Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
When selecting embedding models for RAG/semantic search, designing chunking strategies, or optimizing domain-specific embedding quality.
references/details.md for templates and worked examplesA correctly chosen embedding model and optimized ingestion pipeline that improves retrieval recall and cost-efficiency for vector search applications.
Use Cases
A team building a RAG chatbot over legal contracts struggles with poor retrieval. Using this skill, they consult the model table, pick voyage-law-2 for legal text, apply semantic chunking with overlap, and normalize embeddings. Result: higher recall and fewer missed clauses, with cached vectors cutting API cost.
A startup needs multilingual search across docs in 5 languages. The skill guides them to multilingual-e5-large, warns against mixing models, and sets chunk size within token limits. They build a unified vector index with metadata filtering, achieving consistent cross-language recall without truncation.
Skill Relationships
Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.
Tier 1 · These Skills Use Me
Tier 2 · Current Skill
Tier 3 · I Use These Skills
Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.
Skill File