Individual skill

hybrid-search

Combine dense and sparse retrieval — BM25 + vectors, fusion algorithms, weighting, and tuning. Use when neither keyword nor semantic search alone is good enough.

skills/hybrid-search/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 56
Repository last updated: Oct 10, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
ai-agents Repository topic
ai-agents-automation Repository topic
ai-skills Repository topic
awesome Repository topic
awesome-list Repository topic
chatgpt Repository topic
claude-skills Repository topic
meta-ai Repository topic
muse-ai Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 3,906 bytes

Read excerpt


# Hybrid Search

Dense (semantic) retrieval finds paraphrases but misses exact terms; sparse (keyword/BM25) finds 
exact terms but misses meaning. Hybrid search runs both and fuses the results — consistently 
beating either alone on real-world corpora.

## Overview

The pipeline: query goes to both a vector index (dense) and a keyword index (BM25), each returns 
ranked candidates, a fusion algorithm merges them into one ranking, and optionally a reranker 
refines the top. The tuning: how to normalize scores across systems, the fusion method, and the 
dense/sparse weight. Corpora with names, codes, IDs, and jargon benefit most — which is nearly 
every real corpus.