Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Change terminal command line prompt theme. Globally manage the display style of all x-cmd interactive components. Supports multiple theme vendors: theme, starship, ohmyposh. **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-theme/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 10% | 0% |
> Change terminal command line prompt theme and manage display styles.
bash# Open interactive theme preview x theme # List available themes x theme ls # Use a theme x theme use robby
--app| Command | Description | |---------|-------------| | x theme | Open interactive theme preview (default) | | x theme --app | Open theme preview client | | x theme ls | List all themes | | x theme ls --info | List current environment theme info | | x theme use <name> | Use theme globally | | x theme unuse | Unset theme | | x theme try <name> | Try theme in current session | | x theme untry | Cancel try mode | | x theme current | Show current theme | | x theme update | Update theme resources | | x theme font | Install fonts | | x theme feature use <feature> | Enable feature globally | | x theme feature try <feature> | Try feature in current session |
| Vendor | Description | |--------|-------------| | theme | x-cmd built-in themes (el, ide, mini, l series) | | starship | Starship.rs cross-shell prompt | | ohmyposh | Oh-My-Posh prompt theme engine |
bash# Open interactive theme selector x theme # Use a theme globally x theme use robby # Use random theme x theme use random # Use random from specific themes x theme use random "ys,ya,vitesse"
bash# Try theme in current session only x theme try robby # Cancel try x theme untry
bash# Enable transient mode globally x theme feature use transient_enable always # Disable transient mode x theme feature use transient_enable never # Try emoji feature x theme feature try emoji -t festival
bash# Use starship theme via x theme x theme use --vendor starship gruvbox-rainbow # Use ohmyposh theme via x theme x theme use --vendor ohmyposh montys
| Feature | Description | |---------|-------------| | transient_enable | Simplify prompt after command execution | | transient_cwd | Show cwd in transient mode | | transient_time | Show execution time in transient mode | | emoji | Enable emoji in prompt | | symbol | Use symbols in prompt | | zshplugin | Load zsh plugins |
| Series | Description | |--------|-------------| | el | Elegant line themes | | ide | IDE-style themes | | mini | Minimal themes | | l | Lightweight themes |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 6,860 | 3,012 | -56% | 1 | 1 | 0% | 1,020 | 1,224 | +20% | 0 | 0 | — |
case-02 | fail→pass | 17,120 | 3,138 | -82% | 1 | 1 | 0% | 1,024 | 1,330 | +30% | 0 | 0 | — |
case-03 | fail→pass | 8,635 | 3,390 | -61% | 1 | 1 | 0% | 1,270 | 1,302 | +3% | 0 | 0 | — |
case-04 | fail→pass | 19,791 | 2,790 | -86% | 1 | 1 | 0% | 1,321 | 1,185 | -10% | 0 | 0 | — |
case-05 | fail→pass | 20,355 | 3,951 | -81% | 1 | 1 | 0% | 1,333 | 1,461 | +10% | 0 | 0 | — |
case-06 | pass→pass | 6,522 | 2,538 | -61% | 1 | 1 | 0% | 1,044 | 1,134 | +9% | 0 | 0 | — |
case-07 | fail→pass | 9,876 | 3,931 | -60% | 1 | 1 | 0% | 1,469 | 1,291 | -12% | 0 | 0 | — |
case-08 | fail→pass | 6,290 | 3,518 | -44% | 1 | 1 | 0% | 1,055 | 1,353 | +28% | 0 | 0 | — |
case-09 | fail→pass | 6,610 | 3,242 | -51% | 1 | 1 | 0% | 928 | 1,232 | +33% | 0 | 0 | — |
case-10 | fail→pass | 11,854 | 5,775 | -51% | 1 | 1 | 0% | 1,103 | 1,405 | +27% | 0 | 0 | — |
case-11 | pass→pass | 13,463 | 3,012 | -78% | 1 | 1 | 0% | 998 | 1,221 | +22% | 0 | 0 | — |
case-12 | pass→pass | 6,908 | 3,663 | -47% | 1 | 1 | 0% | 951 | 1,117 | +17% | 0 | 0 | — |
case-13 | pass→pass | 7,224 | 2,522 | -65% | 1 | 1 | 0% | 1,240 | 1,189 | -4% | 0 | 0 | — |
case-14 | pass→pass | 6,016 | 2,952 | -51% | 1 | 1 | 0% | 923 | 1,052 | +14% | 0 | 0 | — |
case-15 | fail→pass | 10,233 | 3,393 | -67% | 1 | 1 | 0% | 1,517 | 1,201 | -21% | 0 | 0 | — |
case-16 | pass→fail | 5,531 | 3,729 | -33% | 1 | 1 | 0% | 756 | 1,275 | +69% | 0 | 0 | — |
case-17 | pass→pass | 9,590 | 2,460 | -74% | 1 | 1 | 0% | 674 | 1,047 | +55% | 0 | 0 | — |
case-18 | pass→pass | 8,203 | 3,046 | -63% | 1 | 1 | 0% | 1,181 | 1,230 | +4% | 0 | 0 | — |
case-19 | fail→pass | 7,048 | 2,803 | -60% | 1 | 1 | 0% | 997 | 1,138 | +14% | 0 | 0 | — |
case-20 | fail→pass | 16,462 | 2,780 | -83% | 1 | 1 | 0% | 1,250 | 1,160 | -7% | 0 | 0 | — |
case-21 | fail→pass | 18,848 | 2,460 | -87% | 1 | 1 | 0% | 1,713 | 1,075 | -37% | 0 | 0 | — |
case-22 | fail→pass | 17,340 | 5,412 | -69% | 1 | 1 | 0% | 1,411 | 1,146 | -19% | 0 | 0 | — |
case-23 | pass→pass | 6,366 | 2,617 | -59% | 1 | 1 | 0% | 762 | 1,126 | +48% | 0 | 0 | — |
case-24 | pass→pass | 15,587 | 23,095 | +48% | 1 | 1 | 0% | 2,657 | 3,491 | +31% | 0 | 0 | — |
case-25 | pass→pass | 10,106 | 7,142 | -29% | 1 | 1 | 0% | 1,690 | 1,940 | +15% | 0 | 0 | — |
case-26 | pass→pass | 12,124 | 8,766 | -28% | 1 | 1 | 0% | 1,916 | 2,086 | +9% | 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. 26 cases were attempted. The headline lift of +33 percentage points is the difference between those two pass rates over the 26 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.