← ClaudeAtlas

clause-comparatorlisted

Compares the same clause or provision as it appears across two or more places — draft rounds of one agreement, a counterparty's version against the user's own precedent, or the same clause type across a portfolio of agreements — and reports exactly what changed in wording and in effect. Use this whenever a user wants to know what moved between versions rather than a full risk review — including phrasings like "what changed between this draft and the last one", "how does their indemnity compare to our standard wording", "redline this against our template", "compare the liability cap across our last five SaaS agreements", "did they weaken the termination clause", or "track what each round of negotiation changed". Distinct from contract-reviewer, which grades a whole agreement for risk from one side's position — this stays neutral on whether a change is good or bad unless a side is given. Fires for any clause type, in any commercial agreement.
Cancellationperiplocagraeca503/legal-ai-skills · ★ 2 · AI & Automation · score 75
Install: claude install-skill Cancellationperiplocagraeca503/legal-ai-skills
# Clause Comparator ## What this does Takes the same clause, or the same clause type, as it appears in two or more places and reports what is different — mechanically, in the wording, and substantively, in what the clause now does. It is a comparison tool, not a review: it does not grade an agreement's overall risk, and it does not draft new wording for a clause that has no comparator (that is redline-proposer). It compares what it is given; it does not supply a "market standard" from memory to compare against. ## Before you start **What is being compared, and against what.** At minimum this means: how many items are being compared, where each is drawn from (document name, version or date, clause number), and whether the comparator is another draft of the same agreement, a different agreement, or a standard the user is supplying. This is blocking — do not start diffing until you know what the two (or more) things actually are. **The comparator text itself, where it is a "standard".** If the user asks to compare a clause against their firm's standard, a market position, or "what's usual", that standard has to arrive as actual text — a template clause, a precedent document, a pasted example. Do not reconstruct a market-standard clause from memory to use as the baseline; general commercial understanding of what a clause "usually" says is not a substitute for the user's own precedent. If no comparator text is supplied and none is asked for, say the comparison is limited to t