Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →SMART disk health monitoring tool. Check disk health, temperature, and attributes using smartctl. **Dependency**: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
.claude/skills/x-cmd-x-smart/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -56% | 0% |
> SMART (Self-Monitoring, Analysis, and Reporting Technology) disk health checking tool.
bashx smart --ls
bash# macOS x smart -a /dev/disk0 # Linux x smart -a /dev/sda # Windows x smart -a C:
bashx smart
Opens interactive UI to select disk and display SMART information.
| Command | Description | |---------|-------------| | x smart --ls | List available disk paths | | x smart -a <disk> | Display all SMART information for the disk | | x smart -H <disk> | Display disk health status only | | x smart --app | Interactive disk selection (default) | | x smart : disk health | Search smartmontools.com via DuckDuckGo | | x smart --help | Show help information |
bash# List all disks x smart --ls # Check specific disk (macOS) x smart -a /dev/disk0 # Check specific disk (Linux) x smart -a /dev/sda # Check health only x smart -H /dev/disk0
bashx smart : disk health x smart : temperature threshold
/dev/disk0, /dev/disk1, etc./dev/sda, /dev/nvme0n1, etc.sudo for disk accessC:, D:, etc.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 8,899 | 2,596 | -71% | 1 | 1 | 0% | 1,489 | 811 | -46% | 0 | 0 | — |
case-02 | fail→pass | 7,227 | 3,264 | -55% | 1 | 1 | 0% | 1,108 | 874 | -21% | 0 | 0 | — |
case-03 | fail→pass | 8,822 | 2,991 | -66% | 1 | 1 | 0% | 1,227 | 867 | -29% | 0 | 0 | — |
case-04 | pass→pass | 9,857 | 3,917 | -60% | 1 | 1 | 0% | 1,521 | 807 | -47% | 0 | 0 | — |
case-05 | fail→pass | 10,817 | 8,107 | -25% | 1 | 1 | 0% | 1,741 | 857 | -51% | 0 | 0 | — |
case-06 | fail→pass | 11,872 | 2,608 | -78% | 1 | 1 | 0% | 1,822 | 798 | -56% | 0 | 0 | — |
case-07 | fail→pass | 24,587 | 2,975 | -88% | 1 | 1 | 0% | 2,015 | 919 | -54% | 0 | 0 | — |
case-08 | pass→pass | 10,561 | 2,967 | -72% | 1 | 1 | 0% | 1,722 | 808 | -53% | 0 | 0 | — |
case-09 | pass→pass | 25,597 | 2,885 | -89% | 1 | 1 | 0% | 1,877 | 857 | -54% | 0 | 0 | — |
case-10 | fail→pass | 12,579 | 3,487 | -72% | 1 | 1 | 0% | 1,738 | 954 | -45% | 0 | 0 | — |
case-11 | pass→pass | 7,860 | 3,401 | -57% | 1 | 1 | 0% | 975 | 758 | -22% | 0 | 0 | — |
case-12 | fail→pass | 10,226 | 5,482 | -46% | 1 | 1 | 0% | 1,463 | 1,227 | -16% | 0 | 0 | — |
case-13 | fail→pass | 9,108 | 3,112 | -66% | 1 | 1 | 0% | 1,529 | 817 | -47% | 0 | 0 | — |
case-14 | pass→pass | 6,952 | 2,714 | -61% | 1 | 1 | 0% | 1,026 | 798 | -22% | 0 | 0 | — |
case-15 | fail→pass | 5,999 | 3,479 | -42% | 1 | 1 | 0% | 774 | 818 | +6% | 0 | 0 | — |
case-16 | fail→pass | 10,126 | 3,388 | -67% | 1 | 1 | 0% | 1,580 | 765 | -52% | 0 | 0 | — |
case-17 | pass→pass | 11,795 | 3,280 | -72% | 1 | 1 | 0% | 1,943 | 761 | -61% | 0 | 0 | — |
case-18 | pass→pass | 5,913 | 3,385 | -43% | 1 | 1 | 0% | 876 | 788 | -10% | 0 | 0 | — |
case-19 | fail→pass | 12,715 | 2,767 | -78% | 1 | 1 | 0% | 1,491 | 854 | -43% | 0 | 0 | — |
case-20 | pass→pass | 14,370 | 9,215 | -36% | 1 | 1 | 0% | 2,325 | 2,026 | -13% | 0 | 0 | — |
case-21 | pass→pass | 22,408 | 10,966 | -51% | 1 | 1 | 0% | 2,027 | 2,391 | +18% | 0 | 0 | — |
case-22 | pass→pass | 10,638 | 7,479 | -30% | 1 | 1 | 0% | 1,767 | 1,565 | -11% | 0 | 0 | — |
case-23 | pass→pass | 12,003 | 8,979 | -25% | 1 | 1 | 0% | 1,971 | 1,676 | -15% | 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 +52 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.