CtrlK
BlogDocsLog inGet started
Tessl Logo

web-design-reviewer

This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then performs fixes at the source code level.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is web-design-reviewer in github/awesome-copilot

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The skill has a well-sequenced workflow with explicit validation and a feedback loop, and it correctly offloads framework fixes to a reference file. It is weakened by inline checklist tables that duplicate an unlinked reference and by padding (diagrams and capability tables) that inflate token cost.

Suggestions

Reference references/visual-checklist.md from the Step 2 inspection section and move the inline 'Inspection Items' tables there instead of duplicating them in the body.

Trim the decorative mermaid diagrams and the 'Required Capabilities'/'Other Compatible Browser Automation Tools' tables, or move them to a reference, to reduce token overhead.

Add one concrete executable check in the body (e.g., a Playwright snippet to capture the four viewports or a console snippet to detect overflow) so the core workflow is actionable rather than a checklist of issues to look for.

DimensionReasoningScore

Conciseness

The body assumes Claude's intelligence (no over-explanation of what a website is) but is padded with decorative mermaid diagrams and organizational tables (Scope of Application, Required Capabilities, Other Compatible Browser Automation Tools) that don't add action value, so it could be tightened.

2 / 3

Actionability

Some concrete specifics exist (viewport widths 375/768/1280/1920, MCP config JSON, Playwright tool names, file-pattern globs), but the core inspection guidance is presented as abstract 'issues to look for' tables rather than executable checks or code in the body itself.

2 / 3

Workflow Clarity

A clear four-step sequence (Information Gathering → Visual Inspection → Issue Fixing → Re-verification) with an explicit feedback loop back to Step 2, before/after screenshot comparison, regression testing, and an iteration limit that escalates to the user after 3 attempts.

3 / 3

Progressive Disclosure

Only one of two reference files is signaled from the body (references/framework-fixes.md); the existing visual-checklist.md is never linked, and inline inspection-item tables duplicate content that should be externalized to it.

2 / 3

Total

9

/

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 strong: it states concrete capabilities, lists natural trigger phrases, and explicitly covers both what the skill does and when to use it. Voice is appropriately third-person about the skill, so no voice penalty applies.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'visual inspection of websites', 'Detects issues with responsive design, accessibility, visual consistency, and layout breakage', and 'performs fixes at the source code level' — naming the domain and several discrete operations rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' (identify and fix design issues at the source code level) and 'when' via an explicit 'Triggers on requests like…' clause, matching the level-3 anchor.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would actually say — 'review website design', 'check the UI', 'fix the layout', 'find design problems' — giving good coverage of common request variants.

3 / 3

Distinctiveness Conflict Risk

The visual-inspection-of-running-websites plus source-level-fix framing is a clear niche with distinct triggers ('review website design', 'check the UI') unlikely to collide with unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Galaxy-Dawn/claude-scholar
Reviewed

Table of Contents

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.