From agentdb-search
Search with feature attributions — return WHY each match scored where it did. Use when debugging recall quality, auditing for bias, or explaining results to a user.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentdb-search:agentdb-explainable-recallThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Standard search returns scores; explainable recall returns *features* — which dimensions of the embedding (or which keywords in hybrid search) drove the match.
Standard search returns scores; explainable recall returns features — which dimensions of the embedding (or which keywords in hybrid search) drove the match.
agentdb_explainable_recall(
query: <embedding | string>
k: 5
features: 'embedding-dims' | 'bm25-tokens' | 'hybrid-both' | 'metadata'
)
Returns: [
{
id, score,
explanation: {
topDims?: [{ dim: 12, contribution: 0.18 }, ...],
topTokens?: [{ token: "jwt", contribution: 0.31 }, ...],
metadataMatch?: { topic: 'auth', project: 'api' }
}
},
...
]
| Use | Features setting |
|---|---|
| Debug an unexpected high-score | embedding-dims — see which dims spiked |
| Verify keyword fall-back works | bm25-tokens — see if exact terms were the driver |
| Confirm metadata filters fired | metadata — see which filter values matched |
| Build user-facing UI | hybrid-both — show both text-level + dim-level signals |
npx claudepluginhub ruvnet/agentdb --plugin agentdb-searchDiagnoses Qdrant search relevance issues (poor results, low precision/recall) and guides tuning of embedding models, HNSW parameters, query strategies, and hybrid search with reranking.
Interprets raw recall results by clustering, flagging contradictions, and producing actionable output. Useful when recall returns 5+ results or user asks a factual/historical question with graph coverage.