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.

1.07x

Quality

—

Does it follow best practices?

Impact

100%

1.07x

Average score across 3 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.

A highly actionable, well-structured reference with concrete commands, sequenced test scripts, and verification checkpoints. Its weaknesses are volume (exhaustive command tables for every reader) and the absence of progressive disclosure — everything lives inline in one large file.

Suggestions

Move per-screen-reader command reference tables (JAWS, TalkBack) into separate files under references/ and link to them from SKILL.md, keeping only the minimum-coverage NVDA/VoiceOver detail inline.

Externalize the full VoiceOver testing checklist and NVDA test script into references/ with one-level-deep links so the main skill stays a lean overview.

Trim or consolidate the exhaustive command listings for readers outside minimum coverage to reduce token cost without losing the core workflow guidance.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is dense with reference data, but at ~540 lines the overall volume is large and exhaustive per-reader command tables (e.g. JAWS, TalkBack beyond minimum coverage) could be tightened.	2 / 3
Actionability	It provides concrete keyboard commands, step-by-step numbered test scripts, and copy-paste-ready HTML/JS for modals, live regions, and tabs — directly executable guidance.	3 / 3
Workflow Clarity	Test scripts and checklists are clearly sequenced with explicit "Check:" verification points at each step, supplying the validation checkpoints the rubric rewards.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is a single monolithic ~540-line file with no bundle files; per-reader command references and checklists that should be separate are all inline.	2 / 3
	Total	10 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that pairs a concrete capability statement with an explicit "Use when" trigger and good natural-language keywords. Its only weakness is that it describes one main action rather than enumerating several distinct ones.

Dimension	Reasoning	Score
Specificity	"Test web applications with screen readers including VoiceOver, NVDA, and JAWS" names the domain and concrete tools, but offers essentially a single action (testing) rather than the multiple distinct actions (e.g. extract/fill/merge) that anchor a 3.	2 / 3
Completeness	It states what it does ("Test web applications with screen readers...") and gives an explicit "Use when validating screen reader compatibility, debugging accessibility issues..." trigger, answering both what and when.	3 / 3
Trigger Term Quality	Natural user phrasing is well covered: "screen reader compatibility", "accessibility issues", "assistive technology support", plus the named readers "VoiceOver, NVDA, and JAWS" — terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Screen-reader-specific triggers (VoiceOver/NVDA/JAWS, screen reader compatibility, assistive technology support) carve a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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 (546 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: abece4a

Reviewed: 4 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.