embedding-strategies – Other skill for AI agents
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.
Install the embedding-strategies skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/embedding-strategies-726ce.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /embedding-strategies – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/embedding-strategies-726ce.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $embedding-strategies – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/embedding-strategies-726ce.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /embedding-strategies – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/embedding-strategies-726ce.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /embedding-strategies – then describe the task you want done.
SKILL.md content
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
Related skills
- employment-contract-templates – Create employment contracts, offer letters, and HR policy documents following legal best…
- ceo-advisor – Executive leadership guidance for strategic decision-making, organizational development…
- cfo-advisor – Financial leadership for startups and scaling companies. Financial modeling, unit…
- creative-ideation – Generate ideas via named methods from creative practice.
- eval-harness-first – Build the evaluation harness that gates every fine-tuning run — golden sets…
- change-management – Framework for rolling out organizational changes without chaos. Covers the ADKAR model…
- decision-questionnaire – Turn an unanswerable decision into a questionnaire doc.
- apk-redteam-pipeline – End-to-end Android APK red-team pipeline