File contents Embeddings Skill
Purpose
Vector embeddings for semantic search and pattern matching with HNSW indexing.
Features
Feature
Description
sql.js Cross-platform SQLite persistent cache (WASM)
HNSW 150x-12,500x faster search
Hyperbolic Poincare ball model for hierarchical data
Normalization L2, L1, min-max, z-score
Chunking Configurable overlap and size
75x faster With agentic-flow ONNX integration
Commands
Initialize Embeddings
npx claude-flow embeddings init --backend sqlite
Embed Text
npx claude-flow embeddings embed --text "authentication patterns"
Batch Embed
npx claude-flow embeddings batch --file documents.json
Semantic Search
npx claude-flow embeddings search --query "security best practices" --top-k 5
Memory Integration
# Store with embeddings
npx claude-flow memory store --key "pattern-1" --value "description" --embed
# Search with embeddings
npx claude-flow memory search --query "related patterns" --semantic
Quantization
Type
Memory Reduction
Speed
Int8
3.92x
Fast
Int4
7.84x
Faster
Binary
32x
Fastest
Best Practices
Use HNSW for large pattern databases
Enable quantization for memory efficiency
Use hyperbolic for hierarchical relationships
Normalize embeddings for consistency
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1 --- 2 name: ruvnet-claude-flow-embeddings 3 description: Embeddings Skill 4 --- 5 6 # Embeddings Skill 7 8 ## Purpose 9 Vector embeddings for semantic search and pattern matching with HNSW indexing. 10 11 ## Features 12 13 | Feature | Description | 14 |---------|-------------| 15 | **sql.js** | Cross-platform SQLite persistent cache (WASM) | 16 | **HNSW** | 150x-12,500x faster search | 17 | **Hyperbolic** | Poincare ball model for hierarchical data | 18 | **Normalization** | L2, L1, min-max, z-score | 19 | **Chunking** | Configurable overlap and size | 20 | **75x faster** | With agentic-flow ONNX integration | 21 22 ## Commands 23 24 ### Initialize Embeddings 25 ```bash 26 npx claude-flow embeddings init --backend sqlite 27 ``` 28 29 ### Embed Text 30 ```bash 31 npx claude-flow embeddings embed --text "authentication patterns" 32 ``` 33 34 ### Batch Embed 35 ```bash 36 npx claude-flow embeddings batch --file documents.json 37 ``` 38 39 ### Semantic Search 40 ```bash 41 npx claude-flow embeddings search --query "security best practices" --top-k 5 42 ``` 43 44 ## Memory Integration 45 46 ```bash 47 # Store with embeddings 48 npx claude-flow memory store --key "pattern-1" --value "description" --embed 49 50 # Search with embeddings 51 npx claude-flow memory search --query "related patterns" --semantic 52 ``` 53 54 ## Quantization 55 56 | Type | Memory Reduction | Speed | 57 |------|-----------------|-------| 58 | Int8 | 3.92x | Fast | 59 | Int4 | 7.84x | Faster | 60 | Binary | 32x | Fastest | 61 62 ## Best Practices 63 1. Use HNSW for large pattern databases 64 2. Enable quantization for memory efficiency 65 3. Use hyperbolic for hierarchical relationships 66 4. Normalize embeddings for consistency 67 68 --- 69 > Converted and distributed by [TomeVault](https://tomevault.io/claim/ruvnet) — claim your Tome and manage your conversions. 70 <!-- tomevault:4.0:skill_md:2026-04-11 -->
commit cacf58f8c7
Frequently asked questions How do I install the Ruvnet Claude Flow Embeddings skill? Run npx skillmds@latest add tomevault-io/ruvnet-claude-flow-embeddings in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
What does the Ruvnet Claude Flow Embeddings skill do? Embeddings Skill It is listed under Coding & Dev Tools on SkillMD.
Is Ruvnet Claude Flow Embeddings safe to use? This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
Which AI agents work with Ruvnet Claude Flow Embeddings? This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Is Ruvnet Claude Flow Embeddings free to use? Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Who published Ruvnet Claude Flow Embeddings? tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.
tomevault-io