The Prompt Library
Attorney-reviewed prompts for Claude, ChatGPT, and Gemini. Filtered by practice area, jurisdiction, and task — with built-in anti-hallucination safeguards on every prompt.
Generate a full commercial contract draft or paste a contract and get a clause-by-clause redline with HIGH/MEDIUM/LOW risk ratings. Built for Claude's 200K context window.
Draft a non-compete clause for a mutual NDA enforceable under California law. We tested this prompt on Claude and Gemini — see why Claude wins on §16600.
Two-in-one demand letter prompt: a pre-litigation demand and an IP cease and desist. Firm, factual, and written like a judge will read it someday.
Draft a plaintiff-side demand letter for a New York commercial construction breach. Tested on Claude vs Gemini — Claude wins on tone and statutory precision.
Turn an appellate decision into a structured legal-research memo with holding vs dicta clearly distinguished. Tested on Claude vs Gemini — accuracy vs context tradeoff.
Two client-comm prompts in one: a sophisticated 1-2 page advisory letter and a sub-500 word case status email with bulleted action items.
Convert messy medical records into a clean dated treatment narrative ready to drop into a demand letter or trial binder exhibit.
Generate a phone-ready PI intake screening checklist with liability, severity, red flags, document asks, and an attorney-review scoring threshold.
Configure Claude as a senior transactional attorney that drafts numbered, defined-term commercial contracts with UCC awareness and a built-in REVIEW NOTES section.
Configure Claude as a research assistant with confidence tagging, citation-fabrication bans, IRAC output, and a built-in verification checklist for every claim.
Configure Claude as a legal communication specialist that switches tone and structure across five recipient profiles, with built-in formatting and ethics guardrails.
A meta-guide on the four most common Claude system prompt pitfalls for law firms — bloat, contradictions, over-constraining, ignoring model updates — plus versioning advice.
Pro members get the Prompt Runner: fill in variables, choose your model, run the prompt, and get output with anti-hallucination checks and reasoning traceability.