ui-testing

Visual testing - catch invisible buttons, broken layouts, contrast

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/ui-testing/SKILL.md

Quality

Content

77%

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

The skill body is highly actionable with concrete fixes and a clear pre-flight verification checklist, but it is presented as one monolithic file referencing bundle files that do not exist, limiting its progressive-disclosure quality.

Suggestions

Move the top-of-file references to ui-web.md / ui-mobile.md either by creating those bundles or removing the dangling references.

Split the large Tailwind safe-combinations table and the optional Automated Checks section into reference files, leaving SKILL.md as a lean overview with one-level-deep links.

Trim the DevTools contrast-check walkthrough and basic contrast-ratio explanations, which restate knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean checklists and PROBLEM/FIX code, but the Tailwind safe-combinations table and DevTools walkthrough add material Claude largely already knows, so it could be tightened further.	2 / 3
Actionability	It provides concrete, copy-paste-ready fixes with specific Tailwind classes, exact pixel targets (44px), and a runnable Playwright/axe test, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 'Before Shipping ANY UI' pre-flight checklist is a clear, sequenced verification gate with grouped checkboxes acting as validation checkpoints, which suits this checklist-based skill.	3 / 3
Progressive Disclosure	It is a single monolithic file whose top-of-file references ('ui-web.md or ui-mobile.md') have no matching bundle files, and inline sections like the Tailwind table and automated checks could be split out for cleaner one-level-deep navigation.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 occupies a clear niche, but it is terse and lacks an explicit 'Use when...' trigger within the description field itself, since that guidance is split into a separate when-to-use field.

Suggestions

Fold a 'Use when...' trigger clause into the description itself (e.g., 'Use when writing visual or accessibility tests for UI components') rather than relying on the separate when-to-use field.

Broaden trigger terms to include natural phrasings users say, such as 'accessibility', 'a11y', 'dark mode', and 'focus states'.

Tighten the action list slightly so the concrete catches read as capabilities rather than a dash-separated fragment.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Visual testing') and three concrete failure types it catches ('invisible buttons, broken layouts, contrast'), matching the anchor that lists multiple specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does, but the 'when to use' guidance lives in a separate frontmatter field rather than the description itself, so the 'Use when...' trigger is missing from the evaluated text and caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'invisible buttons', 'broken layouts', and 'contrast' are relevant and natural, but coverage is terse and misses common variations users would say such as 'accessibility', 'a11y', or 'dark mode'.	2 / 3
Distinctiveness Conflict Risk	The focus on invisible buttons, broken layouts, and contrast carves out a clear visual/accessibility-testing niche unlikely to conflict with other skills.	3 / 3
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alinaqi/claude-bootstrap
Path: skills/ui-testing/SKILL.md
Commit: bb6195f

Reviewed: 6 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.