epistract
01Plugin Claude Code
Plugin marketplace listing 1 plugin: epistract.
Plugin Claude Code
Plugin marketplace listing 1 plugin: epistract.
Plugin Claude Code
Cross-domain knowledge graph framework. Extract structured knowledge from any document corpus. Pre-built domains: drug discovery (biomedical literature), contract analysis (vendor contracts), clinical trials (ClinicalTrials.gov v2 + PubChem enrichment via --enrich), and FDA product labels (Structured Product Labeling.
Instructions file
Instructions for usathyan/epistract, covering project, constraints, technology stack, languages and runtime.
Agent
Fetch a batch of PubMed articles for the epistract corpus. Dispatched by /epistract-acquire when processing many articles in parallel. Each agent handles a batch of PMIDs independently.
Agent
Extract entities and relations from a single document for the epistract knowledge graph. Dispatched by /epistract-ingest when processing multiple documents in parallel. Each agent handles one document independently. Domain-aware: reads the domain SKILL.md for entity types, relation types, and naming standards.
Agent
Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.
Command
Search PubMed and download articles into a local corpus for epistract ingestion.
Command
Add source documents to an epistract project corpus (deduplicated by content hash).
Command
Fetch one or more URLs into an epistract project corpus (deduplicated by content hash).
Command
Ask questions about extracted contract knowledge graph — answers with citations, cost breakdowns, and risk analysis.
Command
Build knowledge graph from existing epistract extractions.
Command
Launch the interactive web workbench for exploring a knowledge graph — chat + force-directed graph + source inspector.
Command
Remove a domain — archive to a recoverable location or permanently delete — with explicit confirmation.
Command
List all installed domains — active and archived — with entity type count, relation type count, last-modified date, and status.
Command
Edit a domain component — schema, extraction prompt, or epistemic analysis — via a guided conversational wizard.
Command
Create a new domain package from sample documents using guided wizard.
Command
Run arXiv-backed quality passes over a project's knowledge graph — triple judging, entity resolution, and a bi-temporal epistemic layer.
Command
Analyze epistemic patterns (hypotheses, contradictions, conditional claims) in a built knowledge graph and produce a Super Domain claims layer.
Command
Export knowledge graph to GraphML, GEXF, CSV, SQLite, or JSON.
Command
Incrementally index an epistract project's corpus and graph for hybrid search.
Command
Ingest scientific documents and build a drug discovery knowledge graph.
Command
Create a new named epistract project (persistent dataset) with its own corpus, graph, and search index.
Command
List, inspect, or delete epistract projects in the registry.
Command
Search entities in the drug discovery knowledge graph.