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".
98
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope around shadcn/ui component management, lists concrete actions, and provides explicit trigger conditions. It uses third person voice consistently and includes both natural language triggers and CLI-specific terms that users would actually type. The description is comprehensive without being unnecessarily verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: adding, searching, fixing, debugging, styling, and composing UI components. Also mentions providing project context, component docs, and usage examples. | 3 / 3 |
Completeness | Clearly answers both 'what' (manages shadcn components — adding, searching, fixing, debugging, styling, composing UI; provides project context, docs, examples) and 'when' (explicitly states 'Applies when working with shadcn/ui, component registries, presets...' and 'Also triggers for...' with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'shadcn/ui', 'component registries', 'presets', '--preset codes', 'components.json', 'shadcn init', 'create an app with --preset', 'switch to --preset'. These cover both natural language and CLI-specific terms users would actually use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around shadcn/ui specifically. The mention of 'components.json', 'shadcn init', '--preset', and 'component registries' creates a very specific domain that is unlikely to conflict with generic UI or component skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%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 file that maximizes information density while maintaining clarity. It provides concrete, executable guidance for every aspect of shadcn/ui usage—from CLI commands to component composition patterns to preset management—with clear workflows, validation checkpoints, and well-organized progressive disclosure to detailed rule files. The correct/incorrect code pairs, component selection table, and quick reference section make it immediately actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is remarkably lean for its breadth. It assumes Claude's competence throughout—no explanations of what components are, how CLIs work, or basic concepts. Every section earns its place: rules are terse bullet points with linked details, the component selection table is a dense lookup, and code examples are minimal but illustrative. | 3 / 3 |
Actionability | Fully actionable throughout: executable CLI commands with exact flags, copy-paste-ready code patterns showing correct vs incorrect usage, a concrete workflow with numbered steps, and a comprehensive quick reference section. The component selection table maps needs directly to specific components. | 3 / 3 |
Workflow Clarity | The main workflow is clearly sequenced (steps 1-9) with explicit validation checkpoints: checking installed components before adding, running --dry-run and --diff before updating, reviewing added components after installation, and asking users before preset switches. The updating components section has a dedicated feedback loop (diff → analyze → decide → confirm). Destructive operations (--overwrite, preset switching) require explicit user approval. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: the SKILL.md serves as a clear overview with concise rules, then links to six detailed reference files (forms.md, composition.md, icons.md, styling.md, base-vs-radix.md, cli.md, customization.md) all one level deep. Each critical rule bullet links to its corresponding detail file. The 'Detailed References' section at the bottom provides a clean navigation index. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- shadcn-ui/ui
- Commit
7865621
- 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.