Home / cuhk-aim-group / neurodiscovery · GitHub

knowledge-graph-builder SKILL.md skillA

knowledge-graph-builder 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/knowledge-graph-builder@git:20260914.cd009af

Pins git:20260914.cd009af 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/knowledge-graph-builder/SKILL.md
Versions recorded: 5
Latest version: git:20260914.cd009af, committed Sep 14, 2026
First version recorded: May 5, 2026
Size: 21,187 bytes
Repository stars: 93
License: MIT

Use this skill when users need to build, populate, or extend a domain-specific knowledge graph from literature and structured databases. Triggers include: 'build knowledge graph', 'extract claims from papers', 'ingest data into graph', 'batch extract claims', 'knowledge graph construction', 'populate graph from PubMed', 'extract structured claims', 'ingest atlas data', or any request involving knowledge graph population from scientific literature or biomedical databases. Covers both structured…

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

# Knowledge Graph Builder

## Overview

This skill provides a reusable framework for constructing domain-specific knowledge graphs by combining two complementary data pipelines:

- **Phase 1 — Structured Ingestion**: Import concepts and relations from curated databases, ontologies, and brain atlases (e.g., NeuroNames, MeSH, DisGeNET, Cognitive Atlas, Nilearn atlases).
- **Phase 2 — Literature Claim Extraction**: Use LLMs to extract structured scientific claims from PubMed paper abstracts, then resolve entities and ingest into the graph.
- **Phase 3 — Hypothesis Engine**: Traverse the graph to find novel connections, contradictions, and unexplored gaps — turning raw claims into testable research hypotheses.

The output is a directed knowledge graph (NetworkX DiGraph + JSON serialization) where nodes represent domain concepts and claims, and edges represent typed relationships with confidence scores and provenance.

**Primary implementation**: `neurooracle/` in the NeuroClaw project.

## Architecture

```
                    ┌─────────────────────┐
                    │  Knowledge Graph     │
                    │  (NetworkX DiGraph)  │
                    └──────┬──────────────┘
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add cuhk-aim-group/neurodiscovery/knowledge-graph-builder@sha256:12d07e6a0b78ff62

The line at the top of this page pins the label git:20260914.cd009af, 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_odz6jiirt5xw5iex.svg)](https://markdownregistry.com/a/art_odz6jiirt5xw5iex)

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

Versions

The registry has recorded 5 versions of this file, between May 5, 2026 and Sep 14, 2026, about one every 33 days.

version	committed	commit	size	audit
git:20260914.cd009af latest	2026-09-14	cd009af	21,187 B	A	view · diff
git:20260606.3980137	2026-06-06	3980137	17,545 B	A	view · diff
git:20260519.c62dcfb	2026-05-19	c62dcfb	17,528 B	A	view · diff
git:20260506.86420c0	2026-05-06	86420c0	17,717 B	A	view · diff
git:20260505.e9ddd22	2026-05-05	e9ddd22	17,691 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 (21187 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_odz6jiirt5xw5iex
GET https://markdownregistry.com/api/v1/resolve?ref=cuhk-aim-group/neurodiscovery/knowledge-graph-builder
GET https://markdownregistry.com/api/v1/blob/12d07e6a0b78ff621962a6a3daa64f46d856fbdae57bce1c2c60311440c91332

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.