CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

73

Quality

92%

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.

A highly actionable, well-sequenced body with concrete commands, contrastive code patterns, and validation checkpoints around destructive operations. Its weaknesses are moderate redundancy between Workflow, Critical Rules, and the Quick Reference, and a progressive-disclosure structure whose referenced files are absent from the bundle, leaving all deep-dive links broken.

Suggestions

Ship the referenced bundle 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) alongside SKILL.md, or remove the links — every off-page reference is currently broken.

Deduplicate the preset/CLI guidance: Workflow step 9 and the Quick Reference repeat the same decode/apply/resolve commands; keep one canonical location and link to cli.md from the other.

Drop or compress the 'Detailed References' section — it re-lists rule links already introduced under Critical Rules, spending tokens on repeated navigation.

DimensionReasoningScore

Conciseness

The body is dense and rule-driven with no padding over concepts Claude already knows — commands, one-line rules, and tables carry real information. It falls short of 5 due to redundancy: preset commands appear in both Workflow step 9 and the Quick Reference, the CLI rules duplicate Quick Reference entries, and rule-file links are repeated verbatim in "Detailed References".

4 / 5

Actionability

Everything is executable: exact invocations ("npx shadcn@latest add button card dialog", "preset resolve --json"), copy-paste-ready TSX pattern snippets with correct/wrong contrasts, and a complete Quick Reference covering init, apply, search, docs, and view. Commands are specific down to flags ("--only theme,font", "--dry-run", "--diff"), matching the score-5 anchor fully.

5 / 5

Workflow Clarity

The 9-step workflow is clearly sequenced with explicit validation checkpoints: check installed components before add, use "--dry-run" and "--diff" to preview before updating, "always read the added files and verify they are correct... Fix all issues before moving on", and "Never use --overwrite without the user's explicit approval". The destructive/batch cap at 3 does not apply because validation and feedback loops (per-file diff → decide → apply-while-preserving-changes) are present, matching the score-5 anchor.

5 / 5

Progressive Disclosure

The authored structure is good — an overview with one-level-deep references (rules/*.md, cli.md, registry.md, customization.md), each rule file introduced with a scope summary. However, the actual bundle contains none of these referenced files (only SKILL.md and assets/*.png exist), so every off-page link is broken and the disclosure chain fails at runtime. This lands at 3: structure exists as written, but navigation is not functional and content gating on missing files cannot work; it is not 4 because broken references are more than a minor organization gap.

3 / 5

Total

17

/

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: third-person voice, multiple concrete capabilities, and an explicit trigger clause covering natural phrases, a file sentinel, and command-level triggers. Both the 'what' and 'when' questions are answered clearly and specifically with minimal conflict risk.

DimensionReasoningScore

Specificity

"Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces" lists multiple specific concrete actions with comprehensive coverage, matching the score-5 anchor exactly. It goes beyond the score-4 anchor by also stating what the skill provides ("project context, component docs, and usage examples") rather than leaving minor gaps.

5 / 5

Completeness

The description 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"). Both are concrete with explicit trigger phrases, matching the score-5 anchor; the 'Use when' guidance is present, so no cap applies.

5 / 5

Trigger Term Quality

Natural triggers are comprehensively covered: "shadcn/ui", "component registries", "presets", "--preset codes", the concrete file sentinel "components.json", and user-voice phrases like "shadcn init", "create an app with --preset", "switch to --preset". This matches the score-5 anchor's coverage of natural terms plus synonyms and file markers; nothing common is missing.

5 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche (shadcn/ui ecosystem) with distinct triggers including the unambiguous "components.json" file marker, minimizing overlap with generic UI or styling skills. This matches the score-5 anchor's "clear niche with distinct triggers; minimal conflict risk"; it is well beyond the score-4 anchor, which still admits overlap with closely related skills.

5 / 5

Total

20

/

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: 17 missing

Warning

Total

14

/

16

Passed

Repository
1weiho/open-slide
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.