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

75%

Does it follow best practices?

Impact

98%

1.03x

Average score across 6 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/accessibility-compliance/skills/screen-reader-testing/SKILL.md

Quality

Content

63%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.

A comprehensive, actionable reference for screen-reader testing with concrete commands and code, but it is a long monolith that explains some basics Claude already knows and does not split per-reader or checklist material into separate files. Tightening prose and moving detailed per-reader references into separate files would lift the weaker dimensions.

Suggestions

Trim explanations of concepts Claude already knows (e.g., what aria-live regions do, browse vs. focus mode definitions) to lift conciseness toward the top anchor.

Split each screen reader's full command reference and testing checklist into one-level-deep reference files (e.g., references/voiceover.md, references/nvda.md) and keep SKILL.md an overview with clear pointers to improve progressive disclosure.

Add an explicit error-recovery feedback loop for failed checks in the test scripts (e.g., 'If heading structure is illogical, fix landmarks and re-run the rotor check') to push workflow clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tight tables and command lists, but at ~530 lines it explains concepts Claude already knows (live-region semantics, browse vs. focus mode descriptions) and could be tightened; it sits at 'mostly efficient with some unnecessary explanation'.	3 / 5
Actionability	Provides concrete, mostly executable guidance — specific keyboard commands, copy-paste HTML/JS for modals, tabs, and live regions, and a numbered NVDA test script — with only minor gaps such as checklist-style rather than fully runnable steps.	4 / 5
Workflow Clarity	The NVDA test script and per-reader checklists give a clear sequence with 'Check:' verification gates for each step; testing is non-destructive so the validation cap does not apply, though error-recovery feedback loops are only implicit.	4 / 5
Progressive Disclosure	Content is a single monolithic SKILL.md with no bundle files; per-reader guides and checklists that could live in separate one-level-deep references are all inlined, so structure exists but content is not appropriately split for navigation.	3 / 5
	Total	14 / 20 Passed

Description

87%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.

A strong description that concretely states what the skill does and when to use it with natural trigger phrases. Minor gaps in reader-name coverage and synonym breadth keep specificity and trigger quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete action ('Test web applications with screen readers') plus three specific readers (VoiceOver, NVDA, JAWS), but the central verb 'Test' is somewhat generic and only 3 of 5 common readers are listed, leaving minor coverage gaps.	4 / 5
Completeness	Clearly answers 'what' (test web apps with screen readers including the three named tools) and explicitly answers 'when' with concrete trigger phrases via the 'Use when validating... debugging... ensuring...' clause.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('screen reader compatibility', 'debugging accessibility issues', 'assistive technology support'); a few common synonyms like 'a11y' are missing, so it falls just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear accessibility/screen-reader niche with distinct triggers that are unlikely to fire for unrelated skills, minimizing conflict risk.	5 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (539 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wshobson/agents
Path: plugins/accessibility-compliance/skills/screen-reader-testing/SKILL.md
Commit: d6837ae

Reviewed: about 12 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.