shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. 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

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is shadcn in shadcn-ui/ui

Quality

Content

92%

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

A high-quality, actionable body with tight workflows and executable guidance that assumes Claude's competence. The one weak point is progressive disclosure: the skill points to several rules/ and reference files that are not present in the bundle.

Suggestions

Ship the referenced bundle files (rules/forms.md, rules/composition.md, rules/icons.md, rules/styling.md, rules/base-vs-radix.md, cli.md, customization.md) so the one-level-deep progressive disclosure actually resolves.

Reduce the slight overlap between the Critical Rules bullet lists and the Key Patterns code block so each rule appears authoritatively in one place.

Consider moving the long Quick Reference command catalog into cli.md to keep the SKILL.md overview leaner.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — terse principle bullets and correct/wrong code pairs with no explanation of what shadcn or Tailwind are, and every section earns its place. It sits well above the verbose/knowledge-explaining bar; only minor rule/pattern overlap keeps it from being maximally tight.	3 / 3
Actionability	Provides fully executable commands (npx shadcn@latest info/add/search/docs, --dry-run, --diff) and concrete copy-paste tsx examples with correct vs. wrong pairs, meeting the score-3 anchor for executable, specific guidance.	3 / 3
Workflow Clarity	The 9-step Workflow and Updating Components sections give a clear sequence with explicit validation checkpoints ("always read the added files and verify", "Fix all issues before moving on", "Never use --overwrite without explicit approval") and feedback loops for the risky add/preset operations, matching the score-3 anchor.	3 / 3
Progressive Disclosure	The structure is well-designed — a concise overview with clearly signaled one-level-deep references (rules/*.md, cli.md, customization.md) and a Detailed References section — but the referenced files are absent from the bundle, so the disclosed depth does not actually exist as shipped.	2 / 3
	Total	11 / 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 names concrete capabilities, provides explicit trigger guidance, and is narrowly scoped to shadcn/ui. It cleanly satisfies the what/when/distinctiveness requirements with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "adding, searching, fixing, debugging, styling, and composing UI" plus "Provides project context, component docs, and usage examples" — matching the score-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (manages components via adding/searching/fixing/etc.) and when with "Applies when..." and "Also triggers for..." clauses, matching the score-3 anchor for clear what-and-when with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms a user would actually say — "shadcn/ui", "component registries", "presets", "--preset codes", "components.json", "shadcn init", "create an app with --preset", "switch to --preset" — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear shadcn/ui niche with distinct triggers (components.json file, preset codes) unlikely to fire for unrelated skills.	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: 14 missing	Warning

	Total	14 / 16 Passed

Repository: graphif/project-graph
Path: .agents/skills/shadcn/SKILL.md
Commit: cea8af2

Reviewed: about 14 hours 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.