knowledge-graph-builder
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 data ingestion (Phase 1) and LLM-based claim extraction from papers (Phase 2).
npx skills add BioTender-max/awesome-bio-agent-skills --skill knowledge-graph-builder --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 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) │ └──────┬──────────────┘ │ ┌─────────────────┼─────────────────┐ │ │ │ ┌────────▼────────┐ ┌─────▼──────────┐ ┌────▼──────
- Overview
- Architecture
- Key Design Decisions (Lessons Learned)
- 1. Schema Design: Three-Tier Nodes
- 2. Entity Resolution: 5-Level Matching
- 3. LLM Extraction: Keep Prompts Short
- 4. Contextualized Triplets (MDKG-style)
- 5. Checkpoint/Resume for Batch Jobs
- Quick Reference
- Agent Reference Rule
- Installation
- Phase 1: Structured Data Ingestion
- Supported Data Sources
- Adding a New Data Source
Core dependencies pip install networkx requests openai pip install nilearn nibabel pip install biopython Use the neuroclaw conda environment conda activate neuroclaw
What does the knowledge-graph-builder skill do?
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 data ingestion (Phase 1) and LLM-based claim extraction from papers (Phase 2).
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill knowledge-graph-builder --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.