ui-visual-validator

Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.

Quality

61%

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 ./skills/ui-visual-validator/SKILL.md

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 well-structured and offers a clear validation workflow with a useful checklist, but it is verbose and restates widely known domain knowledge while inlining catalog material that would benefit from separation into reference files. Actionability is moderate because concrete execution detail is thin.

Suggestions

Trim the Capabilities, Advanced Validation Techniques, Behavioral Traits, and Forbidden Behaviors bullet lists to only items that add non-obvious instruction, removing restatements of concepts Claude already knows.

Move the long tool and technique catalogs into a separate references/ file (e.g., VISUAL_TESTING_TOOLS.md) and link to it from SKILL.md so the body stays a lean overview.

Add concrete, executable guidance for the validation steps — e.g., specific commands or measurement procedures for pixel-diff, contrast-ratio, and responsive breakpoint checks — and make the validate-fix-retry loop explicit.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, with long enumerative capability/technique/tool lists and 'Behavioral Traits'/'Forbidden Behaviors' sections that restate domain knowledge Claude already has; multiple padded sections add tokens without new instruction.	2 / 5
Actionability	Provides some concrete guidance via the numbered Analysis Process and Mandatory Verification Checklist, but as an instruction-only skill it lacks specific executable steps, measurement procedures, or tool commands to carry out the validation.	3 / 5
Workflow Clarity	The 8-step Analysis Process is a clear sequence with checkpoint-like items (e.g., 'Reverse Validation', 'actively look for failure evidence') plus a checklist, though explicit validate-fix-retry feedback loops are only implicit rather than spelled out.	4 / 5
Progressive Disclosure	Content is sectioned with headers but no bundle files exist and bulk reference-like material (long tool and technique catalogs) is inlined in SKILL.md rather than split into one-level-deep reference files.	3 / 5
	Total	12 / 20 Passed

Description

75%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 specific and distinct, naming concrete visual-validation actions and natural trigger terms with a clear (if directive) use-when clause. It is solid but falls short of the top anchor due to non-explicit trigger phrasing and incomplete synonym/tool coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('screenshot analysis', 'visual regression testing', 'component validation', 'verify UI modifications') across multiple areas, with only minor coverage gaps; not quite the comprehensive multi-action listing of a 5.	4 / 5
Completeness	Clearly states what the skill does and provides a when via 'Use PROACTIVELY to verify UI modifications have achieved their intended goals', but the when is directive rather than a concrete 'Use when...' trigger phrase, so it is not fully explicit.	4 / 5
Trigger Term Quality	Includes natural terms users say ('UI testing', 'design system', 'accessibility', 'visual regression') but misses common synonyms and tool/file names; good coverage short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a fairly distinct visual-validation/regression niche with minimal overlap risk against general testing skills; only minor overlap with related QA skills keeps it from a 5.	4 / 5
	Total	16 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/ui-visual-validator/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.