The Prompt Library

116+ Tested AI Prompts for Lawyers

Attorney-reviewed prompts for Claude, ChatGPT, and Gemini. Filtered by practice area, jurisdiction, and task — with built-in anti-hallucination safeguards on every prompt.

0 attorney-reviewed7+ jurisdictions4 AI models45 free prompts

Filtered Results(6)

Clear filters
Strategicclaude

Claude Prompt: O-1A Extraordinary Ability Evidence Mapping

Use Claude to score an O-1A candidate against all eight regulatory criteria, recommend the lead 3-5 criteria, and identify documentation gaps.

immigrationdrafting
Strategicclaude

Claude Prompt: Draft Comprehensive Personal Injury Demand Letter with Damages Calculations

Generate a complete, persuasive personal injury demand letter with itemized economic damages, multiplier and per diem pain-and-suffering analysis, and clear settlement demand.

personal-injurydrafting
Strategicclaude

Claude Prompt: Personal Injury Case Valuation Analysis with Settlement Range

Run a structured case valuation that produces economic damages, multiplier and per diem ranges, venue-aware risk factors, and a low/target/high settlement recommendation.

personal-injurynegotiation
Strategicclaude

Claude Prompt: Senior Contract Risk Analyst System Prompt with Redline Output

Deploy Claude as a senior contract risk analyst with a 14-point review checklist, perspective toggle, color-coded risk tiers, and concrete suggested redlines.

contractsreview
Strategicclaude

Claude Prompt: Clause-by-Clause Contract Review with Reasoning Chains

Walk through every clause with explicit reasoning, a 1-10 risk score, suggested redlines, and a confidence rating you can verify line by line.

general-practicereview
Strategicclaude

Claude Prompt: End-to-End Legal Workflow Orchestrator (6 Stages)

One prompt, six stages, full audit trail — runs the entire intake-to-deliverable pipeline inside a single Claude session with global anti-hallucination rules.

general-practicedrafting

Run prompts directly. Don't copy-paste.

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.