CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

Excellent in-body content: lean, highly actionable, with strong sequenced workflows and safety gates around destructive operations. The major defect is the bundle itself — all referenced detail files (rules/*.md, cli.md, customization.md) are missing, breaking progressive disclosure entirely and leaving dangling links throughout Critical Rules and Detailed References.

Suggestions

Include the referenced files in the bundle: rules/styling.md, rules/forms.md, rules/composition.md, rules/icons.md, rules/base-vs-radix.md, cli.md, and customization.md are linked throughout (Critical Rules, Key Fields, Detailed References) but none exist in the skill directory.

Trim the redundancy between "Key Patterns" and "Critical Rules" — the gap/space-y, size/w-h, and semantic-color examples appear in both sections; keeping them only in one (or in the rule files) would tighten the token budget.

Merge the two Critical Rules subsections that both point to composition.md ("Component Structure" and "Use Components, Not Custom Markup"), or give the second group its own reference file so each subsection maps to a distinct, existing detail file.

DimensionReasoningScore

Conciseness

The body is dense with skill-specific knowledge — CLI flags, composition rules, key fields — and explains nothing Claude already knows. Kept from 5 by redundancy: the "Key Patterns" section restates Critical Rules bullets (gap vs space-y, size vs w/h, semantic colors) verbatim, and "Component Structure" and "Use Components, Not Custom Markup" both duplicate their shared composition.md link with overlapping guidance.

4 / 5

Actionability

Copy-paste-ready throughout: exact commands ("npx shadcn@latest add button card dialog", "--dry-run", "--diff <file>"), a needs-to-component table, complete JSX pattern snippets, and concrete field-by-field guidance (aliases, isRSC, iconLibrary). It covers the common cases fully.

5 / 5

Workflow Clarity

The 9-step Workflow is clearly sequenced with validation checkpoints ("always read the added files and verify they are correct", check installed components before add), and Updating Components is a full feedback loop: dry-run → per-file diff → decide → preserve local changes, with "Never use --overwrite without the user's explicit approval" gating the destructive path. Preset switching even forces an explicit reinstall/merge/skip user decision.

5 / 5

Progressive Disclosure

The body's structure is textbook progressive disclosure — an overview with well-labeled, one-level-deep links (rules/forms.md, rules/composition.md, cli.md, customization.md) — but scoring against the actual bundle: none of the referenced files exist. The bundle contains only SKILL.md and two unreferenced PNGs in assets/, so every detailed-reference link is broken and the disclosed detail is unreachable. Not a 4/5 because the navigation fails in practice; not a 2 because the in-body structure and signaling are themselves clear and the split is appropriate.

3 / 5

Total

17

/

20

Passed

Description

92%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.

A third-person, dense, trigger-rich description that explicitly states both capabilities and activation conditions. All four dimensions are strong; the only nit is a few missing natural synonyms (e.g. "shadcn add", "tailwind") that keep trigger coverage just short of comprehensive.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "adding, searching, fixing, debugging, styling, and composing UI" plus "Provides project context, component docs, and usage examples" — comprehensively covering the skill's duties. Not the 4 anchor's "minor gaps": the action list spans install, maintain, and consult workflows with no obvious missing capability.

5 / 5

Completeness

Explicitly answers both: what ("Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI") and when ("Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for 'shadcn init'...") with concrete trigger phrases. Matches the 5 anchor exactly.

5 / 5

Trigger Term Quality

Strong natural triggers: "shadcn/ui", "component registries", "presets", "--preset codes", "components.json", "shadcn init", "switch to --preset". Not 5 because a few natural phrasings are absent — e.g. "add a component", "shadcn add", "tailwind", or "radix", which users of this skill would plausibly say.

4 / 5

Distinctiveness Conflict Risk

A clear niche with distinct triggers — shadcn-specific terms ("components.json", "--preset codes", "shadcn init") are unlikely to fire for any other skill. The "any project with a components.json file" clause is a precise, unambiguous file-based signal, not generic overlap.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 14 missing

Warning

Total

14

/

16

Passed

Repository
udecode/plate
Reviewed

Table of Contents

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.