shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced body with strong CLI/code examples and validation-gated workflows, but it carries some redundancy between Critical Rules and Key Patterns and, more seriously, points to a set of detail files that are absent from the bundle, leaving its progressive disclosure structurally sound but practically broken.

Suggestions

Ship the referenced detail files (rules/styling.md, rules/forms.md, rules/composition.md, rules/chat.md, rules/icons.md, rules/base-vs-radix.md, cli.md, registry.md, customization.md) or remove the links — currently every 'See ...' reference and the Detailed References index resolves to a missing file.

De-duplicate 'Key Patterns' against 'Critical Rules' by either removing the repeated gap-*/size-*/Badge examples or compressing Key Patterns to only the patterns not already covered by the rule bullets.

Reference the existing assets (shadcn.png / shadcn-small.png) where relevant, or drop them, so the bundle and the body agree on what files exist.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining concepts Claude already knows, but the 'Key Patterns' code block re-demonstrates rules already stated verbatim in 'Critical Rules' (gap-* vs space-y-, size-, Badge variants), which is accurate but redundant and could be tightened. This sits above the verbose level-1 anchor but below the 'every token earns its place' level-3 anchor.	2 / 3
Actionability	Guidance is fully executable: copy-paste TSX snippets, concrete 'npx shadcn@latest ...' commands throughout, a full Quick Reference command catalog, and a Component Selection table mapping needs to specific components. This matches the highest anchor of copy-paste-ready, specific examples.	3 / 3
Workflow Clarity	The 9-step Workflow and the 'Updating Components' section are clearly sequenced with explicit validation checkpoints — 'always check the components list' before add, '--dry-run'/'--diff' to preview, 'always read the added files and verify they are correct', and 'Never use --overwrite without the user's explicit approval'. Destructive/batch operations (add --all, preset apply) carry validation and confirmation steps, so workflow clarity is not capped at 2.	3 / 3
Progressive Disclosure	The in-body structure is well-signaled with one-level-deep references (rules/*.md, cli.md, registry.md, customization.md) and a 'Detailed References' index, but scored against the actual bundle none of these referenced files exist — the bundle contains only two unreferenced PNG assets. So the split is signaled on paper but unresolved in practice, falling short of the working-navigation level-3 anchor and sitting above the monolithic level-1 anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities and provides explicit, varied trigger phrasings covering both interactive and programmatic shadcn usage. It cleanly answers what the skill does and when to invoke it with minimal fluff.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'adding, searching, fixing, debugging, styling, and composing UI' and 'Provides project context, component docs, and usage examples' — matching the anchor that names several specific concrete actions.	3 / 3
Completeness	It answers both 'what' ('Manages shadcn components and projects...') and 'when' ('Applies when working with shadcn/ui... Also triggers for...') with explicit trigger guidance, satisfying the highest anchor; it is not capped at 2 because a clear 'Use when/trigger' clause is present.	3 / 3
Trigger Term Quality	It surfaces natural terms users would actually say — 'shadcn/ui', 'component registries', 'presets', '--preset codes', 'components.json file', and quoted triggers like 'shadcn init' and 'create an app with --preset' — giving broad coverage of phrasings rather than jargon alone.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to shadcn/ui via distinctive triggers ('components.json file', '--preset codes', 'shadcn init'), making it unlikely to fire for unrelated skills; it is well above the 'could overlap' level 2 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 17 missing	Warning

	Total	14 / 16 Passed

Repository: shadcn-ui/ui
Commit: d0fae52

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.