Audit, document, or extend your design system. Use when checking for naming inconsistencies or hardcoded values across components, writing documentation for a component's variants, states, and accessibility notes, or designing a new pattern that fits the existing system.
49
53%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./design/skills/design-system/SKILL.mdQuality
Discovery
85%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 a strong description that clearly defines what the skill does and when to use it, with an explicit 'Use when...' clause covering multiple trigger scenarios. The specificity of actions (auditing naming inconsistencies, documenting variants/states/accessibility, designing new patterns) is excellent. The main weakness is that trigger term coverage could be broader to capture more natural user phrasings related to design systems.
Suggestions
Add additional natural trigger terms users might say, such as 'tokens', 'theme', 'style guide', 'component library', or 'UI kit' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'audit', 'document', 'extend' a design system, plus elaborates with checking naming inconsistencies, hardcoded values, writing documentation for variants/states/accessibility notes, and designing new patterns. | 3 / 3 |
Completeness | Clearly answers both 'what' (audit, document, or extend your design system) and 'when' with an explicit 'Use when...' clause covering three distinct trigger scenarios: checking inconsistencies, writing component documentation, and designing new patterns. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'design system', 'naming inconsistencies', 'hardcoded values', 'components', 'variants', 'states', 'accessibility', but misses common user phrasings like 'tokens', 'theme', 'style guide', 'UI library', or 'component library' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on design systems with specific sub-tasks like naming inconsistency audits, component documentation with variants/states/accessibility, and pattern design creates a clear niche that is unlikely to conflict with general coding, documentation, or UI development skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides well-structured output templates for three design system tasks but is significantly weakened by verbosity (explaining concepts Claude already knows), lack of actionable process steps (how to actually perform an audit vs. just what the output looks like), and missing workflow sequences with validation checkpoints. It reads more like a documentation template collection than an actionable skill.
Suggestions
Remove the 'Components of a Design System' section entirely — Claude already knows what design tokens, components, and patterns are.
Add concrete workflow steps for each mode: e.g., for 'audit', specify which files to scan, what patterns to grep for hardcoded values, and how to validate findings before reporting.
Move the three large output templates to separate reference files (e.g., AUDIT_TEMPLATE.md, DOCUMENT_TEMPLATE.md, EXTEND_TEMPLATE.md) and keep only brief summaries in the main skill.
Add validation checkpoints to the audit workflow, such as confirming file scope with the user before scanning and reviewing findings before generating the final report.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~150+ lines, with large sections explaining what design tokens, components, and patterns are — concepts Claude already knows well. The 'Components of a Design System' section is pure background knowledge that wastes tokens. The three full output templates are lengthy and could be significantly condensed. | 1 / 3 |
Actionability | The output templates provide concrete structure (markdown tables, specific fields), which gives Claude a clear format to follow. However, there are no executable code examples, no concrete commands for actually performing an audit (e.g., grep patterns for hardcoded values, AST parsing), and the guidance remains at the template/description level rather than providing specific steps for how to find issues. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow for any of the three modes (audit, document, extend). The skill shows usage commands and output templates but never describes the actual process — what files to examine, in what order, how to validate findings, or what to do when issues are found. For an audit involving potentially destructive recommendations, there are no validation checkpoints. | 1 / 3 |
Progressive Disclosure | The content is organized into clear sections (audit, document, extend) with a reference to CONNECTORS.md, which is good. However, the three massive output templates are all inline when they could be split into separate reference files, and the 'Components of a Design System' educational section bloats the main file unnecessarily. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
3bf5929
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.