Content
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid design system reference skill with clear constraints using MUST/SHOULD/NEVER language and well-organized tables of design tokens. Its main weaknesses are the lack of executable code examples (CSS/Tailwind/component snippets) that would make it immediately actionable, and some redundancy in reference sections that could be extracted to separate files. The content is well-scoped but reads more like a design specification than an actionable skill.
Suggestions
Add at least 2-3 executable code examples (e.g., a CSS custom properties block defining the tokens, a Tailwind config snippet, or a sample styled component) to make the skill immediately actionable.
Extract the detailed token tables (Semantic Tokens, Text Styles) into a separate REFERENCE.md file and link to it, keeping only the most essential tokens inline.
Remove redundant sections like 'Border Radius Reference' and 'Typography Reference' that repeat information already present in the tables above them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with well-structured tables and clear MUST/SHOULD/NEVER constraints. However, some sections include redundant information (e.g., 'Border Radius Reference' repeats the scale already listed in the Borders section, 'Typography Reference' restates what's in the table, and 'Detected Layout Patterns' adds little value). The duplicate 'body-secondary' entry in the text styles table also suggests unrefined content. | 2 / 3 |
Actionability | The skill provides specific values (hex codes, pixel sizes, font weights) which are concrete and actionable for design implementation. However, it lacks executable code examples — no CSS snippets, no Tailwind classes, no component code. For a UI design system skill, having at least one concrete code example (e.g., a styled button or card component) would make it fully actionable rather than just a reference specification. | 2 / 3 |
Workflow Clarity | This is primarily a reference/constraint skill rather than a multi-step workflow skill. The single-purpose nature (apply these design tokens and rules when building Tldraw-style UIs) is unambiguous. The MUST/SHOULD/NEVER hierarchy provides clear priority ordering, and the 'When to Apply' section clearly scopes when to use the skill. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and tables, making it easy to scan. However, at ~150 lines with detailed token tables and reference sections, some of this content (like the full text styles table or the complete semantic tokens table) could be split into a separate reference file to keep the main skill leaner. No external references are provided. | 2 / 3 |
Total | 9 / 12 Passed |