Home / cuhk-aim-group / neurodiscovery · GitHub

wmh-segmentation SKILL.md skillA

wmh-segmentation from cuhk-aim-group/neurodiscovery is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add cuhk-aim-group/neurodiscovery/wmh-segmentation@git:20260506.86420c0

Pins git:20260506.86420c0 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: cuhk-aim-group/neurodiscovery
Path: skills/wmh-segmentation/SKILL.md
Versions recorded: 5
Latest version: git:20260506.86420c0, committed May 6, 2026
First version recorded: Mar 25, 2026
Size: 6,387 bytes
Repository stars: 93
License: MIT

Use this skill whenever the user wants to perform automated white matter hyperintensity (WMH) segmentation on structural MRI data using the MARS-WMH nnU-Net model. Requires one FLAIR and one T1w NIfTI image (no contrast). Triggers include: 'wmh', 'white matter hyperintensities', 'WMH segmentation', 'MARS-WMH', 'wmh-nnunet', 'segment FLAIR T1', 'white matter lesions', 'vascular WMH', 'mars wmh', or any request to run nnU-Net WMH segmentation on FLAIR+T1w pair.

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

# WMH Segmentation (MARS-WMH nnU-Net)

## Overview
MARS-WMH is the state-of-the-art, clinically-validated deep-learning tool (nnU-Net architecture) for segmenting brain white matter hyperintensities of presumed vascular origin. It takes a FLAIR image (recommended 1 mm isotropic) and a co-registered or registrable T1w image (1 mm isotropic, no contrast) and outputs a precise WMH segmentation mask in NIfTI format (returned in the original input resolution).

This skill serves as the **NeuroClaw interface-layer wrapper** for the official MARS-WMH Docker container (`ghcr.io/miac-research/wmh-nnunet:latest`) and strictly follows the hierarchical design:

1. Check whether Docker (with NVIDIA Container Toolkit) is installed (`docker --version` + `nvidia-smi` via `claw-shell`).
2. If `nvidia-smi` fails → immediately print the exact NVIDIA Container Toolkit installation commands and instruct the user to run them manually before retry.
3. If paths not provided → interactively ask the user for FLAIR and T1w full paths and confirm they exist on disk.
4. If paths provided → verify file existence and readability.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add cuhk-aim-group/neurodiscovery/wmh-segmentation@sha256:a7cce033e4d91dd3

The line at the top of this page pins the label git:20260506.86420c0, 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.

Badge

[![mdr](https://markdownregistry.com/badge/art_czyjldpsrsdhp2ju.svg)](https://markdownregistry.com/a/art_czyjldpsrsdhp2ju)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Mar 25, 2026 and May 6, 2026, about one every 11 days.

version	committed	commit	size	audit
git:20260506.86420c0 latest	2026-05-06	86420c0	6,387 B	A	view · diff
git:20260505.e9ddd22	2026-05-05	e9ddd22	6,396 B	A	view · diff
git:20260328.891ed93	2026-03-28	891ed93	6,339 B	A	view · diff
git:20260325.72d2cbf	2026-03-25	72d2cbf	6,406 B	A	view · diff
git:20260325.df6f256	2026-03-25	df6f256	6,361 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (6387 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

GitHub

cuhk-aim-group/neurodiscovery · 93 stars · license MIT · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_czyjldpsrsdhp2ju
GET https://markdownregistry.com/api/v1/resolve?ref=cuhk-aim-group/neurodiscovery/wmh-segmentation
GET https://markdownregistry.com/api/v1/blob/a7cce033e4d91dd3d028d0071e7daf8747b367e897b210ba73b48a82c967c74f

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.