← ClaudeAtlas

legal-risk-assessmentlisted

Severity-by-likelihood legal risk register for a situation or deal — enumerates concrete risks, scores each one impact 1-5 × likelihood 1-5, renders a heat-map table, attaches mitigations to every risk at or above threshold, defines escalation criteria for immediate human counsel, and sets monitoring triggers. Use when the user says 'what's our exposure', 'how risky is this deal', 'assess the legal risk of this', or before committing to anything with real downside.
alebgl77/claude-inc · ★ 14 · AI & Automation · score 80
Install: claude install-skill alebgl77/claude-inc
# Legal Risk Assessment — Risk Assessor > "Flag legal risk" Turns "this feels risky" into a scored, sorted register with owners and tripwires. Works from a description of the situation plus any documents provided. ## When to use - "What's our exposure if we sign this?" — deal downside read - "How risky is operating without a signed DPA for a quarter?" - "Rank the legal risks of this expansion plan" - Before an exec or board commit on a contested move - Clause-level contract surgery belongs to `review-contract`; this skill scores the whole situation ## Workflow 1. Frame the situation: the decision at stake, timeline, jurisdictions, counterparties, and what "bad" concretely looks like for the business. 2. Enumerate risks across the standard surfaces — contractual, regulatory, IP, privacy and data, employment, litigation, reputational-with-legal-consequence. Each risk is a concrete event ("residuals clause lets the vendor reuse our roadmap"), never a category name ("IP risk"). 3. Score each risk: impact 1-5 (1 = nuisance cost … 5 = company-changing) × likelihood 1-5 (1 = remote … 5 = expected). Score = impact × likelihood, with a one-line rationale per score — unexplained numbers are guesses. 4. Render the heat map sorted by score, descending. 5. Attach a mitigation to every risk at or above threshold (default: score ≥ 8, overridable): the action, its owner, and the residual score once done. 6. Define escalation criteria — observable conditions that send this to human coun