x-design

Use when the user wants to apply a visual design system to a project, references a specific brand's style (Linear-like, Stripe-like, Claude-like), asks for a DESIGN.md, or describes aesthetic intent (warm editorial, dark minimal, stark futuristic) for AI UI generation

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

A highly actionable, well-sequenced router skill with strong progressive disclosure and concrete commands. Its main weakness is token efficiency — several steps carry over-explanation and repeated hedges that could be tightened without losing clarity.

Suggestions

Collapse the repeated 'ask once / skip silently / never push twice' hedges across steps 6-8 into a single shared convention stated once, since Claude retains it.

Trim parenthetical upstream-internals notes (e.g. the agentmemory memory_save field-drop aside citing a source path) — they document an external API's behavior rather than instructing Claude.

Verify the 'gotchas.md' and '../x-shared/*' references resolve in the shipped bundle, or move that content inline; dangling references slightly undercut the otherwise clean one-level-deep structure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable but contains tightening opportunities: repeated 'ask once / skip silently' caveats, parenthetical upstream-internals notes (e.g. agentmemory API behavior verified at a source path), and verbose step prose that over-explains conventions Claude can infer.	2 / 3
Actionability	Provides fully executable curl commands, exact URL templates with {commit}/{slug} substitution, named MCP tools, and copy-paste-ready CLAUDE.md lines and detection checks.	3 / 3
Workflow Clarity	An explicit 8-step sequence with validation checkpoints (confirm project root, verify slug against catalog, preview before fetch, warn before overwrite, detect-before-handoff) plus a Common Mistakes table giving feedback loops for error recovery.	3 / 3
Progressive Disclosure	SKILL.md is an overview pointing one level deep to clearly signaled references (catalog.md, shadcn-handoff.md, ai-slop-patterns.md, gotchas.md) that exist as real bundle files, keeping the main file focused on routing.	3 / 3
	Total	11 / 12 Passed

Description

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.

The description is specific, trigger-rich, and clearly distinguishes the skill's niche while answering both 'what' and 'when' explicitly. It is concise yet comprehensive without fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'apply a visual design system', 'references a specific brand's style', 'asks for a DESIGN.md', 'describes aesthetic intent' — matching the top anchor.	3 / 3
Completeness	Explicitly states both what it does (apply a visual design system / install a DESIGN.md) and when to use it via a clear 'Use when...' clause with enumerated triggers.	3 / 3
Trigger Term Quality	Includes natural phrasings users would say ('Linear-like, Stripe-like, Claude-like', 'warm editorial, dark minimal, stark futuristic', 'DESIGN.md') with good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (routing to a specific design-system catalog) with brand-name and aesthetic-intent triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: quangtran88/x-skills
Commit: 6381b15

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.