mcpbeat

Embedding Strategies

dokhacgiakhoa/embedding-strategies

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.

4k tokens
context cost
the whole folder, loaded on every use
10
files
instructions only
0
copies elsewhere
how many repositories repackaged it
505
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI --skill embedding-strategies

What comes with it

13 909 bytes besides the instruction
sub-skills/1-embedding-model-comparison.md
sub-skills/2-embedding-pipeline.md
sub-skills/donts.md
sub-skills/dos.md
sub-skills/template-1-openai-embeddings.md
sub-skills/template-2-local-embeddings-with-sentence-transformers.md
sub-skills/template-3-chunking-strategies.md
sub-skills/template-4-domain-specific-embedding-pipeline.md
sub-skills/template-5-embedding-quality-evaluation.md

The instruction itself

15 sections, as written by the author

Embedding Strategies

Guide to selecting and optimizing embedding models for vector search applications.

Do not use this skill when

  • The task is unrelated to embedding strategies
  • You need a different domain or tool outside this scope

Instructions

  • Clarify goals, constraints, and required inputs.
  • Apply relevant best practices and validate outcomes.
  • Provide actionable steps and verification.
  • If detailed examples are required, open resources/implementation-playbook.md.

Use this skill when

  • 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

🧠 Knowledge Modules (Fractal Skills)

1. 1. Embedding Model Comparison

2. 2. Embedding Pipeline

3. Template 1: OpenAI Embeddings

4. Template 2: Local Embeddings with Sentence Transformers

5. Template 3: Chunking Strategies

6. Template 4: Domain-Specific Embedding Pipeline

7. Template 5: Embedding Quality Evaluation

8. Do's

9. Don'ts

How to use it

Copy the folder

Take dokhacgiakhoa/embedding-strategies from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.