Stats
Actions
Tags
From agentdb-search
Maximal Marginal Relevance rerank — get diverse top-k instead of redundant top-k. Use when standard search returns 5 near-duplicates, or when you want broader coverage of a topic.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentdb-search:agentdb-mmrThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Diversity reranking on top of vector search. MMR balances relevance to the query with novelty among the picked results.
Diversity reranking on top of vector search. MMR balances relevance to the query with novelty among the picked results.
agentdb_diversity_rank(
query: <embedding | string>
candidates: <id list> // typically the top-50 from vector search
k: 5 // final size
lambda: 0.5 // 0=pure diversity, 1=pure relevance
)
MMR picks greedily:
score(i) = λ · sim(query, i) - (1-λ) · max sim(i, picked_j)
High λ → behaves like vanilla top-k (relevance-only). Low λ → emphasizes novelty among picks.
Default λ = 0.5 is a sensible balance for most uses.
agentdb_diversity_rank with k=5.This is a 50→5 reduction with much higher topic coverage than top-5 directly.
lambda: 'auto' and let it learn.npx claudepluginhub ruvnet/agentdb --plugin agentdb-searchLLM-powered multi-attribute reranking of candidate sets from SQL or lists via pairwise comparisons on clarity, technical depth, insight. Supports custom prompts, model tiers, TopK.
Covers RAG architecture including design patterns, chunking strategies, embedding models, retrieval techniques, hybrid search, and context assembly for LLM pipelines.
Diagnoses Qdrant search relevance issues (poor results, low precision/recall) and guides tuning of embedding models, HNSW parameters, query strategies, and hybrid search with reranking.