sharaf/professional-design-system-architect
Design, build, or audit professional UI design systems across strategy, product language, foundations, tokens, components, patterns, accessibility, content, Figma/code libraries, documentation, QA, governance, adoption, measurement, theming, releases, and migration. Use when the user wants to create a design-system blueprint, review an existing design system, fix design-system drift, plan Figma/code parity, define token or component architecture, evaluate accessibility and governance maturity, or sequence design-system adoption and migration work.
100
100%
Does it follow best practices?
Impact
100%
1.75xAverage 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 thoroughly covers the design system domain with specific actions, comprehensive trigger terms, and a clear 'Use when' clause. It uses proper third-person voice and provides enough specificity to distinguish itself from general UI/UX or coding skills. The only minor concern is that the description is quite long and dense, but the breadth is justified given the scope of design system work.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists numerous specific concrete actions: 'Design, build, or audit professional UI design systems' and enumerates specific domains like strategy, tokens, components, patterns, accessibility, Figma/code libraries, documentation, QA, governance, adoption, measurement, theming, releases, and migration. | 3 / 3 |
Completeness | Clearly answers both 'what' (design, build, or audit UI design systems across many domains) and 'when' with an explicit 'Use when...' clause listing seven specific trigger scenarios like creating blueprints, reviewing existing systems, fixing drift, and planning adoption. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'design system', 'Figma', 'tokens', 'component architecture', 'accessibility', 'governance', 'design-system drift', 'Figma/code parity', 'migration'. These are terms practitioners naturally use when seeking help with design systems. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on UI design systems with very specific triggers like 'design-system blueprint', 'token architecture', 'Figma/code parity', and 'design-system drift' that are unlikely to conflict with general UI, coding, 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 skill that balances completeness with conciseness. The three-mode architecture with clear sequences, validation checkpoints, and copy-paste templates makes it immediately actionable. The progressive disclosure to optional reference files is cleanly handled, though the absence of bundle files means we can't verify those references exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It avoids explaining what design systems are or how tokens work conceptually. Every section serves a structural or instructional purpose, and the copy-paste templates pack maximum information density without redundancy. | 3 / 3 |
Actionability | The skill provides concrete, copy-paste-ready templates for token contracts, scorecard rows, audit findings, component doc areas, and first actions. The mode sequences give specific deliverables (e.g., 'four token layers', '0-4 scores', 'Stabilize, Standardize, Scale roadmap') rather than vague direction. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with explicit validation checkpoints ('scope/foundations before contracts, evidence coverage before scores, scored findings before roadmap'). Each mode has a defined sequence, and step 4 addresses uncertainty handling. The audit mode includes a clear feedback loop: evidence inventory → scores → findings → roadmap. | 3 / 3 |
Progressive Disclosure | The skill provides a complete, self-contained workflow in the main file while clearly signaling four one-level-deep reference files in a well-organized table. The 'Optional References' framing explicitly states the main file is sufficient, with references for 'deeper domain detail' only. | 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