Vector Index Tuning

If you're running vector search at scale and need to squeeze out better latency or recall without blowing your memory budget, this walks you through the tuning process systematically. It covers HNSW parameter sweeps, quantization trade-offs, and the metrics you should track before changing anything in production. The playbook approach is solid: establish baselines, benchmark on real queries, validate on staging. One thing to note is that it assumes you already have workload data and ground truth, so if you're still in the exploratory phase or don't have production metrics yet, you'll want to get that sorted first before diving into parameter optimization.

skills.sh installs: 191
GitHub stars: 39.4K
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill vector-index-tuning --agent claude-code

Installs into .claude/skills of the current project.

Files

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

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

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