# genpark-cosine-bm25-reciprocal-rank-fusion-skill

> genpark-cosine-bm25-reciprocal-rank-fusion-skill — alpha-park-genpark-cosine-bm25-reciprocal-rank-fusion-skill. Use this tool when you need to fuse sparse and dense retrieval methods for improved search results, solving problems of information retrieval and ranking in various applications. It takes in query and document embeddings as inputs and outputs a fused ranking score, combining the strengths of BM25 and Cosine similarities through Reciprocal Rank Fusion. Ideal for use cases where a zero-dependency, hybrid retrieval engine is required for efficient and accurate information retrieval.

Canonical page: https://skillsregistry.net/skills/alpha-park-genpark-cosine-bm25-reciprocal-rank-fusion-skill  
JSON: https://api.skillsregistry.net/v1/skills/alpha-park-genpark-cosine-bm25-reciprocal-rank-fusion-skill

## Description

Zero-dependency hybrid retrieval engine fusing sparse lexical BM25 Okapi and dense Cosine vector similarities via Reciprocal Rank Fusion.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Alpha-Park/genpark-cosine-bm25-reciprocal-rank-fusion-skill)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "alpha-park-genpark-cosine-bm25-reciprocal-rank-fusion-skill"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/alpha-park-genpark-cosine-bm25-reciprocal-rank-fusion-skill` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/alpha-park-genpark-cosine-bm25-reciprocal-rank-fusion-skill/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt