Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manage shadcn/ui components using MCP tools. Use when user needs to: (1) Add new shadcn components to a project (2) Build complex UI features requiring multiple components (3) Research component implementations and examples (4) Get component installation commands Triggers: "add shadcn", "shadcn component", "build UI with shadcn", "install component", "create form", "create dialog"
.claude/skills/microck-shadcn-management/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 150% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -25% | 0% |
Verify project setup:
shadcn___get_project_registriesIf no components.json exists, instruct user: npx shadcn@latest init
For simple component additions (e.g., "add a date picker"):
shadcn___search_items_in_registries(registries, query)
shadcn___view_items_in_registries(items: ["@shadcn/component-name"])
shadcn___get_item_examples_from_registries(registries, query: "component-demo")
shadcn___get_add_command_for_items(items: ["@shadcn/component-name"])
For multi-component features (e.g., "build a login form"), see references/workflows.md.
When to use Complex Build:
Common search queries:
form, input, select, checkbox, radio-groupcard, dialog, sheet, drawer, tabsalert, toast, skeleton, progressbutton, dropdown-menu, navigation-menuExample queries for demos: form-demo, card-with-form, dialog-demo
Always run audit:
shadcn___get_audit_checklistShadcn provides structural foundation with default styling. For custom aesthetics:
Invoke frontend-design skill when:
Workflow:
shadcn-management for component structure and compositionfrontend-design for visual customization:globals.csstailwind.config.jsCustomization targets:
@/app/globals.css - CSS variables, custom fontstailwind.config.js - theme colors, fonts, animations| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,526 | 3,029 | -60% | 1 | 1 | 0% | 1,592 | 897 | -44% | 0 | 0 | — |
case-02 | fail→fail | 10,831 | 2,861 | -74% | 1 | 1 | 0% | 2,320 | 808 | -65% | 0 | 0 | — |
case-03 | fail→fail | 33,224 | 4,464 | -87% | 1 | 1 | 0% | 6,199 | 902 | -85% | 0 | 0 | — |
case-04 | pass→pass | 4,109 | 3,330 | -19% | 1 | 1 | 0% | 715 | 1,125 | +57% | 0 | 0 | — |
case-05 | fail→fail | 7,993 | 3,540 | -56% | 1 | 1 | 0% | 1,326 | 785 | -41% | 0 | 0 | — |
case-06 | fail→pass | 9,702 | 3,216 | -67% | 1 | 1 | 0% | 1,596 | 1,157 | -28% | 0 | 0 | — |
case-07 | pass→pass | 9,762 | 6,565 | -33% | 1 | 1 | 0% | 1,655 | 1,223 | -26% | 0 | 0 | — |
case-08 | fail→pass | 10,029 | 5,477 | -45% | 1 | 1 | 0% | 1,448 | 1,565 | +8% | 0 | 0 | — |
case-09 | fail→fail | 16,805 | 3,402 | -80% | 1 | 1 | 0% | 2,582 | 804 | -69% | 0 | 0 | — |
case-10 | fail→fail | 6,164 | 2,261 | -63% | 1 | 1 | 0% | 891 | 899 | +1% | 0 | 0 | — |
case-11 | pass→pass | 20,579 | 19,890 | -3% | 1 | 1 | 0% | 3,771 | 4,553 | +21% | 0 | 0 | — |
case-12 | fail→pass | 3,204 | 3,423 | +7% | 1 | 1 | 0% | 507 | 1,269 | +150% | 0 | 0 | — |
case-13 | pass→pass | 10,998 | 8,564 | -22% | 1 | 1 | 0% | 2,145 | 2,240 | +4% | 0 | 0 | — |
case-14 | pass→pass | 14,583 | 5,534 | -62% | 1 | 1 | 0% | 2,401 | 1,602 | -33% | 0 | 0 | — |
case-15 | pass→pass | 11,415 | 2,090 | -82% | 1 | 1 | 0% | 1,824 | 1,000 | -45% | 0 | 0 | — |
case-16 | fail→pass | 19,255 | 6,162 | -68% | 1 | 1 | 0% | 2,359 | 1,156 | -51% | 0 | 0 | — |
case-17 | fail→pass | 8,806 | 2,903 | -67% | 1 | 1 | 0% | 1,485 | 1,107 | -25% | 0 | 0 | — |
case-18 | fail→fail | 8,832 | 1,850 | -79% | 1 | 1 | 0% | 1,447 | 854 | -41% | 0 | 0 | — |
case-19 | pass→pass | 21,109 | 2,136 | -90% | 1 | 1 | 0% | 1,434 | 957 | -33% | 0 | 0 | — |
case-20 | pass→pass | 14,739 | 12,745 | -14% | 1 | 1 | 0% | 2,720 | 2,843 | +5% | 0 | 0 | — |
case-21 | pass→pass | 13,000 | 9,330 | -28% | 1 | 1 | 0% | 2,435 | 2,219 | -9% | 0 | 0 | — |
case-22 | pass→pass | 14,614 | 12,147 | -17% | 1 | 1 | 0% | 2,977 | 2,911 | -2% | 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 17 counted toward the lift figure. The other 5 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 +23 percentage points is the difference between those two pass rates over the 17 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.