Name: ui-visual-validator
Rating: 46.400000000000006 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

ui-visual-validator

Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification.

Quality

49%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/ui-visual-validator/SKILL.md

The canonical home for this skill is ui-visual-validator in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

48%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 content is a well-structured but heavily padded methodology document: it lists many tools and capabilities abstractly without executable guidance, though the analysis process and checklist give a usable workflow. Its single progressive-disclosure reference is broken and the bulk belongs in separate files.

Suggestions

Trim padded sections (Behavioral Traits, Forbidden Behaviors, Example Interactions, and generic capability bullets) to roughly halve length and assume Claude's competence.

Add concrete, executable guidance for the named tools (e.g., example CLI commands, Chromatic/Percy/Applitools invocation snippets, or a contrast-ratio measurement command) instead of only naming them.

Either create the referenced 'resources/implementation-playbook.md' (and move the tool/capability detail there) or remove the broken reference; split the large capability catalogs into one-level-deep reference files with clear links.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: eight capability sections each with eight bullets, plus behavioral traits, forbidden behaviors, and example interactions, with generic self-evident lines like 'Stays current with visual testing tools and methodologies' that add no information Claude doesn't already have.	2 / 5
Actionability	Provides some concrete guidance via the Mandatory Verification Checklist and Output Requirements, but names eight tools (Chromatic, Percy, Applitools, etc.) with zero usage commands, setup, or API examples, leaving the guidance incomplete.	3 / 5
Workflow Clarity	The numbered Analysis Process (8 steps) plus the Mandatory Verification Checklist form a clear sequence with explicit checkpoints; not 5 because there are no error-recovery feedback loops.	4 / 5
Progressive Disclosure	Section structure is clear, but all capability detail is inlined in one monolithic file and the lone reference to 'resources/implementation-playbook.md' points to a path that does not exist in the bundle, matching anchor 3 rather than 4.	3 / 5
	Total	12 / 20 Passed

Description

50%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 a competent third-person summary naming the skill's specialty areas, but it lacks an explicit 'Use when' trigger clause and concrete action verbs. It reads more as a role definition than a trigger-rich, action-oriented description.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases users would say (e.g., 'Use when verifying UI changes, running visual regression tests, or checking WCAG contrast compliance').

Replace abstract specialties with concrete actions (e.g., 'Compares screenshots for visual regressions, validates design token compliance, measures color contrast ratios').

Include common trigger synonyms users actually say: 'visual regression', 'screenshot comparison', 'cross-browser visual testing', 'WCAG contrast'.

Dimension	Reasoning	Score
Specificity	Names the domain and specialty areas ('UI testing, design system compliance, and accessibility verification') but describes areas rather than concrete actions, matching anchor 3; not 4 because no specific actions are listed.	3 / 5
Completeness	Provides a clear 'what' (visual validation expert with specialties) but no 'Use when...' trigger clause; per guidelines a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms ('UI testing', 'accessibility', 'design system', 'visual validation') but misses common variations users say like 'visual regression', 'screenshot comparison', 'WCAG', or 'contrast'.	3 / 5
Distinctiveness Conflict Risk	'Visual validation' is a recognizable niche, but 'UI testing' broadly overlaps with general testing and accessibility skills, matching anchor 3 rather than the more distinct anchor 4.	3 / 5
	Total	12 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/ui-visual-validator/SKILL.md
Commit: debb2ec

Reviewed: 24 hours 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.