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

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

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

A high-quality, information-dense skill body: executable commands throughout, a disciplined workflow with validation and confirmation gates for risky operations, and clean progressive disclosure to per-topic rule files. The only weakness is mild redundancy between Critical Rules bullets and Key Patterns code examples.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — terse rule bullets, a selection table, and copy-paste CLI blocks with no padding explaining what shadcn or Tailwind is. It falls short of anchor 5 only because some content repeats: the Key Patterns code pairs re-illustrate rules already stated as bullets in Critical Rules (e.g. gap-* vs space-y-, size- vs w/h-*), which could be consolidated. It is clearly above the anchor-3 'some unnecessary explanation' level.	4 / 5
Actionability	Nearly everything is executable: exact CLI invocations (`npx shadcn@latest add <component> --dry-run`, `preset decode <code>`, `search @shadcn -q "sidebar" -t ui`), correct/wrong code pairs in Key Patterns, a need→component mapping table, and copy-paste-ready Quick Reference commands covering the common cases. This matches anchor 5; anchor 4 ('minor gaps') understates the coverage.	5 / 5
Workflow Clarity	The 9-step Workflow is clearly sequenced with explicit validation checkpoints: check installed components before add, --dry-run/--diff before updates, 'always read the added files and verify they are correct', fix issues before moving on, and confirmation gates for destructive actions ('Never use --overwrite without the user's explicit approval', ask before preset switching, don't guess the registry). Because the batch/destructive operations here do have validation and feedback loops, the workflow-cap-3 rule does not apply and the anchor-5 pattern is the best fit.	5 / 5
Progressive Disclosure	SKILL.md functions as an overview with well-signaled, one-level-deep references: each Critical Rules section links to its rules file (styling.md, forms.md, composition.md, icons.md, chat.md, base-vs-radix.md), and a Detailed References section lists cli.md, registry.md, and customization.md with one-line descriptions of what each contains. No nested references or inlined walls of API detail; navigation is easy. Note: the referenced bundle files were not present in the provided directory to verify existence, but the body's structure fully matches the anchor-5 example.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

An exemplary description: concrete third-person action list, explicit dual trigger clauses covering terms, files, and commands, and a distinctive niche with minimal conflict risk. It reads like the reference good examples rather than any weak pattern.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces" plus "Provides project context, component docs, and usage examples" — giving comprehensive, specific coverage rather than generic phrasing. Anchor 4 ('several specific actions; minor gaps') is too low since no meaningful capability is left out.	5 / 5
Completeness	Both 'what' and 'when' are explicit: what it does is enumerated in the first sentences, and the 'when' is stated twice with concrete triggers — "Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file" and "Also triggers for 'shadcn init'...". This is the anchor-5 pattern; no 'Use when' clause is missing.	5 / 5
Trigger Term Quality	Natural trigger coverage is comprehensive: "shadcn", "shadcn/ui", "component registries", "presets", "--preset codes", "components.json" file marker, and command phrases users would actually type ("shadcn init", "create an app with --preset", "switch to --preset"). This matches the top anchor's standard of synonyms plus file-extension-style markers.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (shadcn/ui tooling) with distinct, unambiguous triggers — the components.json file marker and named CLI commands are unlikely to fire for unrelated skills. It is far more distinguishable than the anchor-4 example ('PDF and Word document files'), which still carries cross-domain overlap.	5 / 5
	Total	20 / 20 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: MODSetter/SurfSense
Path: .agents/skills/shadcn/SKILL.md
Commit: a51f9a3

Reviewed: 2 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.