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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

A well-engineered, highly actionable routing skill with a clear sequenced workflow and concrete commands. Its weak spots are redundancy between the workflow and the Common Mistakes section, and a couple of dangling cross-file references.

Suggestions

Provide gotchas.md (or drop the "See gotchas.md" pointer) so the body does not reference a file absent from the bundle.

Confirm the ../x-shared/*.md files resolve in the deployed plugin layout, or inline the minimal content so the skill is self-contained.

Collapse the duplicated ui-ux-pro-max install pointer into a single canonical mention and have other steps back-reference it to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of concept-explaining fluff, but the Common Mistakes table largely restates workflow cautions and the ui-ux-pro-max install pointer recurs across steps 6, Dependencies, Related Skills, and Common Mistakes, so it could be tightened rather than reaching a lean 3.	2 / 3
Actionability	Fully executable guidance: a complete curl -fsSL command with URL template, exact MCP tool names (get_project_registries, search_items_in_registries), exact basic-memory calls, and exact CLAUDE.md append lines that are copy-paste ready.	3 / 3
Workflow Clarity	The 8-step workflow is clearly sequenced with explicit validation checkpoints (confirm project root, preview+confirm before fetch, curl -f fail-loud on 404, warn before overwrite, detect shadcn before offering), checklists, and error-recovery paths.	3 / 3
Progressive Disclosure	Present references (catalog.md, ai-slop-patterns.md, shadcn-handoff.md) are well-signaled and one level deep, but the body points to gotchas.md which is missing from the bundle, and ../x-shared/*.md paths are absent, so navigation is not fully clean.	2 / 3
	Total	10 / 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, trigger-rich description that clearly signals when to use this skill and carves out a distinct niche. Its only weak spot is that it leans on triggers more than on a concrete list of the actions it performs.

Suggestions

Lead with one concise capability clause naming the concrete actions (e.g., "Resolves design intent, fetches a curated DESIGN.md from a GitHub catalog, and installs it into the project") before the "Use when" triggers to lift specificity.

Dimension	Reasoning	Score
Specificity	It names the domain and primary action ("apply a visual design system to a project") but is trigger-heavy rather than enumerating multiple concrete actions like resolve/fetch/install/handoff, so it does not reach the multi-action anchor of 3.	2 / 3
Completeness	An explicit "Use when..." clause satisfies the trigger-cap rule and the action (apply a visual design system) states the what, so it answers both what and when with explicit triggers.	3 / 3
Trigger Term Quality	Strong natural-term coverage users would actually say: "Linear-like, Stripe-like, Claude-like", "DESIGN.md", and "warm editorial / dark minimal / stark futuristic" for AI UI generation.	3 / 3
Distinctiveness Conflict Risk	A narrow DESIGN.md / brand-style router niche with brand-specific triggers is clearly distinguishable and unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 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
Path: skills/x-design/SKILL.md
Commit: c765280

Reviewed: 13 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.