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 structure a status page. Also use when the user mentions "status page," "status.yourdomain.com," "uptime," "service health," "incident page," or "system status." For incident comms, use public-relations.
.claude/skills/kostja94-status-page-generator/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 53 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 810% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 10% | 0% |
Guides status page design for communicating service health, uptime, and incidents. Typically at status.* subdomain. Reduces support during outages, builds trust.
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 service components.
Identify:
| Section | Purpose | |---------|---------| | Overall status | Operational, Degraded, Outage, Maintenance | | Components | Per service: status, uptime % | | Incidents | Active and past; timeline, updates | | Subscribe | Email, SMS, RSS for notifications | | Uptime history | 90-day or custom range (optional) |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 18,402 | 14,376 | -22% | 1 | 1 | 0% | 2,704 | 2,976 | +10% | 0 | 0 | — |
case-02 | pass→pass | 9,723 | 11,101 | +14% | 1 | 1 | 0% | 1,533 | 2,278 | +49% | 0 | 0 | — |
case-03 | fail→pass | 14,316 | 13,049 | -9% | 1 | 1 | 0% | 2,144 | 2,508 | +17% | 0 | 0 | — |
case-04 | fail→pass | 14,788 | 12,183 | -18% | 1 | 1 | 0% | 2,130 | 2,781 | +31% | 0 | 0 | — |
case-05 | pass→pass | 11,147 | 13,163 | +18% | 1 | 1 | 0% | 1,899 | 2,667 | +40% | 0 | 0 | — |
case-06 | fail→pass | 19,460 | 6,864 | -65% | 1 | 1 | 0% | 2,055 | 1,722 | -16% | 0 | 0 | — |
case-07 | pass→pass | 10,521 | 13,566 | +29% | 1 | 1 | 0% | 1,689 | 2,550 | +51% | 0 | 0 | — |
case-08 | fail→fail | 15,885 | 15,179 | -4% | 1 | 1 | 0% | 2,452 | 2,998 | +22% | 0 | 0 | — |
case-09 | pass→pass | 14,979 | 17,535 | +17% | 1 | 1 | 0% | 2,287 | 3,197 | +40% | 0 | 0 | — |
case-10 | pass→pass | 14,457 | 14,465 | +0% | 1 | 1 | 0% | 2,163 | 2,127 | -2% | 0 | 0 | — |
case-11 | fail→pass | 1,679 | 10,936 | +551% | 1 | 1 | 0% | 248 | 2,258 | +810% | 0 | 0 | — |
case-12 | pass→pass | 10,880 | 9,698 | -11% | 1 | 1 | 0% | 1,650 | 2,154 | +31% | 0 | 0 | — |
case-13 | pass→pass | 11,410 | 9,330 | -18% | 1 | 1 | 0% | 1,763 | 2,333 | +32% | 0 | 0 | — |
case-14 | pass→pass | 13,055 | 12,634 | -3% | 1 | 1 | 0% | 1,876 | 2,582 | +38% | 0 | 0 | — |
case-15 | pass→pass | 10,947 | 10,154 | -7% | 1 | 1 | 0% | 1,901 | 2,210 | +16% | 0 | 0 | — |
case-16 | pass→pass | 18,357 | 11,244 | -39% | 1 | 1 | 0% | 2,604 | 2,398 | -8% | 0 | 0 | — |
case-17 | pass→pass | 10,069 | 9,800 | -3% | 1 | 1 | 0% | 1,474 | 2,112 | +43% | 0 | 0 | — |
case-18 | pass→pass | 25,029 | 13,432 | -46% | 1 | 1 | 0% | 4,227 | 2,821 | -33% | 0 | 0 | — |
case-19 | fail→fail | 6,111 | 8,561 | +40% | 1 | 1 | 0% | 943 | 1,986 | +111% | 0 | 0 | — |
case-20 | pass→pass | 27,575 | 18,992 | -31% | 1 | 1 | 0% | 4,641 | 3,643 | -22% | 0 | 0 | — |
case-21 | pass→pass | 9,651 | 8,251 | -15% | 1 | 1 | 0% | 1,852 | 2,325 | +26% | 0 | 0 | — |
case-22 | pass→pass | 13,283 | 12,143 | -9% | 1 | 1 | 0% | 3,310 | 3,499 | +6% | 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 +18 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.