design-system

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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An actionable skill with strong, concrete output templates, but it is held back by restated conceptual background, an implicit rather than explicit workflow with no validation checkpoints, and a monolithic single-file structure that loads all three modes regardless of which is invoked.

Suggestions

Remove or trim the 'Components of a Design System' and 'Principles' sections, which explain concepts Claude already knows.

Add an explicit numbered process for each mode with a verification step (e.g., for audit: enumerate components → check naming → check tokens → confirm coverage → score).

Split each mode's output template into its own reference file (audit.md, document.md, extend.md) and load only the requested one, keeping SKILL.md as a concise overview.

Dimension	Reasoning	Score
Conciseness	The output templates are tight and earn their place, but the 'Components of a Design System' and 'Principles' sections restate concepts Claude already knows (what design tokens/components/patterns are, 'consistency over creativity'), which is unnecessary padding.	2 / 3
Actionability	Provides concrete, copy-paste-ready output templates with specific tables and fields (Variants, States, Props, Accessibility, Do's and Don'ts, Tokens Used) plus explicit usage commands for each mode.	3 / 3
Workflow Clarity	The three modes are named and their output structure implied via templates, but there is no explicit numbered process sequence and no validation/verification checkpoints (e.g., confirming an audit covers all components before scoring).	2 / 3
Progressive Disclosure	The file is well-sectioned, but all three mode-specific output templates (audit/document/extend) live inline in a single ~185-line file with no per-mode reference files; content that could be split and loaded on demand is not.	2 / 3
	Total	9 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit 'Use when' trigger, multiple concrete actions, and natural trigger terms, clearly occupying the design-system niche. The only weakness is the second-person 'your' phrasing, which the rubric penalizes on specificity.

Suggestions

Rewrite in third person to avoid the specificity penalty, e.g. 'Audits, documents, or extends a design system' instead of 'your design system'.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Audit, document, or extend', 'checking for naming inconsistencies or hardcoded values', 'writing documentation for a component's variants, states, and accessibility notes') which would merit a 3, but the second-person voice ('extend your design system') triggers the rubric's -1 specificity penalty.	2 / 3
Completeness	Explicitly answers both what ('Audit, document, or extend your design system') and when via an explicit 'Use when checking for naming inconsistencies... or designing a new pattern' clause.	3 / 3
Trigger Term Quality	Covers natural terms users would actually say — 'design system', 'naming inconsistencies', 'hardcoded values', 'documentation', 'variants', 'states', 'accessibility', 'pattern' — giving good coverage of likely phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (design systems) with distinct, specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: anthropics/knowledge-work-plugins
Commit: f96c57c

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.