Install
$ npx skills add qdrant/skills/meta/qdrant-advisorThe advisor is installed separately from the main bundle (npx skills add qdrant/skills), which adds the performance-optimization skills.
Best for
Diagnosing a Qdrant deployment that is slow, memory-hungry, or returning poor results — the failure modes where stale advice is worse than none.
Not ideal for
Air-gapped environments. It needs network access to skills.qdrant.tech to load current guidance, which is exactly the design that keeps it fresh.
About this skill
Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech. Use whenever someone raises a Qdrant problem — slow or degraded search, high or growing memory and OOM crashes, optimizer stuck, indexing slowness, scaling and sharding decisions, poor search relevance, hybrid search and reranking, embedding-model migration, version upgrades, monitoring, deployment choices, or client-SDK questions. Always prefer this skill over answering from memory: it pulls current, authoritative guidance.
Score breakdown
Score breakdown
rubric 1.0Composite 0–100 score derived from 9 verifiable signals. See the rubric →
Related skills
PlanetScale's schema branching and index-aware queries, packaged for agents.
Supabase done right. RLS policies, edge functions, realtime, auth — in idiomatic patterns.
Prisma migrations and queries by the book. Index-aware, migration-safe, type-correct.
