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.
77
66%
Does it follow best practices?
Impact
100%
1.13xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/embedding-strategies/SKILL.mdEvaluation results
100%
25%Multi-Domain Document Embedding Service
Voyage AI model selection
Voyage AI library
0%
100%
Legal model
100%
100%
Code model
100%
100%
General/default model
100%
100%
API key from env
100%
100%
Separate model instances
0%
100%
Document embedding method
100%
100%
Query embedding method
100%
100%
100%
10%Offline Research Paper Search Engine
Local model prefixes and chunking
Local embedding library
100%
100%
Recommended model name
0%
100%
Normalized embeddings
100%
100%
Query prefix applied
100%
100%
Document prefix (E5) or no-prefix (BGE)
100%
100%
Chunking with overlap
100%
100%
Metadata stored
100%
100%
Cosine similarity ranking
100%
100%
100%
Embedding Model Evaluation Toolkit
OpenAI batching and quality evaluation
OpenAI model selection
100%
100%
Batching loop
100%
100%
Batch size 100
100%
100%
Matryoshka dimensions param
100%
100%
Precision@k metric
100%
100%
Recall@k metric
100%
100%
MRR metric
100%
100%
NDCG@k metric
100%
100%
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
47823e3
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.