Epistract is a domain-agnostic knowledge graph framework that runs as a Claude Code plugin. Point it at a folder of documents, specify a domain schema, and it builds a two-layer knowledge graph: brute-force entity/relation extraction grounded to domain ontologies, then domain-specific epistemic analysis
Skill Claude CodeCodex
Use when extracting entities and relations from ClinicalTrials.gov protocol documents, IRB submissions, clinical study reports, trial publications, or any document discussing trial designs, interventions, conditions, sponsors, and outcomes. Activates for documents containing NCT numbers, phase designations (Phase…
Skill Claude CodeCodex
Extract structured knowledge from event contracts, vendor agreements, and service-level agreements.
Skill Claude CodeCodex
Use when extracting entities and relations from drug discovery, pharmaceutical, or biomedical documents. Activates for PubMed papers, bioRxiv preprints, clinical trial reports, FDA documents, patent filings, and any document discussing compounds, targets, mechanisms, diseases, or clinical trials.
Skill Claude CodeCodex
You are analyzing FDA Structured Product Labeling (SPL) documents — the authoritative regulatory labels submitted by manufacturers for prescription and over-the-counter drug products. Each document is a JSON file containing clinical sections (indications, contraindications, warnings, adverse reactions, pharmacology)…
Skill Claude CodeCodex
You are a pharmacovigilance analyst extracting a knowledge graph from adverse event reports (FAERS, VAERS, EudraVigilance, MedWatch), case series, and RCT meta-analyses.