Source profileQuality 71/100

wshobson/agents/plugins/llm-application-dev/skills/vector-index-tuning/SKILL.md

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.

Source repository stars
38,313
Declared platforms
0
Static risk flags
1
Last source update
2026-07-22
Source checked
2026-07-28
DecisionCompatibilityInstallWorkflowPermissionsEvidenceSource

Decision brief

What it does—and where it fits

Guide to optimizing vector indexes for production performance.

Best for

  • Tuning HNSW parameters
  • Implementing quantization
  • Optimizing memory usage

Not for

  • Tasks that require unconfirmed production actions or broad system permissions.
  • Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/wshobson/agents --skill "plugins/llm-application-dev/skills/vector-index-tuning"
Safe inspection promptEditorial

Inspect the Agent Skill "vector-index-tuning" from https://github.com/wshobson/agents/blob/c4b82b0ad771190355eb8e204b1329732a18449a/plugins/llm-application-dev/skills/vector-index-tuning/SKILL.md at commit c4b82b0ad771190355eb8e204b1329732a18449a. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    When to Use This Skill

    Tuning HNSW parameters

    Tuning HNSW parametersImplementing quantizationOptimizing memory usage
  2. 02

    Core Concepts

    Review the “Core Concepts” section in the pinned source before continuing.

    Review and apply the “Core Concepts” source section.
  3. 03

    1. Index Type Selection

    Review the “1. Index Type Selection” section in the pinned source before continuing.

    Review and apply the “1. Index Type Selection” source section.
  4. 04

    2. HNSW Parameters

    Review the “2. HNSW Parameters” section in the pinned source before continuing.

    Review and apply the “2. HNSW Parameters” source section.

Permission review

Static risk signals and limitations

Reads files

low · line 47

The documentation asks the agent to read local files, directories, or repositories.

Full template library and detailed worked examples live in `references/details.md`. Read that file when you need the concrete templates.

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score71/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars38,313SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
wshobson/agents
Skill path
plugins/llm-application-dev/skills/vector-index-tuning/SKILL.md
Commit
c4b82b0ad771190355eb8e204b1329732a18449a
License
MIT
Collected
2026-07-28
Default branch
main
View the original SKILL.md

Vector Index Tuning

Guide to optimizing vector indexes for production performance.

When to Use This Skill

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

Core Concepts

1. Index Type Selection

Data Size           Recommended Index
────────────────────────────────────────
< 10K vectors  →    Flat (exact search)
10K - 1M       →    HNSW
1M - 100M      →    HNSW + Quantization
> 100M         →    IVF + PQ or DiskANN

2. HNSW Parameters

ParameterDefaultEffect
M16Connections per node, ↑ = better recall, more memory
efConstruction100Build quality, ↑ = better index, slower build
efSearch50Search quality, ↑ = better recall, slower search

3. Quantization Types

Full Precision (FP32): 4 bytes × dimensions
Half Precision (FP16): 2 bytes × dimensions
INT8 Scalar:           1 byte × dimensions
Product Quantization:  ~32-64 bytes total
Binary:                dimensions/8 bytes

Templates and detailed worked examples

Full template library and detailed worked examples live in references/details.md. Read that file when you need the concrete templates.

Best Practices

Do's

  • Benchmark with real queries - Synthetic may not represent production
  • Monitor recall continuously - Can degrade with data drift
  • Start with defaults - Tune only when needed
  • Use quantization - Significant memory savings
  • Consider tiered storage - Hot/cold data separation

Don'ts

  • Don't over-optimize early - Profile first
  • Don't ignore build time - Index updates have cost
  • Don't forget reindexing - Plan for maintenance
  • Don't skip warming - Cold indexes are slow