Agent skill · research science · borghei
legal-red-team
Adversarial verification for AI-generated legal content. Use when fact-checking legal documents, validating citations, detecting hallucinations, scoring document quality, or assessing distribution readiness.
Why this skill is useful
Adds a comprehensive adversarial verification framework with executable scripts for legal document validation that the AI cannot generate on its own.
What it needs
Requires python installed locally. About 9k 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. Legal Red Team Production-ready adversarial verification framework for AI-generated legal content. Covers factual accuracy, citation validation, arithmetic checking, speculation detection, and distribution readiness scoring. --- Table of Contents Verification Categories Tools Six-Step Methodology Severity Taxonomy Quality Score Known Hallucination Patterns Reference Guides Workflows Troubleshooting Success Criteria Scope and Limitations Anti-Patterns Tool Reference --- Verification Categories Every AI-generated legal document must be checked across 6 categories. # Category What to Check Red Flags --- ---------- -------------- ----------- 1 Factual Accuracy Dates, references, numbers, entity names, timelines Wrong effective dates, confused entity names, incorrect amounts 2 Legal Authority Citations Primary/secondary sources, format, hierarchy, currency Non-existent articles, wrong section numbers, outdated citations 3 Arithmetic Validation Timelines, percentages, financial calculations, deadlines Date math errors, percentage miscalculations, compounding mistakes 4 Source Verification Verifiable claims, official sources, cross-referencing Unverifiable assertions stated as fact, single-source claims 5 Speculation Detection Opinion vs fact, uncertainty language, predictive claims Predictions stated as certainty, guidance treated as binding law 6 Disclaimer Adequacy Legal advice disclaimers, jurisdiction, date, professional consultation Missing disclaimers, overly broad claims, no jurisdiction limits --- Clarify First Before the verification, confirm these inputs. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills borghei/legal-red-team