菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | agentdb-mmr |
| description | 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. |
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.Walk the causal graph in AgentDB to explain why two memories are connected, or trace a root cause. Use when the user asks "why did X happen", "what led to Y", or after an incident.
Record a causal relationship between two memories in AgentDB — "X caused Y", "A supersedes B", "patch-foo depends-on patch-bar". Use when the user is documenting cause/effect, dependencies, supersessions, or after-action analysis.
Store memories in tier-aware hierarchical memory — working / short-term / long-term — and recall with tier filters. Use for working-set context that should fade, vs facts that should persist, vs patterns that should be searchable forever.
Initialize an AgentDB Cognitive Container (.rvf file) in the current project. Sets up storage, embedder config, and the agentdb MCP server. Use when the user is starting a new project that needs vector memory, or asks to "set up agentdb" / "init agentdb".
Show AgentDB health — pattern count, embedder status, cache hit rate, learning gain since init. Use when the user asks "is agentdb working?", "how many memories?", "show agentdb stats", or after long-running sessions to confirm state.
Execute Cypher queries against AgentDB's graph backend. Use when the user wants to write a custom traversal that the standard tools don't cover, or when explaining graph state.