skills sourced live from GitHub · all skills listed are free · each skill is provided under its author's license.
home / AI Agents & MCP / Embedding Strategies Skill by @wshobson
The skill is the plugins/llm-application-dev/skills/embedding-strategies folder inside that repository. Copy it into the folder your agent loads skills from; check your agent's documentation for where that is.
Advice on choosing embedding models and chunking approaches for semantic search and RAG, including tuning for specific domains.
Compares model options, outlines a basic embedding pipeline and lists do's and don'ts such as reducing dimensions and handling multilingual text. Detailed templates and worked examples sit in separate reference files.
The original SKILL.md is organised into these sections:
Written and maintained by @wshobson. It is published under the MIT license, which allows reuse with attribution. See the author profile. SkillDirectory does not claim authorship: this page adds our own review and links back to the original, and the skill's text belongs to its author.
# 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 | …
Excerpt only, quoted from the author's repository. Open the repository for the complete file.