Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Decode a wedding vendor contract — venue, photographer, caterer, band — before signing: deposits and their refundability, cancellation and postponement terms, the substitute-performer and force-majeure clauses, and overtime math. Use when someone asks review this venue contract, is this photographer contract normal, what if we have to postpone, or decode this caterer agreement. Produces a clause decode with 🔴🟡🟢 severity, the cancellation-cost timeline, the questions to ask this vendor, and what'
.claude/skills/mohitagw15856-wedding-vendor-contract-decoder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 83% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 101% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 113% | 0% |
Wedding contracts are signed in the happiest possible mood about the least happy possible clauses — what happens if someone cancels, postpones, no-shows, or sends a substitute. And the money is structured backwards from consumer intuition: deposits are usually retainers (often non-refundable by design — the vendor turned away other bookings for your date), while the cancellation timeline decides whether a change of plans costs 20% or 100%. This skill decodes the clauses that bite, computes the walk-away cost at each date, and lists what vendors routinely amend when asked before signing.
Ask for these only if they aren't already provided:
Always compute the walk-away table: for each contract milestone date, the cost of cancelling that day (deposit + scheduled payments + any penalty), and the same for a date change if the contract distinguishes — because "what does changing the date cost in March?" is the question the contract was designed not to answer plainly.
1. The verdict — sign / amend these clauses first / keep shopping, in two sentences.
2. Clause decode
| Clause (§) | What it says | What it means for your wedding | Severity | |---|---|---|---|
3. 💸 The walk-away table — per milestone date: cancellation cost · date-change cost (or "contract is silent — that's question #1").
4. Questions for the vendor — 4–6, aimed at the silences: postponement terms, substitute policy, overtime rate in writing, delivery dates, what happens if they cancel.
5. What's negotiable — date-change addendum (the most-granted ask in the industry), delivery deadlines, overtime caps, substitute-approval rights, payment-schedule shifts.
End the artifact with, verbatim: "This is a plain-language reading, not legal/financial advice — laws vary by jurisdiction; confirm anything load-bearing with a qualified professional."
Client-side event-contract review — cancellation-schedule math, postponement-clause triage, silence auditing.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 31,522 | 12,080 | -62% | 1 | 1 | 0% | 4,174 | 2,430 | -42% | 0 | 0 | — |
case-02 | fail→pass | 38,668 | 39,573 | +2% | 1 | 1 | 0% | 4,469 | 5,829 | +30% | 0 | 0 | — |
case-03 | fail→fail | 26,118 | 28,602 | +10% | 1 | 1 | 0% | 2,824 | 4,404 | +56% | 0 | 0 | — |
case-04 | pass→pass | 19,044 | 29,223 | +53% | 1 | 1 | 0% | 1,952 | 4,621 | +137% | 0 | 0 | — |
case-05 | pass→pass | 21,579 | 16,874 | -22% | 1 | 1 | 0% | 2,272 | 2,947 | +30% | 0 | 0 | — |
case-06 | fail→fail | 23,987 | 31,992 | +33% | 1 | 1 | 0% | 3,104 | 4,809 | +55% | 0 | 0 | — |
case-07 | fail→pass | 19,722 | 18,029 | -9% | 1 | 1 | 0% | 2,715 | 3,349 | +23% | 0 | 0 | — |
case-08 | fail→pass | 13,699 | 25,300 | +85% | 1 | 1 | 0% | 2,180 | 3,981 | +83% | 0 | 0 | — |
case-09 | fail→pass | 17,243 | 20,650 | +20% | 1 | 1 | 0% | 1,953 | 3,923 | +101% | 0 | 0 | — |
case-10 | fail→pass | 15,986 | 15,194 | -5% | 1 | 1 | 0% | 1,831 | 3,905 | +113% | 0 | 0 | — |
case-11 | fail→pass | 6,366 | 22,859 | +259% | 1 | 1 | 0% | 1,214 | 4,115 | +239% | 0 | 0 | — |
case-12 | pass→pass | 17,379 | 18,382 | +6% | 1 | 1 | 0% | 2,233 | 3,427 | +53% | 0 | 0 | — |
case-13 | fail→pass | 9,527 | 16,736 | +76% | 1 | 1 | 0% | 1,485 | 3,000 | +102% | 0 | 0 | — |
case-14 | fail→fail | 16,217 | 20,844 | +29% | 1 | 1 | 0% | 1,805 | 3,792 | +110% | 0 | 0 | — |
case-15 | pass→pass | 19,823 | 25,980 | +31% | 1 | 1 | 0% | 2,171 | 4,367 | +101% | 0 | 0 | — |
case-16 | fail→pass | 13,970 | 22,751 | +63% | 1 | 1 | 0% | 2,146 | 3,889 | +81% | 0 | 0 | — |
case-17 | fail→fail | 19,308 | 20,987 | +9% | 1 | 1 | 0% | 2,245 | 3,661 | +63% | 0 | 0 | — |
case-18 | fail→fail | 16,677 | 23,294 | +40% | 1 | 1 | 0% | 1,945 | 3,941 | +103% | 0 | 0 | — |
case-19 | fail→pass | 23,525 | 25,663 | +9% | 1 | 1 | 0% | 2,777 | 4,564 | +64% | 0 | 0 | — |
case-20 | fail→fail | 14,445 | 21,012 | +45% | 1 | 1 | 0% | 1,606 | 4,695 | +192% | 0 | 0 | — |
case-21 | pass→pass | 14,738 | 23,300 | +58% | 1 | 1 | 0% | 1,630 | 4,390 | +169% | 0 | 0 | — |
case-22 | fail→pass | 18,177 | 13,863 | -24% | 1 | 1 | 0% | 2,013 | 3,444 | +71% | 0 | 0 | — |
case-23 | fail→fail | 16,628 | 15,077 | -9% | 1 | 1 | 0% | 1,919 | 2,809 | +46% | 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. 23 cases were attempted. The headline lift of +43 percentage points is the difference between those two pass rates over the 23 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.