OpenAI's UI design system. Use when building interfaces inspired by OpenAI's aesthetic - light mode, Inter font, 4px grid.
75
68%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/openai/SKILL.mdQuality
Discovery
75%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 is well-structured with a clear 'Use when' clause and a distinctive niche targeting OpenAI's design system. Its main weakness is the lack of concrete action verbs describing what the skill actually does (e.g., generate components, apply styles, create layouts) and limited trigger term coverage for how users might naturally request this skill.
Suggestions
Add specific concrete actions like 'Generates UI components, applies styling, creates layouts following OpenAI's design system'
Expand trigger terms to include natural variations like 'ChatGPT-style UI', 'OpenAI look and feel', 'clean minimal interface', or 'OpenAI-inspired design'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (UI design system) and mentions some specific elements (light mode, Inter font, 4px grid), but doesn't list concrete actions like 'create layouts', 'style components', or 'apply typography'. It describes attributes rather than actions. | 2 / 3 |
Completeness | Clearly answers both 'what' (OpenAI's UI design system) and 'when' (Use when building interfaces inspired by OpenAI's aesthetic) with an explicit 'Use when...' clause and trigger context. | 3 / 3 |
Trigger Term Quality | Includes 'OpenAI' and some design terms like 'light mode', 'Inter font', '4px grid', but misses common user terms like 'OpenAI style', 'ChatGPT UI', 'design tokens', 'components', or 'theme'. Coverage of natural variations is limited. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive - specifically targets OpenAI's design aesthetic, which is a clear niche unlikely to conflict with other design system skills (e.g., Anthropic brand, Material Design). The mention of specific attributes (Inter font, 4px grid) further narrows the scope. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive design system reference with clear constraint language (MUST/SHOULD/NEVER) and specific values. Its main weaknesses are the lack of executable code examples (CSS/Tailwind/component snippets), some apparent data extraction artifacts (0px input height, near-duplicate color entries), and a monolithic structure that could benefit from splitting detailed reference tables into separate files.
Suggestions
Add executable code examples showing how to apply the design tokens - e.g., CSS custom properties block, a Tailwind config snippet, or a sample component implementing the system
Review and fix apparent data extraction errors: '0px' input field height and near-duplicate body-secondary entries with marginally different hex values (#525252 vs #5B5B5B vs #565656) - consolidate or explain the variance
Move detailed reference tables (full text styles, spacing scale, element widths) to a separate REFERENCE.md file and link to it from the main skill
Remove low-value metadata like 'Count' column and 'Inter (used 19x)' - these appear to be raw analysis artifacts rather than actionable design guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with well-structured tables and clear MUST/SHOULD/NEVER constraints. However, there's some redundancy (e.g., multiple near-identical body-secondary entries with slightly different hex colors, the 'Count' column in text styles, and the font families section noting 'Inter (used 19x)' adds little value). The detected layout patterns section with element widths like '8px, 21px, 14px, 61px, 36px' feels like raw extraction data rather than curated guidance. | 2 / 3 |
Actionability | The skill provides specific values (hex codes, pixel sizes, font weights) which are concrete and actionable for implementation. However, there are no executable code examples - no CSS snippets, no Tailwind classes, no component code. For a UI design system skill, concrete code showing how to apply these tokens (e.g., CSS custom properties, a Tailwind config, or a component example) would significantly improve actionability. Also, '0px height for input fields' seems like a data extraction error rather than intentional guidance. | 2 / 3 |
Workflow Clarity | This is a reference/constraint skill rather than a multi-step workflow skill. The 'When to Apply' section clearly scopes usage, and the MUST/SHOULD/NEVER hierarchy provides unambiguous decision-making guidance. For a design system reference, the single-task nature (apply these constraints when building UI) is clear and well-organized. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and tables, but it's a fairly long monolithic document. Some sections (like the full text styles table with near-duplicate entries, or the detailed border radius reference) could be split into a separate reference file. There are no references to external files for deeper dives on specific topics like component patterns or accessibility guidelines. | 2 / 3 |
Total | 9 / 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.
126714e
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.