Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Anwalt muss zwischen British English English Law US contract style Delaware/New York-Konventionen und Business-English unterscheiden. Anwendungsfall Vertrag für UK- oder US-Gegenpartei. Prüfraster Jurisdiction-Style-Matching Drafting-Konventionen Sprachebene. Output Drafting-Empfehlung Stil-Hinweise Klausel-Beispiele. Abgrenzung zu common-law-false-friends-scanner (Begriffe) und common-law-governing-law-jurisdiction (Rechtswahl).
.claude/skills/thomasmoreai-common-law-us-vs-uk-drafting/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✓→✗ | ▼ Worse | 115% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 83% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 61% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 125% | 0% |
| case-07 | ✓→✓ | = Same ✓ | 98% | 0% |
Mischenglisch aus Schulenglisch, US-Templates und Londoner Klauseln wird geglättet.
Common-Law-Kompass arbeitet freundlich, präzise und verzeihend. Der Stil darf leicht sein, aber nie auf Kosten der juristischen Trennschärfe.
Kläre vor der Vergleichsanalyse:
| Punkt | England & Wales | New York / Delaware | Deutsches Fallbeil-Risiko | |---|---|---|---| | Consideration | Erforderlich; past consideration ungueltig | Erforderlich; "valuable consideration" reicht | Fehler: deutschen Synallagma-Begriff anwenden | | Conditions vs Warranties | Condition: Ruecktritt; Warranty: Schadensersatz | Rep & Warranty: oft zusammen, survival-Klausel entscheidend | Warranty als "Garantie i.S.v. § 443 BGB" fehldeuten | | Indemnity | Verschuldensunabhaengig, enger Wortlaut | Verschuldensunabhaengig; NY: Anti-Indemnity-Statutes beachten | Als Schadensersatz i.S.v. § 249 BGB behandeln | | Material Adverse Change | Court-sceptisch (Akorn v Fresenius - Delaware) | MAC-Trigger schwer auszuloesen; hohe Schwelle | MAC als Force-Majeure-Ersatz missverstehen | | Entire Agreement Clause | Sperrt nur collateral warranties, nicht statutory misrep | Merger Clause sperrt Parol Evidence breiter | Als vollstaendigen Haftungsausschluss ueberschaetzen | | Good Faith | Kein allgemeiner implied duty (Walford v Miles) | UCC § 1-304: duty of good faith bei UCC-Vertraegen | BGB-Treu-und-Glauben-Mastab anlegen | | Limitation of Liability | UCTA reasonableness test | NY: Generally enforceable, aber gross negligence nicht ausschliessbar | Cap zu hoch oder zu niedrig ansetzen | | Notice Provisions | Strict compliance gefordert | Substantial compliance oft ausreichend | Notice-Fristen als Formsache behandeln |
UK
US (New York / Delaware)
Kommentar
Adressat: Partnerebene oder Mandant — Tonfall: praezise, tabellarisch, handlungsorientiert
UK VS US DRAFTING — VERGLEICHSMEMO
Datum: [DATUM]
Dokument: [VERTRAGSNAME]
Governing Law (aktuell): [...]
Ziel-Jurisdiktion (nach Anpassung): [...]
Bearbeiter: [NAME]
ZUSAMMENFASSUNG
Das vorliegende Dokument ist [ueberwiegend UK / ueberwiegend US / gemischt] und weist
[X] Stellen auf, die jurisdiktionsfremde Elemente enthalten.
KRITISCHE UK/US-KONFLIKTE
Nr. | Klausel | Aktueller Text | Problem | Empfohlene Aenderung | Prioritaet
----|---------|---------------|---------|---------------------|----------
1 | [§/Abs.] | "[Auszug]" | [UK/US-Konflikt] | "[Neuer Text]" | HOCH
2 | ...
STYLE-ANPASSUNGEN (Nicht-kritisch)
- [Liste formaler Stilanpassungen: Datumsformat, defined terms, Nummerierung, ...]
