Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Provides a snapshot of the current operating state: active priorities, recent signals, pending action items, and system health. Without arguments, shows a high-level overview. With `--node`, shows detailed status for a specific node.
.claude/skills/miosa-osa-status/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -31% | 0% |
> Show current system state -- active nodes, recent signals, pending items.
/status [--node <name>] [--verbose]Provides a snapshot of the current operating state: active priorities, recent signals, pending action items, and system health. Without arguments, shows a high-level overview. With --node, shows detailed status for a specific node.
rhythm/today.md for current priorities.With --verbose: include full signal summaries and cross-references.
bash# System overview /status # Status for a specific node /status --node ai-masters # Verbose output with full details /status --verbose
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,968 | 9,479 | +19% | 1 | 1 | 0% | 1,172 | 1,666 | +42% | 0 | 0 | — |
case-02 | fail→fail | 6,747 | 8,539 | +27% | 1 | 1 | 0% | 1,014 | 1,585 | +56% | 0 | 0 | — |
case-03 | fail→pass | 17,802 | 30,213 | +70% | 1 | 1 | 0% | 2,923 | 4,803 | +64% | 0 | 0 | — |
case-04 | fail→pass | 8,257 | 5,135 | -38% | 1 | 1 | 0% | 1,240 | 1,026 | -17% | 0 | 0 | — |
case-05 | pass→pass | 14,627 | 2,084 | -86% | 1 | 1 | 0% | 2,276 | 510 | -78% | 0 | 0 | — |
case-06 | fail→pass | 14,147 | 8,651 | -39% | 1 | 1 | 0% | 2,087 | 1,523 | -27% | 0 | 0 | — |
case-07 | fail→pass | 13,205 | 7,599 | -42% | 1 | 1 | 0% | 1,995 | 1,373 | -31% | 0 | 0 | — |
case-08 | pass→pass | 17,435 | 2,539 | -85% | 1 | 1 | 0% | 3,116 | 495 | -84% | 0 | 0 | — |
case-09 | pass→pass | 10,671 | 2,340 | -78% | 1 | 1 | 0% | 1,700 | 493 | -71% | 0 | 0 | — |
case-10 | fail→pass | 6,711 | 3,440 | -49% | 1 | 1 | 0% | 1,028 | 714 | -31% | 0 | 0 | — |
case-11 | pass→pass | 9,861 | 5,552 | -44% | 1 | 1 | 0% | 1,479 | 978 | -34% | 0 | 0 | — |
case-12 | pass→pass | 4,935 | 2,573 | -48% | 1 | 1 | 0% | 666 | 576 | -14% | 0 | 0 | — |
case-13 | fail→pass | 12,398 | 2,256 | -82% | 1 | 1 | 0% | 2,006 | 608 | -70% | 0 | 0 | — |
case-14 | fail→pass | 20,347 | 1,976 | -90% | 1 | 1 | 0% | 3,403 | 522 | -85% | 0 | 0 | — |
case-15 | pass→pass | 14,259 | 4,587 | -68% | 1 | 1 | 0% | 2,336 | 859 | -63% | 0 | 0 | — |
case-16 | fail→pass | 5,677 | 2,574 | -55% | 1 | 1 | 0% | 830 | 520 | -37% | 0 | 0 | — |
case-17 | fail→pass | 1,476 | 3,914 | +165% | 1 | 1 | 0% | 174 | 473 | +172% | 0 | 0 | — |
case-18 | fail→pass | 13,688 | 2,406 | -82% | 1 | 1 | 0% | 2,128 | 542 | -75% | 0 | 0 | — |
case-19 | fail→pass | 12,921 | 3,917 | -70% | 1 | 1 | 0% | 1,907 | 885 | -54% | 0 | 0 | — |
case-20 | fail→fail | 10,217 | 5,645 | -45% | 1 | 1 | 0% | 1,710 | 1,055 | -38% | 0 | 0 | — |
case-21 | pass→pass | 8,080 | 7,120 | -12% | 1 | 1 | 0% | 1,051 | 1,076 | +2% | 0 | 0 | — |
case-22 | pass→pass | 12,064 | 12,246 | +2% | 1 | 1 | 0% | 2,028 | 1,561 | -23% | 0 | 0 | — |
case-23 | pass→pass | 14,784 | 5,817 | -61% | 1 | 1 | 0% | 2,262 | 1,303 | -42% | 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.