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

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./design/skills/design-system/SKILL.md

Quality

Content

51%Weight 40%Scale 1-5

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

The skill is well-organized and presents useful output templates, but it functions more as a documentation scaffold than executable guidance, with weak workflow sequencing and no validation steps for the batch audit operation. Moving the long templates into bundled reference files would improve both conciseness and progressive disclosure.

Suggestions

Add an explicit, sequenced audit procedure (e.g., 1. inventory components, 2. scan for hardcoded tokens, 3. check naming, 4. score completeness, 5. validate against token registry) with a validation checkpoint before producing the report.

Move the three full output templates into separate bundled reference files (e.g., references/audit-template.md) and link to them from SKILL.md to reduce token load and improve progressive disclosure.

Provide concrete executable guidance for detecting hardcoded values (e.g., a grep/AST scan command or tool call) rather than leaving the audit method implicit.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with organized sections and templates rather than padded prose, though the three full output templates are lengthy and could be referenced from a bundled file to trim tokens.	4 / 5
Actionability	It provides structured output templates with concrete fields and tables, but these are fill-in-the-blank scaffolding rather than executable code or commands, and the actual audit steps (how to find hardcoded values) are left implicit.	3 / 5
Workflow Clarity	The three modes (audit/document/extend) are named but not sequenced into steps, and the audit workflow — a batch operation over components — lacks validation checkpoints or an ordered procedure, leaving significant gaps.	2 / 5
Progressive Disclosure	Content is well sectioned, but no bundle files exist and the long output templates are fully inlined in SKILL.md; content that could live in separate reference files is not split out, so structure is only moderate.	3 / 5
	Total	12 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 strong and specific: it clearly states both what the skill does and when to use it, with natural trigger phrases. Minor gaps in synonyms and slight overlap risk keep it just below perfect on a couple of dimensions.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Audit, document, or extend your design system", "checking for naming inconsistencies or hardcoded values across components", "writing documentation for a component's variants, states, and accessibility notes", "designing a new pattern"), with only minor coverage gaps such as token migration.	4 / 5
Completeness	Explicitly answers both "what" (audit/document/extend a design system) and "when" via a clear "Use when..." clause listing concrete trigger scenarios, matching the anchor that answers both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like "naming inconsistencies", "hardcoded values", "component's variants, states, and accessibility notes", and "designing a new pattern" match what users would say, though a few common synonyms (e.g., "design tokens", "style guide") are missing.	4 / 5
Distinctiveness Conflict Risk	The design-system niche is fairly distinct with specific triggers, but it has minor overlap risk with general documentation or component-building skills.	4 / 5
	Total	17 / 20 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
Path: design/skills/design-system/SKILL.md
Commit: 6d223a7

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.