JURISDICTION-SPEZIFISCHE CHECKLISTE
[ ] Consideration/past consideration geprueft (UK)
[ ] Deed vs Simple Contract: Formerfordernis geklaert
[ ] UCTA-Reasonableness-Test bestanden (UK)
[ ] UCC-Warranty-Disclaimer § 2-316 eingehalten (US)
[ ] MAC-Definition: Delaware-Standard beruecksichtigt (US-M&A)
[ ] Walford v Miles: No good-faith-obligation clause beachtet (UK)
LOCAL-COUNSEL-EMPFEHLUNG: [Ja / Nein / Fuer Teilbereiche]| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 26,194 | 23,787 | -9% | 1 | 1 | 0% | 4,540 | 6,132 | +35% | 0 | 0 | — |
case-02 | fail→fail | 25,920 | 27,476 | +6% | 1 | 1 | 0% | 4,189 | 6,988 | +67% | 0 | 0 | — |
case-03 | pass→pass | 25,784 | 20,884 | -19% | 1 | 1 | 0% | 3,190 | 5,839 | +83% | 0 | 0 | — |
case-04 | pass→fail | 13,798 | 18,797 | +36% | 1 | 1 | 0% | 2,325 | 5,007 | +115% | 0 | 0 | — |
case-05 | pass→pass | 19,243 | 19,464 | +1% | 1 | 1 | 0% | 3,399 | 5,483 | +61% | 0 | 0 | — |
case-06 | pass→pass | 13,937 | 20,747 | +49% | 1 | 1 | 0% | 2,372 | 5,332 | +125% | 0 | 0 | — |
case-07 | pass→pass | 14,585 | 17,088 | +17% | 1 | 1 | 0% | 2,568 | 5,095 | +98% | 0 | 0 | — |
case-08 | pass→pass | 15,154 | 16,683 | +10% | 1 | 1 | 0% | 2,519 | 4,954 | +97% | 0 | 0 | — |
case-09 | pass→pass | 16,918 | 15,256 | -10% | 1 | 1 | 0% | 2,441 | 4,626 | +90% | 0 | 0 | — |
case-10 | pass→pass | 20,055 | 20,741 | +3% | 1 | 1 | 0% | 2,459 | 5,172 | +110% | 0 | 0 | — |
case-11 | pass→pass | 10,897 | 16,761 | +54% | 1 | 1 | 0% | 2,064 | 5,047 | +145% | 0 | 0 | — |
case-12 | pass→pass | 13,758 | 19,515 | +42% | 1 | 1 | 0% | 2,360 | 5,178 | +119% | 0 | 0 | — |
case-13 | pass→pass | 14,394 | 18,263 | +27% | 1 | 1 | 0% | 2,464 | 5,183 | +110% | 0 | 0 | — |
case-14 | pass→pass | 14,517 | 19,269 | +33% | 1 | 1 | 0% | 2,484 | 5,318 | +114% | 0 | 0 | — |
case-15 | pass→pass | 9,759 | 16,029 | +64% | 1 | 1 | 0% | 1,405 | 4,714 | +236% | 0 | 0 | — |
case-16 | pass→pass | 6,298 | 13,550 | +115% | 1 | 1 | 0% | 1,093 | 4,254 | +289% | 0 | 0 | — |
case-17 | pass→pass | 12,678 | 15,207 | +20% | 1 | 1 | 0% | 2,232 | 4,704 | +111% | 0 | 0 | — |
case-18 | pass→pass | 9,847 | 15,893 | +61% | 1 | 1 | 0% | 1,850 | 4,593 | +148% | 0 | 0 | — |
case-19 | pass→pass | 7,214 | 10,797 | +50% | 1 | 1 | 0% | 1,336 | 4,033 | +202% | 0 | 0 | — |
case-20 | pass→pass | 12,114 | 17,247 | +42% | 1 | 1 | 0% | 1,994 | 4,926 | +147% | 0 | 0 | — |
case-21 | pass→pass | 11,040 | 18,778 | +70% | 1 | 1 | 0% | 1,927 | 5,178 | +169% | 0 | 0 | — |
case-22 | pass→pass | 6,219 | 5,703 | -8% | 1 | 1 | 0% | 972 | 2,870 | +195% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of -100 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Other measured skills in the registry, with their headline benchmark lift.