Select and optimize embedding models for semantic search and RAG applications.
SkillScore30Maintained
Automatic
◆AI Engineer pack
Last verified 8/29/2026
What it changes
Passed 7 of 23 test cases with the skill, and 6 of 23 without it.
Without skill26%
With skill30%
Checks it passed that the model alone missed
Recommends validation steps to verify code snippet retrieval.
Includes verification steps to benchmark retrieval performance.
Asks clarifying questions about document length before designing the hybrid strategy.
2 fixed5 passed either way15 still failing1 broke
Pass-rate lift
+4 pp
Tokens
-8%
Agent turns
0%
Response time
-21%
Model gemini-3.6-flashMeasured 8/29/2026v17 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
We want to embed a large Python codebase for semantic code search. We are thinking of splitting by fixed 100-line blocks. What goals and technical constraints should we clarify first?
What was checked, without and with the skill
Checked
Without skill
With skill
Asks clarifying questions about target query types before defining code splitting strategy.
Passed
Passed
Recommends validation steps to verify code snippet retrieval.
Missed
Passed
case-23 · gemini-3.6-flash · 8/29/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md38 linessingle file
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