Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Script a product demo that lands — the audience's-workflow storyline (their day, not your feature list), the golden path rehearsed with fallbacks, the wow moment placed early, and the demo-death contingencies (the backup video, the reset state, the narration bridge). Use when asked script our product demo, demo this to a customer/exec, our demos meander through features, or the demo broke live last time. Produces the demo storyline, the click-path script with fallbacks, the wow placement, and th
.claude/skills/mohitagw15856-demo-script/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 90% | 0% |
Feature-tour demos die politely: "here's the dashboard, here's settings, here's our AI" — a museum walk through someone else's house. The demo that lands is a story about the audience's day: their actual workflow, with its familiar pain, walked through the product — pain first (recruit the deck-narrative-arc tension), the wow moment inside the first three minutes (attention is front-loaded; demos that save the best for last perform it to phones), and every click scripted on a rehearsed golden path with the contingency kit standing by — because live demos break, and the difference between a stumble and a disaster is whether the recovery was pre-built.
Ask for these if not provided:
Their task, start → done · the pain, named · where each shown capability answers a step]
| # | Click/action | Talk-track line | Point at | |---|---|---|---| The wow marked ★ at its minute · the skippable-if-short section marked]
Fragility → bridge line · the backup recording's tab · the one-step reset · the pre-meeting verification checklist]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | pass→pass | 9,880 | 6,013 | -39% | 1 | 1 | 0% | 1,654 | 2,167 | +31% | 0 | 0 | — |
case-20 | pass→pass | 10,932 | 11,626 | +6% | 1 | 1 | 0% | 1,832 | 3,062 | +67% | 0 | 0 | — |
case-01 | fail→pass | 22,692 | 14,634 | -36% | 1 | 1 | 0% | 3,830 | 3,565 | -7% | 0 | 0 | — |
case-02 | fail→pass | 35,976 | 22,544 | -37% | 1 | 1 | 0% | 5,398 | 4,533 | -16% | 0 | 0 | — |
case-03 | fail→pass | 23,523 | 18,119 | -23% | 1 | 1 | 0% | 4,042 | 3,985 | -1% | 0 | 0 | — |
case-04 | pass→pass | 20,311 | 17,045 | -16% | 1 | 1 | 0% | 3,522 | 4,111 | +17% | 0 | 0 | — |
case-05 | pass→pass | 12,551 | 12,772 | +2% | 1 | 1 | 0% | 2,169 | 3,115 | +44% | 0 | 0 | — |
case-06 | pass→pass | 7,817 | 8,377 | +7% | 1 | 1 | 0% | 1,312 | 2,546 | +94% | 0 | 0 | — |
case-07 | fail→pass | 17,688 | 15,057 | -15% | 1 | 1 | 0% | 3,288 | 3,739 | +14% | 0 | 0 | — |
case-08 | fail→pass | 10,254 | 14,422 | +41% | 1 | 1 | 0% | 1,830 | 3,482 | +90% | 0 | 0 | — |
case-09 | pass→pass | 18,477 | 15,360 | -17% | 1 | 1 | 0% | 3,254 | 3,930 | +21% | 0 | 0 | — |
case-10 | pass→pass | 10,919 | 10,446 | -4% | 1 | 1 | 0% | 1,742 | 2,953 | +70% | 0 | 0 | — |
case-11 | pass→pass | 13,033 | 17,417 | +34% | 1 | 1 | 0% | 2,260 | 4,017 | +78% | 0 | 0 | — |
case-12 | fail→pass | 10,192 | 6,243 | -39% | 1 | 1 | 0% | 1,612 | 2,094 | +30% | 0 | 0 | — |
case-14 | fail→pass | 6,984 | 4,806 | -31% | 1 | 1 | 0% | 1,225 | 2,010 | +64% | 0 | 0 | — |
case-15 | pass→pass | 12,102 | 15,823 | +31% | 1 | 1 | 0% | 2,180 | 3,732 | +71% | 0 | 0 | — |
case-16 | pass→pass | 11,153 | 7,849 | -30% | 1 | 1 | 0% | 2,053 | 2,472 | +20% | 0 | 0 | — |
case-17 | pass→pass | 13,953 | 11,011 | -21% | 1 | 1 | 0% | 2,314 | 2,928 | +27% | 0 | 0 | — |
case-18 | pass→pass | 13,248 | 11,241 | -15% | 1 | 1 | 0% | 2,383 | 3,561 | +49% | 0 | 0 | — |
case-19 | fail→pass | 8,683 | 6,368 | -27% | 1 | 1 | 0% | 1,385 | 2,173 | +57% | 0 | 0 | — |
case-21 | fail→pass | 12,748 | 6,849 | -46% | 1 | 1 | 0% | 2,215 | 2,404 | +9% | 0 | 0 | — |
case-22 | pass→pass | 11,157 | 8,845 | -21% | 1 | 1 | 0% | 1,931 | 2,689 | +39% | 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 +41 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.