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 building RAG systems, search engines, or when neither vector nor keyword search alone provides sufficient recall (e.g., domain-specific terms, exact codes).
references/details.md for concrete templates and worked examplesA hybrid retrieval implementation with improved recall and precision, combining semantic and exact-match signals, ready to integrate into RAG or search pipelines.
Use Cases
A team builds a RAG chatbot over internal docs. Pure vector search misses queries with product codes and error strings. Using this skill, they add a keyword path and fuse with RRF, then log both scores and A/B test. Result: recall on exact-term questions rises sharply, support agents find answers faster, reducing escalation rate.
A legal tech startup indexes contracts with domain vocabulary. Vector search returns semantically close but wrong clauses. They apply hybrid search with linear weighted fusion tuned on labeled queries, plus cross-encoder rerank. Outcome: higher precision on clause retrieval, lawyers review less irrelevant text, saving billable hours.
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