# Smart Search

> Use this for hybrid Vector+BM25 search to find specific existing info in the knowledge base—use only for factual, pre-existing content (skip guidance on creating/structuring docs, formatting, external queries, or search method questions)

- Skill: `chainlesschain/smart-search` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add chainlesschain/smart-search`
- Raw SKILL.md: https://api.skillmd.com/api/skills/chainlesschain/smart-search/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: chainlesschain (https://skillmd.com/u/chainlesschain)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/chainlesschain/smart-search

---


# Smart Search Skill

Search across your knowledge base using hybrid Vector+BM25 search.

## Usage

```
/smart-search <query>
/smart-search similar <document_reference>
```

## Search Modes

| Mode               | Description                                           |
| ------------------ | ----------------------------------------------------- |
| `search` (default) | Hybrid search combining semantic and keyword matching |
| `similar`          | Find documents similar to a reference                 |
| `vector`           | Pure semantic/vector search                           |
| `keyword`          | Pure BM25 keyword search                              |

## How It Works

1. **Hybrid Search** (default): Combines vector similarity (60% weight) with BM25 keyword matching (40% weight) using Reciprocal Rank Fusion
2. **Vector Search**: Uses RAG embeddings for semantic similarity
3. **BM25 Search**: Okapi BM25 algorithm with Chinese/English tokenizer
4. **Performance**: <20ms search latency with parallel execution