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 the user wants to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.
.claude/skills/coco-research-update-cursor-settings/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-18 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-01 | ✓→✗ | ▼ Worse | -18% | 0% |
| case-03 | ✓→✗ | ▼ Worse | 10% | 0% |
| case-04 | ✓→✗ | ▼ Worse | -41% | 0% |
| case-05 | ✓→✗ | ▼ Worse | -3% | 0% |
This skill guides you through modifying Cursor/VSCode user settings. Use this when the user wants 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 |
typescript// Read the settings file first const settingsPath = "~/Library/Application Support/Cursor/User/settings.json"; // Use the Read tool 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.When modifying settings.json:
| 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 | | "cursor style" | editor.cursorStyle | | "smooth scrolling" | editor.smoothScrolling |
// and /* */). When reading, be aware comments may exist. When writing, preserve comments if possible..vscode/settings.json) apply only to the current project.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 8,868 | 17,675 | +99% | 1 | 1 | 0% | 1,304 | 1,175 | -10% | 0 | 0 | — |
case-01 | pass→fail | 8,595 | 13,734 | +60% | 1 | 1 | 0% | 1,505 | 1,228 | -18% | 0 | 0 | — |
case-03 | pass→fail | 8,252 | 16,501 | +100% | 1 | 1 | 0% | 960 | 1,053 | +10% | 0 | 0 | — |
case-04 | pass→fail | 12,514 | 6,121 | -51% | 1 | 1 | 0% | 2,159 | 1,276 | -41% | 0 | 0 | — |
case-05 | pass→fail | 13,889 | 12,725 | -8% | 1 | 1 | 0% | 1,283 | 1,248 | -3% | 0 | 0 | — |
case-06 | pass→fail | 11,266 | 7,970 | -29% | 1 | 1 | 0% | 1,055 | 1,192 | +13% | 0 | 0 | — |
case-07 | pass→fail | 6,082 | 20,140 | +231% | 1 | 1 | 0% | 1,107 | 1,137 | +3% | 0 | 0 | — |
case-08 | pass→fail | 9,845 | 25,767 | +162% | 1 | 1 | 0% | 842 | 1,189 | +41% | 0 | 0 | — |
case-09 | pass→fail | 13,741 | 6,910 | -50% | 1 | 1 | 0% | 1,686 | 1,215 | -28% | 0 | 0 | — |
case-10 | pass→fail | 5,647 | 11,012 | +95% | 1 | 1 | 0% | 969 | 1,116 | +15% | 0 | 0 | — |
case-11 | pass→fail | 12,355 | 18,062 | +46% | 1 | 1 | 0% | 1,034 | 1,120 | +8% | 0 | 0 | — |
case-12 | pass→fail | 10,255 | 11,550 | +13% | 1 | 1 | 0% | 977 | 1,217 | +25% | 0 | 0 | — |
case-13 | fail→fail | 10,802 | 5,779 | -47% | 1 | 1 | 0% | 759 | 1,441 | +90% | 0 | 0 | — |
case-14 | pass→fail | 12,212 | 18,455 | +51% | 1 | 1 | 0% | 981 | 1,323 | +35% | 0 | 0 | — |
case-15 | pass→fail | 12,472 | 12,978 | +4% | 1 | 1 | 0% | 1,279 | 1,229 | -4% | 0 | 0 | — |
case-16 | pass→fail | 9,422 | 17,224 | +83% | 1 | 1 | 0% | 784 | 1,216 | +55% | 0 | 0 | — |
case-17 | pass→fail | 11,965 | 17,631 | +47% | 1 | 1 | 0% | 1,277 | 1,120 | -12% | 0 | 0 | — |
case-18 | fail→pass | 10,882 | 19,428 | +79% | 1 | 1 | 0% | 985 | 1,665 | +69% | 0 | 0 | — |
case-19 | pass→fail | 6,232 | 17,424 | +180% | 1 | 1 | 0% | 1,166 | 1,435 | +23% | 0 | 0 | — |
case-20 | pass→pass | 6,946 | 8,432 | +21% | 1 | 1 | 0% | 1,007 | 1,232 | +22% | 0 | 0 | — |
case-21 | pass→fail | 9,829 | 9,754 | -1% | 1 | 1 | 0% | 2,027 | 1,084 | -47% | 0 | 0 | — |
case-22 | fail→fail | 4,141 | 12,471 | +201% | 1 | 1 | 0% | 695 | 1,239 | +78% | 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. 22 cases were attempted, and 3 counted toward the lift figure. The other 19 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 -73 percentage points is the difference between those two pass rates over the 3 comparable cases. 19 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.