Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →/schedule [--week <date>] [--gaps]
.claude/skills/miosa-osa-schedule/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 137% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 317% | 0% |
/schedule --week <date>] --gaps]
Content calendar management -- view, plan, and identify gaps.
| Arg | Type | Required | Description | |-----|------|----------|-------------| | --week | date | No | Week to view/plan. Default: current week | | --gaps | flag | No | Highlight gaps in the next 4 weeks |
Genre: plan Format: Markdown calendar table
Produces:
1. Load current editorial calendar
2. Display scheduled content with status (planned/in-progress/ready/published)
3. If --gaps: compare against target cadence and flag empty slots
4. Check pillar mix balance (60% evergreen, 20% timely, 20% thought leadership)
5. List upcoming deadlines for all in-progress content/schedule
/schedule --week 2026-04-01
/schedule --gaps| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 18,381 | 18,450 | +0% | 1 | 1 | 0% | 2,756 | 3,845 | +40% | 0 | 0 | — |
case-01 | fail→pass | 16,056 | 24,283 | +51% | 1 | 1 | 0% | 3,129 | 2,940 | -6% | 0 | 0 | — |
case-02 | fail→pass | 13,811 | 15,011 | +9% | 1 | 1 | 0% | 2,390 | 3,165 | +32% | 0 | 0 | — |
case-03 | fail→pass | 18,093 | 17,916 | -1% | 1 | 1 | 0% | 3,202 | 2,720 | -15% | 0 | 0 | — |
case-04 | pass→pass | 46,226 | 23,795 | -49% | 1 | 1 | 0% | 3,715 | 3,523 | -5% | 0 | 0 | — |
case-06 | pass→pass | 20,294 | 22,946 | +13% | 1 | 1 | 0% | 3,741 | 4,329 | +16% | 0 | 0 | — |
case-07 | fail→pass | 10,760 | 21,527 | +100% | 1 | 1 | 0% | 1,481 | 3,517 | +137% | 0 | 0 | — |
case-08 | fail→pass | 4,602 | 13,172 | +186% | 1 | 1 | 0% | 641 | 2,672 | +317% | 0 | 0 | — |
case-09 | fail→pass | 15,170 | 11,953 | -21% | 1 | 1 | 0% | 2,134 | 2,511 | +18% | 0 | 0 | — |
case-10 | fail→pass | 10,740 | 2,243 | -79% | 1 | 1 | 0% | 1,417 | 566 | -60% | 0 | 0 | — |
case-11 | fail→pass | 7,614 | 1,785 | -77% | 1 | 1 | 0% | 857 | 560 | -35% | 0 | 0 | — |
case-12 | fail→pass | 10,278 | 1,968 | -81% | 1 | 1 | 0% | 1,692 | 667 | -61% | 0 | 0 | — |
case-13 | pass→pass | 17,421 | 16,157 | -7% | 1 | 1 | 0% | 3,046 | 2,630 | -14% | 0 | 0 | — |
case-14 | pass→pass | 16,286 | 11,237 | -31% | 1 | 1 | 0% | 2,028 | 1,627 | -20% | 0 | 0 | — |
case-15 | pass→pass | 11,104 | 2,571 | -77% | 1 | 1 | 0% | 1,611 | 608 | -62% | 0 | 0 | — |
case-16 | fail→pass | 10,488 | 5,491 | -48% | 1 | 1 | 0% | 1,605 | 967 | -40% | 0 | 0 | — |
case-17 | pass→pass | 11,436 | 2,867 | -75% | 1 | 1 | 0% | 1,711 | 817 | -52% | 0 | 0 | — |
case-18 | pass→pass | 14,187 | 6,687 | -53% | 1 | 1 | 0% | 1,987 | 1,519 | -24% | 0 | 0 | — |
case-19 | pass→pass | 11,837 | 5,105 | -57% | 1 | 1 | 0% | 1,727 | 1,224 | -29% | 0 | 0 | — |
case-20 | pass→pass | 8,976 | 4,549 | -49% | 1 | 1 | 0% | 1,140 | 1,050 | -8% | 0 | 0 | — |
case-21 | fail→pass | 9,606 | 2,835 | -70% | 1 | 1 | 0% | 1,105 | 638 | -42% | 0 | 0 | — |
case-22 | pass→pass | 5,590 | 1,958 | -65% | 1 | 1 | 0% | 682 | 520 | -24% | 0 | 0 | — |
case-23 | fail→fail | 5,772 | 2,180 | -62% | 1 | 1 | 0% | 817 | 647 | -21% | 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 +48 percentage points is the difference between those two pass rates over the 23 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.