CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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".

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The body itself is excellent — maximally actionable commands and code, a well-sequenced workflow with real validation checkpoints, and no filler. However, its progressive-disclosure design is broken in practice: all seven referenced markdown files (five rules files, cli.md, customization.md) are missing from the bundle, so every pointer to detailed content leads nowhere.

Suggestions

Add the missing bundle files — rules/styling.md, rules/forms.md, rules/composition.md, rules/base-vs-radix.md, rules/icons.md, cli.md, and customization.md — or inline their essential content; every detailed-content link in the body is currently broken.

Drop the 'Detailed References' section or fold it into the section-level links, since it duplicates paths already given in the Critical Rules headers and the Key Fields section.

Trim Key Patterns entries that restate Critical Rules verbatim (gap-* vs space-y-*, size-* vs w-* h-*) and keep only the patterns not already encoded as bullets.

DimensionReasoningScore

Conciseness

The body is dense with rule content and does not explain concepts Claude already knows, but several rules appear twice — Critical Rules bullets are re-demonstrated in Key Patterns (gap vs space-y, size vs w/h) and the same file links are restated in Detailed References. This fits 'efficient with minor instances that could be trimmed' rather than the lean-every-token-earns-its-place anchor of 5.

4 / 5

Actionability

Fully executable throughout: exact commands (`npx shadcn@latest add button --dry-run`, `docs button dialog select`), copy-paste TSX patterns for the common cases, and a component-selection table. This matches the top anchor for copy-paste-ready guidance covering common cases.

5 / 5

Workflow Clarity

The 8-step workflow is clearly sequenced with explicit validation checkpoints and feedback loops: dry-run/`--diff` before overwriting, "always read the added files and verify they are correct", import-fix recovery for third-party registries, and confirm-first rules for `--overwrite` and preset switching. Destructive/batch operations are present but consistently guarded, so the cap of 3 does not apply.

5 / 5

Progressive Disclosure

The in-file structure is well designed (one-level-deep, clearly signaled links to rules/*.md, cli.md, customization.md), but the bundle contains none of these files — only assets/. Every one of the seven referenced paths is broken, so the disclosure structure fails at runtime; per the guideline to score against the actual bundle structure, this falls to the 'structure present but not usable' level, below anchor 3 where references exist but are merely under-signaled.

2 / 5

Total

16

/

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 strong description: concrete capability list in third person, explicit and multi-trigger 'when' clause including a file-marker heuristic (components.json), and clear distinctiveness. The only gap is a few natural trigger phrasings around the most common actions (adding/updating components).

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "adding, searching, fixing, debugging, styling, and composing UI" plus "Provides project context, component docs, and usage examples" — giving comprehensive coverage of the skill's capabilities in third person. Nothing here is vague or padded, so it matches the top anchor rather than the 'several actions with minor gaps' anchor below.

5 / 5

Completeness

Explicitly answers both questions: 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..."). This matches the anchor requiring clear 'what' AND concrete trigger phrases for 'when'.

5 / 5

Trigger Term Quality

Good keyword coverage: "shadcn/ui", "component registries", "presets", "--preset codes", "components.json file", "shadcn init", "create an app with --preset". A few natural user phrasings are missing (e.g. "shadcn add", "add/update a component", "registry item"), so it sits just below the comprehensive-synonyms anchor of 5 and clearly above anchor 3, which expects missing common variations.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers — the tool name, the components.json file marker, and preset-specific commands make it unlikely to fire for unrelated skills. The only conceivable overlap ("styling, and composing UI") is anchored to shadcn-specific trigger clauses, keeping it at the top anchor rather than the 'minor overlap risk' anchor 4.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 14 missing

Warning

Total

15

/

16

Passed

Repository

openai/plugins

Path

plugins/build-web-apps/skills/shadcn-best-practices/SKILL.md

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.