Home / cuhk-aim-group / neurodiscovery · skills/connectome-discovery/SKILL.md · GitHub

connectome-discovery skillA

connectome-discovery is agent-read markdown (skill) from cuhk-aim-group/neurodiscovery: Use this workflow skill whenever the user wants to turn connectome-model outputs into network discoveries: compare aligned brain maps, compute permutation significance, rank neuromodulation targets, summarize atlas-level effects, or combine CPM with spatial interpretation. Triggers include 'connectome discovery', 'network map similarity', 'permutation P value', 'target ranking', 'neuromodulation target', and 'spatial connectome interpretation'..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Connectome Discovery Workflow

## Overview

`connectome-discovery` is a scientific interpretation workflow, not a second
CPM implementation. It consumes fitted-model outputs or aligned network maps
and produces map similarities, empirical significance, and candidate target
rankings.

| Stage | Canonical owner |
|---|---|
| Connectome prediction | `cpm`, BrainGNN, BNT, or another model skill |
| Atlas/space validation | `fmri-skill`, `nibabel-skill` |
| Map similarity and permutation | `models/connectome_discovery/mapping.py` |
| Surface/network rendering | `brain-visualization` |

---

## Installation

```bash
pip install numpy scipy pandas
```

---

## Workflows

### 1. Generate model evidence

Run `cpm` or another connectome model and freeze its held-out predictions,
selected edges, atlas, and node ordering.

### 2. Align maps

Reference and candidate maps must use the same atlas, node order, hemisphere
convention, and value orientation. Resampling or atlas mapping must be recorded.

### 3. Score and rank targets

Use `models/connectome_discovery/mapping.py` for:

- `cosine_similarity_map`
- `permutation_pvalue`
- `rank_targets`
…

Read the whole file at its exact version.

How to install

Latest version
mdr add cuhk-aim-group/neurodiscovery/connectome-discovery@git:20260825.cbd02ff
Exact content
mdr add cuhk-aim-group/neurodiscovery/connectome-discovery@sha256:fc80734b97911f44

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_abousbrdjgbdfol3.svg)](https://markdownregistry.com/a/art_abousbrdjgbdfol3)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260825.cbd02ff latest2026-08-25 cbd02ff 2,860 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (2860 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 · 91 stars · license MIT · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_abousbrdjgbdfol3
GET https://markdownregistry.com/api/v1/resolve?ref=cuhk-aim-group/neurodiscovery/connectome-discovery
GET https://markdownregistry.com/api/v1/blob/fc80734b97911f44e1e0e79cdab6c915b075307e6ebd42c0fda449536ddf75cc

Your agent 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.

More from cuhk-aim-group/neurodiscovery

abcd-skill skill
cuhk-aim-group/neurodiscovery · skills/abcd-skill/SKILL.md · Use this skill whenever the user wants an end-to-end workflow for the ABCD Study dataset, including controlled access…
git:20260825.f7533a2 · audit A · 91 stars
abide-skill skill
cuhk-aim-group/neurodiscovery · skills/abide-skill/SKILL.md · Use this skill whenever the user wants an end-to-end workflow for the ABIDE (Autism Brain Imaging Data Exchange)…
git:20260505.e9ddd22 · audit A · 91 stars
academic-research-hub skill
cuhk-aim-group/neurodiscovery · skills/academic-research-hub/SKILL.md · Use this skill when users need to search academic papers, download research documents, extract citations, or gather…
git:20260506.86420c0 · audit A · 91 stars
adhd200-skill skill
cuhk-aim-group/neurodiscovery · skills/adhd200-skill/SKILL.md · Use this skill whenever the user wants an end-to-end workflow for the ADHD-200 dataset, including download, BIDS…
git:20260505.e9ddd22 · audit A · 91 stars
adni-skill skill
cuhk-aim-group/neurodiscovery · skills/adni-skill/SKILL.md · Use this skill whenever the user wants an end-to-end workflow for ADNI or ADNI-DOD data, including controlled LONI IDA…
git:20260825.f7533a2 · audit A · 91 stars
aibl-skill skill
cuhk-aim-group/neurodiscovery · skills/aibl-skill/SKILL.md · Use this skill whenever the user wants an end-to-end workflow for the AIBL (Australian Imaging, Biomarkers and…
git:20260506.f8d0216 · audit A · 91 stars
aomic-skill skill
cuhk-aim-group/neurodiscovery · skills/aomic-skill/SKILL.md · Use this skill whenever the user wants an end-to-end workflow for the AOMIC (Amsterdam Open MRI Collection) dataset…
git:20260506.f8d0216 · audit A · 91 stars
asl-skill skill
cuhk-aim-group/neurodiscovery · skills/asl-skill/SKILL.md · Use this skill whenever the user wants to process Arterial Spin Labeling (ASL) perfusion MRI data including CBF…
git:20260506.f8d0216 · audit A · 91 stars
beautiful-log skill
cuhk-aim-group/neurodiscovery · skills/beautiful-log/SKILL.md · Use this skill after a conversation or task is completed when the user wants a clean, beautiful HTML chat log. It keeps…
git:20260506.86420c0 · audit A · 91 stars
bids-organizer skill
cuhk-aim-group/neurodiscovery · skills/bids-organizer/SKILL.md · Use this skill whenever the user wants to automatically organize raw neuroimaging data (DICOM, NIfTI, EEG, etc.) into a…
git:20260506.86420c0 · audit A · 91 stars
bnt skill
cuhk-aim-group/neurodiscovery · skills/bnt/SKILL.md · Use this model doc whenever the user wants to run BrainNetworkTransformer for fMRI phenotype prediction, including data…
git:20260515.bfd8dae · audit A · 91 stars
bold5000-skill skill
cuhk-aim-group/neurodiscovery · skills/bold5000-skill/SKILL.md · Use this skill whenever the user wants an end-to-end workflow for the BOLD5000 dataset, including download, BIDS…
git:20260505.e9ddd22 · audit A · 91 stars

Every file in cuhk-aim-group/neurodiscovery

Browse by kind, by grade A, or by owner.