Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Kanzlei startet Common-Law- UK- US- oder bilinguales Drafting-Mandat und braucht strukturierten Einstieg. Jurisdiktionscheck False-Friends-Scan Arbeitsplan. Prüfraster Jurisdiktion-Identifikation Primaeranliegen-Erfassung Skill-Routing. Output Mandat-Karte Jurisdiktion-Check Arbeitsplan. Abgrenzung zu allen Einzel-Skills (nur Master-Routing-Funktion).
.claude/skills/thomasmoreai-common-law-kommandocenter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 99% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 88% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 84% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 53% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 45% | 0% |
Einstieg für jedes Mandat, in dem deutsche Rechtsdenke auf English Law, US Law, Common Law, internationale Vertragsmuster oder zweisprachige Vertragsfassungen trifft.
Common-Law-Kompass arbeitet freundlich, präzise und verzeihend. Der Stil darf leicht sein, aber nie auf Kosten der juristischen Trennschärfe.
Kläre vor dem ersten Schritt:
UK (England & Wales)
US (New York / Delaware)
Rechtsvergleichend
Adressat: Mandant (intern) — Tonfall: sachlich-juristisch, strukturiert
COMMON-LAW-MANDATSEINSTIEG — KURZLAGE
Datum: [DATUM]
Mandat: [BEZEICHNUNG]
Bearbeiter: [NAME]
1. JURISDIKTION
Rechtsordnung: [English Law / New York Law / Delaware / ...]
Verbindliche Sprache: [EN / DE+EN]
Vertragstyp: [SPA / SHA / Loan / Services / ...]
2. PARTEIROLLE & INTERESSEN
Mandant: [PARTEI]
Gegenpartei: [PARTEI]
Kerninteressen: [...]
3. FALSE-FRIENDS-TREFFER (Ampel)
GRUEN: [Begriff] — unproblematisch
GELB: [Begriff] — Klarstellungsbedarf, Kommentar: [...]
ROT: [Begriff] — dringend ueberarbeiten, Risiko: [...]
4. OFFENE ANNAHMEN / LOCAL-COUNSEL-BEDARF
- [...]
5. NAECHSTE SCHRITTE
- [Schritt 1 mit Frist]
- [Schritt 2 mit Verantwortlichem]| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 21,755 | 24,069 | +11% | 1 | 1 | 0% | 3,961 | 6,057 | +53% | 0 | 0 | — |
case-02 | pass→pass | 21,273 | 21,642 | +2% | 1 | 1 | 0% | 3,968 | 5,760 | +45% | 0 | 0 | — |
case-03 | pass→pass | 18,491 | 17,726 | -4% | 1 | 1 | 0% | 3,957 | 5,269 | +33% | 0 | 0 | — |
case-04 | pass→pass | 15,503 | 16,832 | +9% | 1 | 1 | 0% | 3,029 | 5,045 | +67% | 0 | 0 | — |
case-05 | pass→pass | 10,481 | 10,791 | +3% | 1 | 1 | 0% | 2,310 | 4,276 | +85% | 0 | 0 | — |
case-06 | pass→pass | 14,424 | 18,383 | +27% | 1 | 1 | 0% | 2,629 | 5,225 | +99% | 0 | 0 | — |
case-07 | pass→pass | 9,919 | 12,687 | +28% | 1 | 1 | 0% | 1,860 | 4,171 | +124% | 0 | 0 | — |
case-08 | pass→pass | 8,447 | 10,592 | +25% | 1 | 1 | 0% | 1,690 | 3,778 | +124% | 0 | 0 | — |
case-09 | pass→pass | 14,143 | 16,276 | +15% | 1 | 1 | 0% | 2,636 | 4,481 | +70% | 0 | 0 | — |
case-10 | fail→pass | 14,084 | 17,652 | +25% | 1 | 1 | 0% | 2,552 | 5,074 | +99% | 0 | 0 | — |
case-11 | pass→pass | 7,917 | 11,680 | +48% | 1 | 1 | 0% | 1,530 | 3,945 | +158% | 0 | 0 | — |
case-12 | pass→pass | 14,364 | 16,935 | +18% | 1 | 1 | 0% | 2,580 | 5,063 | +96% | 0 | 0 | — |
case-13 | pass→pass | 7,565 | 12,206 | +61% | 1 | 1 | 0% | 1,486 | 4,200 | +183% | 0 | 0 | — |
case-14 | pass→pass | 8,654 | 8,211 | -5% | 1 | 1 | 0% | 1,583 | 3,409 | +115% | 0 | 0 | — |
case-15 | pass→pass | 8,033 | 12,165 | +51% | 1 | 1 | 0% | 1,572 | 4,148 | +164% | 0 | 0 | — |
case-16 | pass→pass | 12,334 | 15,012 | +22% | 1 | 1 | 0% | 2,370 | 4,782 | +102% | 0 | 0 | — |
case-17 | fail→pass | 14,867 | 16,771 | +13% | 1 | 1 | 0% | 2,698 | 5,076 | +88% | 0 | 0 | — |
case-18 | fail→pass | 14,324 | 14,151 | -1% | 1 | 1 | 0% | 2,315 | 4,249 | +84% | 0 | 0 | — |
case-19 | pass→pass | 4,613 | 11,038 | +139% | 1 | 1 | 0% | 1,022 | 4,050 | +296% | 0 | 0 | — |
case-20 | pass→pass | 11,675 | 13,095 | +12% | 1 | 1 | 0% | 2,266 | 4,525 | +100% | 0 | 0 | — |
case-21 | pass→pass | 18,195 | 15,224 | -16% | 1 | 1 | 0% | 3,037 | 4,748 | +56% | 0 | 0 | — |
case-22 | pass→pass | 12,486 | 16,756 | +34% | 1 | 1 | 0% | 2,602 | 5,145 | +98% | 0 | 0 | — |
case-23 | pass→pass | 15,671 | 18,105 | +16% | 1 | 1 | 0% | 2,671 | 4,744 | +78% | 0 | 0 | — |
case-24 | pass→pass | 11,244 | 12,909 | +15% | 1 | 1 | 0% | 2,160 | 4,543 | +110% | 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. 24 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 24 comparable cases.
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.