screen-reader-testing

Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.

1.03x

Quality

—

Does it follow best practices?

Impact

98%

1.03x

Average score across 6 eval scenarios

Securityby

Passed

No known issues

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 body is highly actionable and well-sequenced but voluminous and monolithic, with no progressive disclosure into reference files. Tightening generic sections and splitting per-reader detail would lift the weaker dimensions.

Suggestions

Split per-screen-reader command references and test scripts into separate reference files (e.g. voiceover.md, nvda.md) and keep SKILL.md as an overview with one-level-deep links to improve progressive_disclosure.

Trim the 'Best Practices' Do's/Don'ts and the 'When to Use' list, which restate knowledge Claude already has and duplicate the description, to improve conciseness.

Move the long Common Test Scenarios code blocks into a referenced examples file so the main body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material (exact commands, checklists) Claude would not reliably recall, but the ~530-line body and generic Best Practices section ("Use semantic HTML first - ARIA is supplemental") explain concepts Claude already knows and could be tightened.	2 / 3
Actionability	Provides executable command tables, copy-paste HTML/JS for modals, live regions, tabs, and a debugging function — fully concrete and actionable.	3 / 3
Workflow Clarity	The NVDA test script and VoiceOver checklist give clearly sequenced steps with explicit "Check:" checkpoints; testing is non-destructive so the missing-feedback-loop cap does not apply.	3 / 3
Progressive Disclosure	The skill is a single ~530-line monolithic file with per-screen-reader detail and test scripts inline and no bundle references; content that should be separate is inline, matching the 'structure present but content should be split' anchor rather than the <50-line simple-skill exception.	2 / 3
	Total	10 / 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 concise, third-person, and clearly states both capability and trigger conditions with concrete named tools. It is an exemplary description.

Dimension	Reasoning	Score
Specificity	"Test web applications with screen readers including VoiceOver, NVDA, and JAWS" names a concrete action and lists multiple specific tools, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what ("Test web applications with screen readers...") and an explicit "Use when..." trigger clause, satisfying both halves.	3 / 3
Trigger Term Quality	"screen reader compatibility", "accessibility issues", "assistive technology support", plus named products give good coverage of natural terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The screen-reader-testing niche with named tools and explicit triggers is clearly distinct from other skills and unlikely to trigger for the wrong one.	3 / 3
	Total	12 / 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
skill_md_line_count	SKILL.md is long (539 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wshobson/agents
Commit: 5cc2549

Reviewed: 3 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.