Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Deutscher Anwalt uebersetzt Vertrags- oder Rechtsbegriffe ins Englische und will funktionale nicht wörtliche Übersetzung. Anwendungsfall Vertragsverhandlung mit UK/US-Gegenpartei Memo an englischsprachigen Mandanten. Prüfraster Zielrechtsordnung-Prüfung Klauselzweck Risiko-Aequivalent False-Friends-Check. Output uebersetzter Begriff mit Erklärung Alternativen. Abgrenzung zu common-law-false-friends-scanner (Fehler-Scan) und common-law-us-vs-uk-drafting (Drafting-Konventionen).
.claude/skills/thomasmoreai-common-law-begriffe-uebersetzung/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 44% | 0% |
Der Skill baut mandatsbezogene Glossare mit Do/Don't-Spalte und Formulierungen für deutsches Recht in englischer Sprache.
Common-Law-Kompass arbeitet freundlich, präzise und verzeihend. Der Stil darf leicht sein, aber nie auf Kosten der juristischen Trennschärfe.
| Englischer Begriff | Falsche dt. Uebersetzung | Richtige Einordnung | Fundstelle | |---|---|---|---| | Consideration | Gegenleistung | Verpflichtungselement; Bargain; kein Synallagma | Currie v Misa 1875] | | Warranty | Garantie | Zusicharung im Vertrag; Verletzung = Schadensersatz (kein Ruecktritt) | SGA 1979 s 61 | | Condition | Bedingung | Wesentliches Vertragselement; Verletzung = Kuendigung und Schadensersatz | Bunge v Tradax 1981] | | Indemnity | Buergschaft | Primaere selbstaendige Haftung (kein Ausfallerfordernis) | Moschi v Lep 1973] | | Guarantee | Garantie | Sekundaere Haftung; nur bei Ausfall des Hauptschuldners | Holme v Brunskill (1878) | | Estoppel | Bestandskraft / Verwirkung | Rechtshinderungseinwand; verschiedene Arten (promissory, proprietary, common law) | Central London Property v High Trees 1947] | | Tort | Delikt | Ausservertragliche Haftung; weiter als BGB-Deliktsrecht | Donoghue v Stevenson 1932] | | Specific performance | Erfuellungsklage | Billigkeitsrechtsmittel; nur wenn Schadensersatz unzulaenglich; Ermessen | Co-op Insurance v Argyll 1997] |
Bevor losgelegt wird, klaere:
UEBERSETZUNGSMATRIX COMMON LAW
Dokument: [BEZEICHNUNG] — Datum: [DATUM]
Begriff | Kontext | Empfohlene dt. Entsprechung | Risiko Fehluebers.
--------|---------|---------------------------|-------------------
[TERM] | [Klausel] | [ENTSPRECHUNG] | [RISIKO]| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,140 | 24,519 | +16% | 1 | 1 | 0% | 3,562 | 4,346 | +22% | 0 | 0 | — |
case-02 | fail→fail | 22,579 | 20,639 | -9% | 1 | 1 | 0% | 4,301 | 4,836 | +12% | 0 | 0 | — |
case-03 | fail→pass | 20,239 | 16,157 | -20% | 1 | 1 | 0% | 3,618 | 4,168 | +15% | 0 | 0 | — |
case-04 | pass→pass | 14,692 | 17,540 | +19% | 1 | 1 | 0% | 2,937 | 4,798 | +63% | 0 | 0 | — |
case-05 | pass→fail | 18,340 | 17,275 | -6% | 1 | 1 | 0% | 3,324 | 4,429 | +33% | 0 | 0 | — |
case-06 | pass→pass | 4,537 | 4,291 | -5% | 1 | 1 | 0% | 835 | 1,896 | +127% | 0 | 0 | — |
case-07 | fail→pass | 25,826 | 19,058 | -26% | 1 | 1 | 0% | 3,936 | 4,402 | +12% | 0 | 0 | — |
case-08 | fail→pass | 27,589 | 20,666 | -25% | 1 | 1 | 0% | 3,363 | 4,478 | +33% | 0 | 0 | — |
case-09 | fail→pass | 19,979 | 21,646 | +8% | 1 | 1 | 0% | 3,327 | 4,788 | +44% | 0 | 0 | — |
case-10 | pass→pass | 14,720 | 17,671 | +20% | 1 | 1 | 0% | 2,387 | 4,086 | +71% | 0 | 0 | — |
case-11 | fail→pass | 24,600 | 25,338 | +3% | 1 | 1 | 0% | 4,108 | 4,919 | +20% | 0 | 0 | — |
case-12 | fail→pass | 18,131 | 21,308 | +18% | 1 | 1 | 0% | 3,163 | 4,791 | +51% | 0 | 0 | — |
case-13 | fail→pass | 16,637 | 15,667 | -6% | 1 | 1 | 0% | 2,840 | 4,172 | +47% | 0 | 0 | — |
case-14 | fail→pass | 26,147 | 23,556 | -10% | 1 | 1 | 0% | 4,184 | 4,811 | +15% | 0 | 0 | — |
case-15 | fail→pass | 11,932 | 14,192 | +19% | 1 | 1 | 0% | 1,982 | 3,582 | +81% | 0 | 0 | — |
case-16 | pass→pass | 24,025 | 25,833 | +8% | 1 | 1 | 0% | 3,804 | 5,010 | +32% | 0 | 0 | — |
case-17 | fail→pass | 15,824 | 17,977 | +14% | 1 | 1 | 0% | 2,762 | 4,193 | +52% | 0 | 0 | — |
case-18 | fail→fail | 20,895 | 26,695 | +28% | 1 | 1 | 0% | 2,893 | 4,315 | +49% | 0 | 0 | — |
case-19 | fail→fail | 29,778 | 18,808 | -37% | 1 | 1 | 0% | 4,548 | 4,566 | +0% | 0 | 0 | — |
case-20 | fail→pass | 17,017 | 16,201 | -5% | 1 | 1 | 0% | 3,125 | 3,856 | +23% | 0 | 0 | — |
case-21 | fail→pass | 20,709 | 21,387 | +3% | 1 | 1 | 0% | 3,654 | 4,777 | +31% | 0 | 0 | — |
case-22 | pass→pass | 20,006 | 22,388 | +12% | 1 | 1 | 0% | 3,752 | 5,010 | +34% | 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 +55 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.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.