Audit UI code against the Mediatheca design system. Checks F# (Fable/Feliz) view files and CSS for violations of glassmorphism rules, typography hierarchy, theme tokens, DesignSystem.fs usage, backdrop-filter nesting, spacing/layout conventions, animation standards, and DaisyUI 5 patterns. Use when the user asks to "design check", "check design", "audit styles", "review UI code", "check glassmorphism", or any request to verify UI code follows the design system.
99
100%
Does it follow best practices?
Impact
99%
2.82xAverage score across 3 eval scenarios
Passed
No known issues
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 an excellent skill description that hits all the marks. It provides comprehensive specificity about what violations are checked, includes natural trigger terms users would actually say, explicitly states when to use it, and is highly distinctive due to the specific technology stack and design system references.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: checks F# view files and CSS for violations across 8 distinct areas including glassmorphism rules, typography hierarchy, theme tokens, DesignSystem.fs usage, backdrop-filter nesting, spacing/layout conventions, animation standards, and DaisyUI 5 patterns. | 3 / 3 |
Completeness | Clearly answers both what (audit UI code against Mediatheca design system, checking specific violation types) AND when (explicit 'Use when...' clause with multiple trigger phrases and a catch-all for design system verification requests). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'design check', 'check design', 'audit styles', 'review UI code', 'check glassmorphism', plus the general 'verify UI code follows the design system'. These are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specific to Mediatheca design system, F#/Fable/Feliz stack, and DaisyUI 5. The combination of technology stack and design system name makes conflicts with other skills extremely unlikely. | 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 a well-crafted skill that efficiently guides Claude through a design system audit. It provides concrete commands, clear workflow steps, a structured output format, and appropriate references to external rule files. The severity classification helps prioritize findings.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, assuming Claude's competence with F#/Fable, CSS, and design systems. No unnecessary explanations of what glassmorphism is or how design systems work—just actionable steps. | 3 / 3 |
Actionability | Provides concrete executable commands (git diff), specific file paths to read, exact output format with table structure, and clear examples of what violations look like with their fixes. | 3 / 3 |
Workflow Clarity | Clear 6-step sequence with explicit checkpoints: identify files → load rules → read DesignSystem → check against categories → report with structured format → offer fixes. The workflow handles the multi-step audit process well. | 3 / 3 |
Progressive Disclosure | Appropriately references external files (`references/design-rules.md`, `src/Client/DesignSystem.fs`) for detailed rules rather than inlining them. The skill itself stays focused on the workflow while pointing to where the full rule set lives. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
38245b8
Table of Contents
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.