Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.
.claude/skills/kunanonj-cursor-update-cursor-settings/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 83% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 52% | 0% |
Modify Cursor/VSCode user settings. Use this when you want to change editor settings, preferences, configuration, themes, keybindings, or any settings.json values.
| OS | Path | |----|------| | macOS | ~/Library/Application Support/Cursor/User/settings.json | | Linux | ~/.config/Cursor/User/settings.json | | Windows | %APPDATA%\Cursor\User\settings.json |
Read the settings file first to get current contents.
Common setting categories:
editor.fontSize, editor.tabSize, editor.wordWrap, editor.formatOnSaveworkbench.colorTheme, workbench.iconTheme, workbench.sideBar.locationfiles.autoSave, files.exclude, files.associationsterminal.integrated.fontSize, terminal.integrated.shell.*cursor. or aipopup.// and /* */). Preserve comments when possible..vscode/settings.json): Apply only to the current project~/.cursor/cli-config.json. For IDE agent, it is controlled from Cursor Settings > Agent > Attribution.| User Request | Setting | |--------------|---------| | "bigger/smaller font" | editor.fontSize | | "change tab size" | editor.tabSize | | "format on save" | editor.formatOnSave | | "word wrap" | editor.wordWrap | | "change theme" | workbench.colorTheme | | "hide minimap" | editor.minimap.enabled | | "auto save" | files.autoSave | | "line numbers" | editor.lineNumbers | | "bracket matching" | editor.bracketPairColorization.enabled | | "smooth scrolling" | editor.smoothScrolling |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,029 | 4,748 | +18% | 1 | 1 | 0% | 749 | 1,230 | +64% | 0 | 0 | — |
case-02 | fail→fail | 5,783 | 6,014 | +4% | 1 | 1 | 0% | 1,101 | 1,040 | -6% | 0 | 0 | — |
case-03 | fail→fail | 4,099 | 5,788 | +41% | 1 | 1 | 0% | 840 | 951 | +13% | 0 | 0 | — |
case-04 | fail→fail | 4,835 | 3,348 | -31% | 1 | 1 | 0% | 837 | 1,268 | +51% | 0 | 0 | — |
case-05 | pass→pass | 3,170 | 1,969 | -38% | 1 | 1 | 0% | 541 | 991 | +83% | 0 | 0 | — |
case-06 | pass→pass | 3,615 | 1,919 | -47% | 1 | 1 | 0% | 679 | 1,030 | +52% | 0 | 0 | — |
case-07 | fail→pass | 9,052 | 1,573 | -83% | 1 | 1 | 0% | 1,706 | 957 | -44% | 0 | 0 | — |
case-08 | fail→pass | 6,000 | 3,812 | -36% | 1 | 1 | 0% | 1,174 | 1,513 | +29% | 0 | 0 | — |
case-09 | pass→pass | 5,332 | 2,631 | -51% | 1 | 1 | 0% | 917 | 1,157 | +26% | 0 | 0 | — |
case-10 | pass→pass | 2,573 | 2,071 | -20% | 1 | 1 | 0% | 461 | 1,098 | +138% | 0 | 0 | — |
case-11 | pass→pass | 3,841 | 3,078 | -20% | 1 | 1 | 0% | 707 | 1,177 | +66% | 0 | 0 | — |
case-12 | pass→pass | 4,393 | 3,071 | -30% | 1 | 1 | 0% | 857 | 1,124 | +31% | 0 | 0 | — |
case-13 | pass→pass | 4,252 | 2,384 | -44% | 1 | 1 | 0% | 813 | 1,155 | +42% | 0 | 0 | — |
case-14 | pass→pass | 2,120 | 3,167 | +49% | 1 | 1 | 0% | 357 | 1,236 | +246% | 0 | 0 | — |
case-15 | pass→pass | 1,439 | 1,851 | +29% | 1 | 1 | 0% | 304 | 999 | +229% | 0 | 0 | — |
case-16 | pass→pass | 14,054 | 6,161 | -56% | 1 | 1 | 0% | 2,451 | 1,744 | -29% | 0 | 0 | — |
case-17 | pass→pass | 5,283 | 1,242 | -76% | 1 | 1 | 0% | 795 | 880 | +11% | 0 | 0 | — |
case-18 | pass→pass | 8,101 | 2,658 | -67% | 1 | 1 | 0% | 1,341 | 1,056 | -21% | 0 | 0 | — |
case-19 | fail→pass | 4,911 | 2,677 | -45% | 1 | 1 | 0% | 892 | 1,180 | +32% | 0 | 0 | — |
case-20 | pass→pass | 5,670 | 4,377 | -23% | 1 | 1 | 0% | 1,160 | 1,512 | +30% | 0 | 0 | — |
case-21 | pass→pass | 6,324 | 4,627 | -27% | 1 | 1 | 0% | 1,186 | 1,570 | +32% | 0 | 0 | — |
case-22 | pass→pass | 5,736 | 4,199 | -27% | 1 | 1 | 0% | 1,021 | 1,417 | +39% | 0 | 0 | — |
case-23 | pass→pass | 7,664 | 4,808 | -37% | 1 | 1 | 0% | 1,397 | 1,548 | +11% | 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, and 21 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +13 percentage points is the difference between those two pass rates over the 21 comparable cases. 3 cases got worse with the skill loaded, and they are 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.