Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to create, optimize, or audit a giveaway, contest, or promotional campaign page. Also use when the user mentions "giveaway," "contest," "sweepstakes," "promo," "Gleam," "Woobox," or "viral campaign." For sitewide page planning, use website-structure.
.claude/skills/kostja94-contest-page-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -19% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 29% | 0% |
Guides giveaway and contest pages for promotional campaigns. Drives signups, engagement, and viral sharing. Often uses Gleam, Woobox, Viralsweep, or similar. Common for e-commerce, SaaS launches, and community growth.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for product and campaign goals.
Identify:
| Section | Purpose | |---------|---------| | Headline | "Win Prize]" or "Enter the Contest Name]" | | Prize | What they win; image, value, appeal | | Rules | How to enter; eligibility; end date | | Actions | Required actions (email, follow, share) | | Countdown | Urgency; end date visible | | Legal | Official rules link; disclosure |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 48,311 | 10,802 | -78% | 1 | 1 | 0% | 1,541 | 2,251 | +46% | 0 | 0 | — |
case-02 | pass→pass | 17,088 | 9,862 | -42% | 1 | 1 | 0% | 2,386 | 1,940 | -19% | 0 | 0 | — |
case-03 | pass→pass | 7,705 | 34,772 | +351% | 1 | 1 | 0% | 1,323 | 1,712 | +29% | 0 | 0 | — |
case-04 | pass→pass | 17,592 | 8,657 | -51% | 1 | 1 | 0% | 2,002 | 2,097 | +5% | 0 | 0 | — |
case-05 | pass→pass | 13,459 | 10,457 | -22% | 1 | 1 | 0% | 2,340 | 2,238 | -4% | 0 | 0 | — |
case-06 | pass→pass | 11,277 | 10,241 | -9% | 1 | 1 | 0% | 1,815 | 2,067 | +14% | 0 | 0 | — |
case-07 | pass→pass | 9,034 | 7,702 | -15% | 1 | 1 | 0% | 1,633 | 1,846 | +13% | 0 | 0 | — |
case-08 | pass→pass | 14,498 | 12,071 | -17% | 1 | 1 | 0% | 2,591 | 2,748 | +6% | 0 | 0 | — |
case-09 | pass→pass | 15,926 | 51,200 | +221% | 1 | 1 | 0% | 1,620 | 2,358 | +46% | 0 | 0 | — |
case-10 | pass→pass | 14,236 | 10,331 | -27% | 1 | 1 | 0% | 2,279 | 2,509 | +10% | 0 | 0 | — |
case-11 | pass→pass | 13,510 | 9,419 | -30% | 1 | 1 | 0% | 2,372 | 2,224 | -6% | 0 | 0 | — |
case-12 | pass→pass | 11,666 | 9,533 | -18% | 1 | 1 | 0% | 2,027 | 1,994 | -2% | 0 | 0 | — |
case-13 | pass→pass | 8,515 | 9,729 | +14% | 1 | 1 | 0% | 1,384 | 2,180 | +58% | 0 | 0 | — |
case-14 | fail→pass | 8,045 | 2,655 | -67% | 1 | 1 | 0% | 1,299 | 972 | -25% | 0 | 0 | — |
case-15 | pass→pass | 8,521 | 7,982 | -6% | 1 | 1 | 0% | 1,412 | 1,982 | +40% | 0 | 0 | — |
case-16 | fail→pass | 6,283 | 3,045 | -52% | 1 | 1 | 0% | 1,010 | 1,125 | +11% | 0 | 0 | — |
case-17 | pass→pass | 15,140 | 11,963 | -21% | 1 | 1 | 0% | 2,477 | 2,466 | -0% | 0 | 0 | — |
case-18 | pass→pass | 11,232 | 10,800 | -4% | 1 | 1 | 0% | 1,892 | 2,345 | +24% | 0 | 0 | — |
case-19 | pass→pass | 15,235 | 10,537 | -31% | 1 | 1 | 0% | 2,163 | 2,109 | -2% | 0 | 0 | — |
case-20 | pass→pass | 11,096 | 11,967 | +8% | 1 | 1 | 0% | 2,008 | 2,774 | +38% | 0 | 0 | — |
case-21 | pass→pass | 8,048 | 8,018 | -0% | 1 | 1 | 0% | 1,556 | 2,027 | +30% | 0 | 0 | — |
case-22 | pass→pass | 8,854 | 7,872 | -11% | 1 | 1 | 0% | 1,526 | 2,087 | +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 +14 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.