Eval Dataset Nda Prompts 30

Use when running the NDA benchmark that tests drafting, review, intake, and edge-case handling across LB/KSA/UAE/DIFC/FR/UK. Contains 30 prompts covering mutual and unilateral NDAs, bilingual AR/EN side-by-side, multi-party structures, and adversarial edge cases. Primary benchmark for confidentiality-related AI capabilities.

sboghossian Updated

File contents

sboghossian/mini-claude-for-legal/tree/main/skills/eval/eval-dataset-nda-prompts-30 commit d09826e7d4

Frequently asked questions

npx skillmds@latest add sboghossian-mini-claude-for-legal/eval-dataset-nda-prompts-30