Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.
.claude/skills/itamarzand88-employment-contract-templates/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 33% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 62% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -11% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 12% | 0% |
<!-- source: employment-contract-templates — https://raw.githubusercontent.com/wshobson/agents/main/plugins/hr-legal-compliance/skills/employment-contract-templates/SKILL.md -->
Templates and patterns for creating legally sound employment documentation including contracts, offer letters, and HR policies.
| Document | Purpose | When Used | | ----------------------- | ----------------------- | ------------- | | Offer Letter | Initial job offer | Pre-hire | | Employment Contract | Formal agreement | Hire | | Employee Handbook | Policies & procedures | Onboarding | | NDA | Confidentiality | Before access | | Non-Compete | Competition restriction | Hire/Exit |
Employment Relationship:
├── At-Will vs. Contract
├── Employee vs. Contractor
├── Full-Time vs. Part-Time
├── Exempt vs. Non-Exempt
└── Jurisdiction-Specific RequirementsDISCLAIMER: These templates are for informational purposes only and do not constitute legal advice. Consult with qualified legal counsel before using any employment documents.
Full template library and detailed worked examples live in references/details.md. Read that file when you need the concrete templates.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,848 | 11,228 | -13% | 1 | 1 | 0% | 2,169 | 2,463 | +14% | 0 | 0 | — |
case-02 | pass→pass | 9,662 | 12,757 | +32% | 1 | 1 | 0% | 1,887 | 2,501 | +33% | 0 | 0 | — |
case-03 | pass→pass | 3,985 | 3,714 | -7% | 1 | 1 | 0% | 711 | 1,151 | +62% | 0 | 0 | — |
case-04 | pass→pass | 9,487 | 6,177 | -35% | 1 | 1 | 0% | 1,595 | 1,427 | -11% | 0 | 0 | — |
case-05 | pass→pass | 8,795 | 8,823 | +0% | 1 | 1 | 0% | 1,730 | 1,932 | +12% | 0 | 0 | — |
case-06 | pass→pass | 3,057 | 3,976 | +30% | 1 | 1 | 0% | 552 | 1,186 | +115% | 0 | 0 | — |
case-07 | pass→pass | 6,138 | 4,240 | -31% | 1 | 1 | 0% | 1,169 | 1,384 | +18% | 0 | 0 | — |
case-08 | pass→pass | 9,691 | 7,738 | -20% | 1 | 1 | 0% | 1,620 | 1,918 | +18% | 0 | 0 | — |
case-09 | pass→pass | 6,354 | 2,941 | -54% | 1 | 1 | 0% | 1,081 | 949 | -12% | 0 | 0 | — |
case-10 | pass→pass | 14,048 | 11,054 | -21% | 1 | 1 | 0% | 2,387 | 2,604 | +9% | 0 | 0 | — |
case-11 | pass→pass | 7,710 | 5,004 | -35% | 1 | 1 | 0% | 1,273 | 1,406 | +10% | 0 | 0 | — |
case-12 | pass→pass | 6,155 | 4,187 | -32% | 1 | 1 | 0% | 1,090 | 1,195 | +10% | 0 | 0 | — |
case-13 | pass→pass | 10,817 | 10,180 | -6% | 1 | 1 | 0% | 1,921 | 2,496 | +30% | 0 | 0 | — |
case-14 | pass→pass | 7,567 | 7,161 | -5% | 1 | 1 | 0% | 1,450 | 1,815 | +25% | 0 | 0 | — |
case-15 | pass→pass | 7,115 | 6,152 | -14% | 1 | 1 | 0% | 1,257 | 1,522 | +21% | 0 | 0 | — |
case-16 | pass→pass | 13,148 | 12,386 | -6% | 1 | 1 | 0% | 2,344 | 2,605 | +11% | 0 | 0 | — |
case-17 | pass→pass | 9,922 | 6,077 | -39% | 1 | 1 | 0% | 1,620 | 1,529 | -6% | 0 | 0 | — |
case-18 | pass→pass | 8,966 | 7,797 | -13% | 1 | 1 | 0% | 1,593 | 1,777 | +12% | 0 | 0 | — |
case-19 | pass→pass | 11,775 | 10,130 | -14% | 1 | 1 | 0% | 1,990 | 2,179 | +9% | 0 | 0 | — |
case-20 | fail→fail | 13,843 | 13,867 | +0% | 1 | 1 | 0% | 2,584 | 3,167 | +23% | 0 | 0 | — |
case-21 | fail→fail | 14,623 | 13,908 | -5% | 1 | 1 | 0% | 3,118 | 3,582 | +15% | 0 | 0 | — |
case-22 | fail→fail | 13,260 | 17,786 | +34% | 1 | 1 | 0% | 2,701 | 3,912 | +45% | 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 +5 percentage points is the difference between those two pass rates over the 22 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.