vector-index-tuning SKILL.md skillA
vector-index-tuning from wshobson/agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wshobson/agents/vector-index-tuning@git:20260522.be57c0bPins git:20260522.be57c0b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wshobson/agents
- Path
plugins/llm-application-dev/skills/vector-index-tuning/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260522.be57c0b, committed May 22, 2026
- First version recorded
- Dec 16, 2025
- Size
- 2,325 bytes
- Repository stars
- 42,320
- License
- MIT
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 | Parameter | Default | Effect | | ------------------ | ------- | ---------------------------------------------------- | | **M** | 16 | Connections per node, ↑ = better recall, more memory | | **efConstruction** | 100 | Build quality, ↑ = better index, slower build | | **efSearch** | 50 | Search 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 …
Read the whole file at its exact version.
How to install
mdr add wshobson/agents/vector-index-tuning@sha256:fc6a365161f5fd7eThe line at the top of this page pins the label git:20260522.be57c0b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_j63elja2ysf6ahwo)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Dec 16, 2025 and May 22, 2026, about one every 52 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260522.be57c0b latest | 2026-05-22 | be57c0b | 2,325 B | A | view · diff |
| git:20260307.47a5dbc | 2026-03-07 | 47a5dbc | 15,249 B | A | view · diff |
| git:20260119.5684887 | 2026-01-19 | 5684887 | 15,424 B | A | view · diff |
| git:20251216.01d93fc | 2025-12-16 | 01d93fc | 15,268 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2325 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
wshobson/agents · 42,320 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_j63elja2ysf6ahwo GET https://markdownregistry.com/api/v1/resolve?ref=wshobson/agents/vector-index-tuning GET https://markdownregistry.com/api/v1/blob/fc6a365161f5fd7ea08792759db7b358683aed8b410a4418c65bc1e61b971355
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.