embedding-strategies
Helps select, optimize, and fine-tune embedding models for RAG applications.
Install
mkdir -p .claude/skills/embedding-strategies && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/450" && unzip -o skill.zip -d .claude/skills/embedding-strategies && rm skill.zipInstalls to .claude/skills/embedding-strategies
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
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.Key capabilities
- →Compare performance of vector embedding models
- →Implement text chunking with overlap
- →Normalize and clean dataset documents
- →Select models for domain-specific search
- →Optimize embedding dimensions for cost/accuracy
How it works
Uses a comparative matrix of model capabilities and pipeline templates to map specific domain needs to optimal embeddings.
Inputs & outputs
When to use embedding-strategies
- →Choose an embedding model for RAG
- →Optimize text chunking strategies
- →Compare performance of different embedding models
About this skill
Embedding Strategies
Guide to selecting and optimizing embedding models for vector search applications.
When to Use This Skill
- Choosing embedding models for RAG
- Optimizing chunking strategies
- Fine-tuning embeddings for domains
- Comparing embedding model performance
- Reducing embedding dimensions
- Handling multilingual content
Core Concepts
1. Embedding Model Comparison (2026)
| Model | Dimensions | Max Tokens | Best For |
|---|---|---|---|
| voyage-3-large | 1024 | 32000 | Claude apps (Anthropic recommended) |
| voyage-3 | 1024 | 32000 | Claude apps, cost-effective |
| voyage-code-3 | 1024 | 32000 | Code search |
| voyage-finance-2 | 1024 | 32000 | Financial documents |
| voyage-law-2 | 1024 | 32000 | Legal documents |
| text-embedding-3-large | 3072 | 8191 | OpenAI apps, high accuracy |
| text-embedding-3-small | 1536 | 8191 | OpenAI apps, cost-effective |
| bge-large-en-v1.5 | 1024 | 512 | Open source, local deployment |
| all-MiniLM-L6-v2 | 384 | 256 | Fast, lightweight |
| multilingual-e5-large | 1024 | 512 | Multi-language |
2. Embedding Pipeline
Document → Chunking → Preprocessing → Embedding Model → Vector
↓
[Overlap, Size] [Clean, Normalize] [API/Local]
Templates and detailed worked examples
Full template library and detailed worked examples live in references/details.md. Read that file when you need the concrete templates.
Best Practices
Do's
- Match model to use case: Code vs prose vs multilingual
- Chunk thoughtfully: Preserve semantic boundaries
- Normalize embeddings: For cosine similarity search
- Batch requests: More efficient than one-by-one
- Cache embeddings: Avoid recomputing for static content
- Use Voyage AI for Claude apps: Recommended by Anthropic
Don'ts
- Don't ignore token limits: Truncation loses information
- Don't mix embedding models: Incompatible vector spaces
- Don't skip preprocessing: Garbage in, garbage out
- Don't over-chunk: Lose important context
- Don't forget metadata: Essential for filtering and debugging
When not to use it
- →Standard keyword-based search implementations
- →Non-vectorized dataset processing
Limitations
- →Limited by availability of current 2026 model performance data
- →Chunking optimization requires dataset analysis
How it compares
It selects models based on empirical constraints (token limits, dimensions) rather than using a default global model.
Compared to similar skills
embedding-strategies side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| embedding-strategies (this skill) | 8 | 2mo | No flags | Intermediate |
| pinecone | 3 | 7mo | Review | Intermediate |
| embeddings | 0 | 6mo | Review | Advanced |
| trulens-dataset-curation | 1 | 3mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by wshobson
View all by wshobson →You might also like
pinecone
davila7
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
embeddings
ruvnet
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
trulens-dataset-curation
truera
Create and curate evaluation datasets with ground truth for TruLens
embedding-strategies
javiertarazon
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 dom...
rag-index
brifl
Experimental RAG indexing utilities (scanner + indexer + retriever).
cocoindex
cocoindex-io
Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge graphs, creating search indexes, or processing data streams with incremental updates.