CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/screen-reader-test-author

Builds the full manual-accessibility artifact surface: step-by-step screen-reader test scripts for NVDA (Windows), JAWS (Windows), VoiceOver (macOS / iOS), or TalkBack (Android) with per-step keystroke + expected announcement; per-archetype WCAG 2.2 checklists (references/wcag-checklist.md); per-widget keystroke matrices pairing expected NVDA and VoiceOver announcements with the WCAG SC each row verifies (references/widget-matrix.md); and a guided NVDA / VoiceOver session protocol that merges script + checklist into a signed pass/fail session report. Use when authoring an accessibility-acceptance test, checklist, or widget matrix the team will run before sign-off, when scripting a manual a11y audit, OR when walking a tester through a guided screen-reader session.

72

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

86%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 well-structured, highly actionable skill body that leverages real reference bundles and provides copy-paste templates with validation checkpoints. Trimming the Overview rationale and deduplicating the shortcut table would tighten it further.

Suggestions

Consolidate the NVDA/VoiceOver keystroke tables that appear in both Step 3 and 'Running the session' into a single source, referencing it once.

Trim the Overview's tool-coverage statistics ('axe-core, pa11y, Lighthouse catch ~30-40%') — Claude already knows automated tools miss manual a11y issues.

Clarify when to follow Steps 1-5 vs. the 'Running the session' protocol (e.g., authoring-time vs. sign-off-time) to remove the minor sequencing ambiguity between the two workflows.

DimensionReasoningScore

Conciseness

Mostly efficient and dense with concrete tables, but carries minor over-explanation (the axe-core '30-40%' framing in the Overview) and repeats the NVDA/VoiceOver shortcut table in both Step 3 and 'Running the session', which could be consolidated.

4 / 5

Actionability

Fully executable guidance: actual keystrokes (H, F, VO+Cmd+H), expected announcement strings, a YAML flow template, and copy-paste-ready markdown templates for the test plan and signed session report covering the common cases.

5 / 5

Workflow Clarity

Both the Steps 1-5 authoring flow and the 'Running the session' protocol are clearly sequenced with checkpoints ('Without a rendered URL ... stop and ask', PASS/FAIL/BLOCKED, focus-return and timing checkpoints), but the relationship between the two parallel workflows is slightly underspecified and there is no explicit validate→fix→retry loop.

4 / 5

Progressive Disclosure

Clean overview in SKILL.md with well-signaled, one-level-deep references to real bundle files (screen-reader-scripts.md, wcag-checklist.md, widget-matrix.md), each linked inline and re-listed in the References section; content is appropriately split.

5 / 5

Total

18

/

20

Passed

Description

92%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, third-person description that concretely enumerates the artifact surface and gives explicit multi-scenario trigger guidance. Minor room to broaden trigger synonyms beyond specialist phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the full artifact surface — 'step-by-step screen-reader test scripts ... with per-step keystroke + expected announcement', 'per-archetype WCAG 2.2 checklists', 'per-widget keystroke matrices', and 'a guided ... session protocol that merges script + checklist into a signed pass/fail session report' — covering the domain comprehensively.

5 / 5

Completeness

Explicitly answers both 'what' (builds scripts, checklists, matrices, session protocol/report) and 'when' via a concrete 'Use when authoring ... when scripting ... OR when walking a tester through ...' clause.

5 / 5

Trigger Term Quality

Includes natural trigger phrases a user would say ('accessibility-acceptance test', 'checklist', 'widget matrix', 'manual a11y audit', 'guided screen-reader session', 'before sign-off'), but leans on specialized jargon and misses some common synonyms a non-specialist might use.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — manual screen-reader test authoring — with distinct triggers and explicit boundaries against sibling skills (wcag-keyboard-navigation, aria-authoring-patterns), minimizing wrong-skill activation.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents

DiscoveryImplementationValidation