Skills · Data & AI

Embedding Strategies

Unverified30/40

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Originally by wshobson · MIT

Claude CodePartialHas SKILL.md but declares no allowed-tools — Claude Code will ask for permission each time
CursorPartialPlain prose you can paste in — but no Cursor rules file
CodexPartialPlain prose you can paste in — but no AGENTS.md
Gemini CLIPartialPlain prose you can paste in
CopilotPartialPlain prose you can paste in — but no Copilot instructions file
npx agentalley add embedding-strategies

This command does not work yet — the CLI is still being built. Until then, use Raw in the reader below to take the file.

Who is stuck, and on what

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

The whole source

No sign-in, no blur, nothing truncated
embedding-strategies/SKILL.md66 lines2.8 KBRawView on GitHub
Frontmatter — 2 properties
nameembedding-strategies
descriptionSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
1---
2name: embedding-strategies
3description: Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
4---A5No allowed-tools declared — no way to tell what this skill may touch
5 
6# Embedding Strategies
7 
8Guide to selecting and optimizing embedding models for vector search applications.
9 
10## When to Use This Skill
11 
12- Choosing embedding models for RAG
13- Optimizing chunking strategies
14- Fine-tuning embeddings for domains
15- Comparing embedding model performance
16- Reducing embedding dimensions
17- Handling multilingual content
18 
19## Core Concepts
20 
21### 1. Embedding Model Comparison (2026)
22 
23| Model | Dimensions | Max Tokens | Best For |
24| -------------------------- | ---------- | ---------- | ----------------------------------- |
25| **voyage-3-large** | 1024 | 32000 | Claude apps (Anthropic recommended) |
26| **voyage-3** | 1024 | 32000 | Claude apps, cost-effective |
27| **voyage-code-3** | 1024 | 32000 | Code search |
28| **voyage-finance-2** | 1024 | 32000 | Financial documents |
29| **voyage-law-2** | 1024 | 32000 | Legal documents |
30| **text-embedding-3-large** | 3072 | 8191 | OpenAI apps, high accuracy |
31| **text-embedding-3-small** | 1536 | 8191 | OpenAI apps, cost-effective |
32| **bge-large-en-v1.5** | 1024 | 512 | Open source, local deployment |
33| **all-MiniLM-L6-v2** | 384 | 256 | Fast, lightweight |
34| **multilingual-e5-large** | 1024 | 512 | Multi-language |
35 
36### 2. Embedding Pipeline
37 
38```
39Document → Chunking → Preprocessing → Embedding Model → Vector
40
41 [Overlap, Size] [Clean, Normalize] [API/Local]
42```
43 
44## Templates and detailed worked examples
45 
46Full template library and detailed worked examples live in `references/details.md`. Read that file when you need the concrete templates.
47 
48## Best Practices
49 
50### Do's
51 
52- **Match model to use case**: Code vs prose vs multilingual
53- **Chunk thoughtfully**: Preserve semantic boundaries
54- **Normalize embeddings**: For cosine similarity search
55- **Batch requests**: More efficient than one-by-one
56- **Cache embeddings**: Avoid recomputing for static content
57- **Use Voyage AI for Claude apps**: Recommended by Anthropic
58 
59### Don'ts
60 
61- **Don't ignore token limits**: Truncation loses information
62- **Don't mix embedding models**: Incompatible vector spaces
63- **Don't skip preprocessing**: Garbage in, garbage out
64- **Don't over-chunk**: Lose important context
65- **Don't forget metadata**: Essential for filtering and debugging
66 

Reviews

Installed this one?Write the first review and take the Trailblazer badge.

Reviews only open after a real install, so this is empty — and we leave it empty rather than invent one.

Alternatives

Also in Data & AI