CtrlK
BlogDocsLog inGet started
Tessl Logo

shadcn

Manages shadcn/ui components and projects, providing context, documentation, and usage patterns for building modern design systems.

56

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/shadcn/SKILL.md

The canonical home for this skill is shadcn in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

92%Scale 1-5

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

This is an exceptionally well-crafted skill that balances breadth with conciseness. It provides highly actionable guidance through concrete CLI commands, executable code examples with correct/incorrect comparisons, and a clear multi-step workflow with validation checkpoints. The progressive disclosure is excellent, with the main file serving as a comprehensive overview while delegating detailed rules to clearly referenced sub-files.

DimensionReasoningScore

Conciseness

The skill is largely efficient and avoids explaining basic concepts Claude already knows. It's dense with actionable rules and patterns. Minor verbosity in some sections (e.g., the 'When to Use' section and some repeated emphasis on CLI runners), but overall respects token budget well for the breadth of content covered.

4 / 5

Actionability

Highly actionable throughout: concrete CLI commands with exact flags, executable TSX code examples showing correct vs incorrect patterns, a component selection table mapping needs to specific components, and a step-by-step workflow with specific commands at each stage. The Key Patterns section provides copy-paste ready code with inline correct/wrong annotations.

5 / 5

Workflow Clarity

The workflow section provides a clear 9-step sequence with explicit validation checkpoints: checking installed components before adding, using --dry-run and --diff before updating, reading and verifying added files, and requiring explicit user approval before --overwrite. The 'Updating Components' section has a dedicated feedback loop (diff → analyze → decide → apply). The preset switching workflow offers three explicit paths with confirmation steps.

5 / 5

Progressive Disclosure

Excellent progressive disclosure structure: the SKILL.md serves as a clear overview with well-organized sections, and detailed rules are appropriately delegated to one-level-deep referenced files (rules/forms.md, rules/composition.md, rules/icons.md, rules/styling.md, rules/base-vs-radix.md, cli.md, customization.md). Each reference is clearly signaled with descriptive labels. The 'Detailed References' section at the bottom provides a clean navigation index.

5 / 5

Total

19

/

20

Passed

Description

36%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.

The description identifies the specific technology (shadcn/ui) which provides some distinctiveness, but it relies on vague action verbs like 'manages' and 'providing' rather than concrete capabilities. It completely lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill over others. The trigger terms are limited and miss common synonyms and related terms users would naturally use.

Suggestions

Add an explicit 'Use when...' clause with trigger terms like 'shadcn', 'shadcn/ui', 'ui components', 'component library', 'radix primitives', 'tailwind components', or when users ask about installing or configuring UI components.

Replace vague verbs like 'manages' and 'providing context' with concrete actions such as 'installs and configures shadcn/ui components', 'generates component code with proper imports', 'applies theming and variant patterns'.

Include natural synonyms and related terms users might say, such as 'shadcn', 'cn utility', 'tailwind CSS components', 'radix UI', or specific component names like 'dialog', 'dropdown', 'data table'.

DimensionReasoningScore

Specificity

Names the domain (shadcn/ui components) but the actions are vague and generic — 'manages', 'providing context, documentation, and usage patterns' are abstract rather than concrete actions like 'installs components', 'generates configuration files', or 'creates themed variants'.

2 / 5

Completeness

Has a vague 'what' (manages shadcn/ui components, provides documentation and usage patterns) but completely lacks a 'when' clause. There is no explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when...' caps completeness at 3, and the 'what' is also weak, so a 2 is appropriate.

2 / 5

Trigger Term Quality

Includes 'shadcn/ui', 'components', 'design systems', and 'usage patterns' which are relevant keywords. However, it misses natural user phrases like 'shadcn', 'ui library', 'component library', 'tailwind components', 'radix', or specific component names that users would mention.

3 / 5

Distinctiveness Conflict Risk

The mention of 'shadcn/ui' specifically helps distinguish it from generic component or design system skills. However, 'managing components', 'design systems', and 'usage patterns' are broad enough to overlap with other UI framework or component library skills.

3 / 5

Total

10

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.