Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Draft a firm, professional demand letter that states the facts, the legal/contractual basis, the specific demand, and a deadline. Use when asked to write a demand letter, send a formal demand for payment, draft a cease-and-desist, or formally request resolution before legal action. Produces a structured, factual letter with a clear ask and consequences — assertive but not threatening or defamatory. Not legal advice; have counsel review before sending.
.claude/skills/mohitagw15856-demand-letter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 32% | 0% |
A demand letter works when it's calm, factual, and specific: here's what happened, here's the basis, here's exactly what I want, by when, or here's what follows. This skill drafts that letter. Not legal advice — laws and remedies vary; have a qualified lawyer review before sending, especially before threatening litigation.
Given the dispute, draft the full letter anyway using the facts provided and clearly-labelled placeholders only where the sender must insert specifics (names, exact amounts, dates). Keep the tone firm and professional — never insulting, never an empty threat.
Ask for (if not already provided):
A ready-to-review letter:
End with: ⚠️ Before sending — items to verify (exact figures, the governing clause, applicable notice periods, whether counsel should review or send it).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 10,565 | 10,150 | -4% | 1 | 1 | 0% | 2,010 | 2,342 | +17% | 0 | 0 | — |
case-02 | fail→pass | 11,161 | 9,796 | -12% | 1 | 1 | 0% | 2,001 | 2,214 | +11% | 0 | 0 | — |
case-03 | fail→pass | 13,333 | 13,882 | +4% | 1 | 1 | 0% | 2,202 | 2,818 | +28% | 0 | 0 | — |
case-04 | pass→pass | 12,842 | 13,492 | +5% | 1 | 1 | 0% | 2,099 | 3,019 | +44% | 0 | 0 | — |
case-05 | fail→pass | 12,453 | 13,410 | +8% | 1 | 1 | 0% | 2,154 | 2,792 | +30% | 0 | 0 | — |
case-06 | fail→pass | 11,573 | 11,418 | -1% | 1 | 1 | 0% | 2,051 | 2,702 | +32% | 0 | 0 | — |
case-07 | pass→pass | 11,321 | 11,821 | +4% | 1 | 1 | 0% | 1,776 | 2,644 | +49% | 0 | 0 | — |
case-08 | fail→pass | 11,729 | 12,554 | +7% | 1 | 1 | 0% | 2,077 | 2,580 | +24% | 0 | 0 | — |
case-09 | fail→pass | 9,134 | 12,270 | +34% | 1 | 1 | 0% | 1,610 | 2,939 | +83% | 0 | 0 | — |
case-10 | fail→pass | 9,726 | 10,875 | +12% | 1 | 1 | 0% | 1,865 | 2,543 | +36% | 0 | 0 | — |
case-11 | fail→pass | 12,194 | 10,283 | -16% | 1 | 1 | 0% | 2,039 | 2,570 | +26% | 0 | 0 | — |
case-12 | fail→pass | 11,118 | 11,923 | +7% | 1 | 1 | 0% | 1,899 | 2,576 | +36% | 0 | 0 | — |
case-13 | fail→pass | 11,005 | 12,043 | +9% | 1 | 1 | 0% | 2,088 | 2,909 | +39% | 0 | 0 | — |
case-14 | fail→pass | 12,516 | 9,497 | -24% | 1 | 1 | 0% | 2,430 | 2,507 | +3% | 0 | 0 | — |
case-15 | fail→pass | 9,770 | 8,936 | -9% | 1 | 1 | 0% | 1,916 | 2,501 | +31% | 0 | 0 | — |
case-16 | fail→pass | 9,180 | 10,234 | +11% | 1 | 1 | 0% | 1,701 | 2,721 | +60% | 0 | 0 | — |
case-17 | fail→fail | 11,556 | 10,807 | -6% | 1 | 1 | 0% | 2,044 | 2,756 | +35% | 0 | 0 | — |
case-18 | fail→pass | 10,209 | 9,921 | -3% | 1 | 1 | 0% | 1,863 | 2,517 | +35% | 0 | 0 | — |
case-19 | pass→pass | 11,687 | 8,869 | -24% | 1 | 1 | 0% | 2,012 | 2,149 | +7% | 0 | 0 | — |
case-20 | fail→pass | 14,965 | 12,636 | -16% | 1 | 1 | 0% | 2,633 | 2,576 | -2% | 0 | 0 | — |
case-21 | fail→fail | 13,237 | 12,734 | -4% | 1 | 1 | 0% | 2,403 | 2,920 | +22% | 0 | 0 | — |
case-22 | fail→pass | 10,383 | 10,499 | +1% | 1 | 1 | 0% | 1,788 | 2,453 | +37% | 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 +77 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/14/2026 | +77% |
Other measured skills in the registry, with their headline benchmark lift.