← LeaderboardThe Skill Leaderboard

vector-index-tuning

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

Description awaits a fresh source check.

Published by rmyndharis ↗rmyndharis/antigravity-skills

Try your first task

vector-index-tuning

Start a fresh conversation. Replace the highlighted placeholders.

Use vector-index-tuning to benchmark vector-index configurations on a staging dataset using [real queries and ground truth] against [latency, recall, QPS, data-size, and memory targets], then recommend the best configuration and report recall, latency, QPS, and memory trade-offs without applying changes to production.

Required inputs

  • [real queries and ground truth]
  • [latency, recall, QPS, data-size, and memory targets]

User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗

SKILL.md

name: vector-index-tuningdescription: Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

Vector Index Tuning

Guide to optimizing vector indexes for production performance.

Use this skill when

  • Tuning HNSW parameters
  • Implementing quantization
  • Optimizing memory usage
  • Reducing search latency
  • Balancing recall vs speed
  • Scaling to billions of vectors

Do not use this skill when

  • You only need exact search on small datasets (use a flat index)
  • You lack workload metrics or ground truth to validate recall
  • You need end-to-end retrieval system design beyond index tuning

Instructions

  1. Gather workload targets (latency, recall, QPS), data size, and memory budget.
  2. Choose an index type and establish a baseline with default parameters.
  3. Benchmark parameter sweeps using real queries and track recall, latency, and memory.
  4. Validate changes on a staging dataset before rolling out to production.

Refer to resources/implementation-playbook.md for detailed patterns, checklists, and templates.

Safety

  • Avoid reindexing in production without a rollback plan.
  • Validate changes under realistic load before applying globally.
  • Track recall regressions and revert if quality drops.

Resources

  • resources/implementation-playbook.md for detailed patterns, checklists, and templates.