Agent skill · data analytics · borghei
tabular-document-review
Extract structured data from multiple documents into comparison matrix with citations. Use for bulk document review.
Why this skill is useful
Adds executable scripts for document discovery and extraction aggregation that automate legal document review processes.
What it needs
Requires python installed locally. About 7k tokens when loaded. Last updated 2026-07-21. 462 stars on the source repository.
What this skill does
⚠️ EXPERIMENTAL — This skill is provided for educational and informational purposes only. It does NOT constitute legal advice. All responsibility for usage rests with the user. Consult qualified legal professionals before acting on any output. Tabular Document Review Skill Overview Production-ready toolkit for extracting structured data from multiple legal documents into a comparison matrix with citations. Supports user-defined extraction columns, parallel processing with up to 10 agents, confidence scoring, and output in markdown table or structured JSON. Designed for legal teams performing bulk contract review, NDA comparison, employment agreement analysis, and lease review. Table of Contents Tools Reference Guides Workflows Extraction Scenarios Troubleshooting Success Criteria Scope & Limitations Anti-Patterns Tool Reference Clarify First Before the review, confirm these inputs. If any is unknown or vague, ASK — do not assume: [ ] The extraction columns — define exactly what each cell holds; a vague "Date" matches dozens of dates, while "Effective Date" with guidance does not [ ] Document set location and formats — drives discovery and how many parallel agents to allocate (ceil(N/10), max 10) [ ] Document type — contracts, NDAs, employment, leases — selects the pre-defined column set and per-column extraction guidance Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the matrix. Tools 1. Document Discovery (scripts/documentdiscovery.py) Scan a directory for legal documents and generate an inventory manifest. 2. Extraction Aggregator (scripts/extractionaggregator.py) Aggregate multiple extraction result JSONs into a unified comparison matrix. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills borghei/tabular-document-review