uinaf/uinaf-design-system
Apply the uinaf brand identity to anything that ships under the uinaf name — web interfaces, blog posts, changelogs, documentation, READMEs, slides, OG / social images, email, terminal banners, app or product UI starting points. Covers voice, design tokens, components, motion, and brand assets, with a Tailwind v4 path for web work. Use when producing or restyling any uinaf-branded artefact. Skip for non-uinaf work; this is opinionated brand guidance, not a generic UI kit.
98
100%
Does it follow best practices?
Impact
97%
1.67xAverage score across 5 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 clearly defines its scope, lists concrete artifact types and capabilities, provides explicit trigger guidance with both positive ('Use when...') and negative ('Skip for...') conditions, and is highly distinctive due to its brand-specific focus. The description is comprehensive yet concise, uses proper third-person voice, and would allow Claude to confidently select or reject this skill from a large pool.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and artifact types: web interfaces, blog posts, changelogs, documentation, READMEs, slides, OG/social images, email, terminal banners, app/product UI. Also specifies what it covers: voice, design tokens, components, motion, brand assets, and a Tailwind v4 path. | 3 / 3 |
Completeness | Clearly answers both 'what' (apply uinaf brand identity covering voice, design tokens, components, motion, assets) and 'when' ('Use when producing or restyling any uinaf-branded artefact. Skip for non-uinaf work'). The explicit 'Use when...' and 'Skip for...' clauses are excellent. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would mention: 'uinaf' (the brand name itself is the primary trigger), 'web interfaces', 'blog posts', 'changelogs', 'documentation', 'READMEs', 'slides', 'OG images', 'social images', 'email', 'terminal banners', 'brand', 'Tailwind v4', 'restyling'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to the 'uinaf' brand with an explicit exclusion ('Skip for non-uinaf work; this is opinionated brand guidance, not a generic UI kit'). This clear boundary makes it very unlikely to conflict with generic UI or design 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-structured brand system skill. It front-loads the universal hard rules that apply everywhere (keeping them concise enough to justify inline placement), provides a clear workflow with a verification step, and delegates all detailed guidance to one-level-deep reference files organized by task type. The content is dense with actionable specifics — exact URLs, pixel values, Unicode characters, casing scopes — while remaining lean and scannable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place — hard rules are terse and specific, the workflow is minimal, and the reference index is a clean lookup table. No concepts are over-explained; Claude is trusted to understand terms like 'pill radius', 'CDN', and 'OG image' without preamble. | 3 / 3 |
Actionability | Provides concrete CDN URLs, exact CSS import paths, specific pixel values (2px norm, 6px cap), exact Unicode characters to use, and a bundled stylesheet. Rules are binary and unambiguous (no emoji, no shadows, no icon fonts) rather than vague guidance. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced: identify surface → load references → pull assets → write copy → verify against hard rules. Step 5 is an explicit validation checkpoint, and the 'Handoffs' section provides clear next-action routing for verification, review, and updates. | 3 / 3 |
Progressive Disclosure | Exemplary progressive disclosure: the SKILL.md is a concise overview with hard rules inline (they're short enough to warrant it), while all detailed guidance is one level deep in clearly labeled reference files. The 'Read by task' index makes navigation instant and avoids nested chains. | 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.
Reviewed
Table of Contents