Skills that share tags, products or a category with Qdrant Hybrid Search Combining: RAG Implementation (wshobson/agents, 40k stars), Hunt RAG Vector (elementalsouls/Claude-BugHunter, 4.8k stars), Qdrant Search Quality (github/awesome-copilot, 40k stars) and Qdrant (Luciole-Studio/Misaka-Agent, 171 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Qdrant Hybrid Search Combining?

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.