CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/screen-reader-test-author

Builds a screen-reader test narrative - a step-by-step manual test script for NVDA (Windows), JAWS (Windows), VoiceOver (macOS / iOS), or TalkBack (Android) - that exercises a specific user flow through a component or page and captures the expected announcement at each step. Use when authoring an accessibility-acceptance test the team will run before sign-off, OR when scripting a manual a11y audit.

75

Quality

94%

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

85%

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 with explicit PASS/validation checkpoints and a properly signaled one-level reference for the full scripts. Its only weakness is mild padding where the Overview and a duplicated verbosity note restate context Claude already knows.

Suggestions

Trim the Overview's automated-tool coverage statistics and the rationale for manual testing; assume Claude knows why manual screen-reader testing matters and lead with what the skill produces.

Remove the duplicated VoiceOver-verbosity note from SKILL.md Step 3 since the same guidance appears in the reference file, keeping it in one place.

Consider moving the four-row failure-mode table in Step 4 into the reference if the body grows, to keep SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly task-focused, but the Overview's 'automated tools catch ~30-40%... remaining 60-70%' preamble and the VoiceOver-verbosity note (repeated in the reference) explain context Claude already knows and could be tightened, matching the 'mostly efficient but some unnecessary explanation' anchor rather than the lean score-3 bar.

2 / 3

Actionability

Provides concrete keystroke tables with exact shortcuts (VO+Cmd+H, VO+Cmd+J), explicit PASS criteria, a real failure-mode table, and a copy-paste markdown checklist template, matching the 'fully executable / copy-paste ready' score-3 anchor.

3 / 3

Workflow Clarity

A clear 5-step sequence (pick SR, define flow, capture keystrokes, define PASS, wire to test plan) with explicit validation checkpoints in Step 4 (PASS criteria plus a failures table) and a debugging note for missing live-region announcements, matching the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

SKILL.md is a concise overview that offloads the full per-reader scripts to a verified one-level reference (references/screen-reader-scripts.md), clearly signaled with a markdown link in Step 3, matching the 'clear overview with well-signaled one-level-deep references' anchor.

3 / 3

Total

11

/

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 specific, trigger-rich, and complete, naming concrete actions and four screen-reader targets while giving an explicit 'Use when' clause for both authoring and audit contexts. It is highly distinct from adjacent skills and free of vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Builds a screen-reader test narrative', 'exercises a specific user flow', 'captures the expected announcement at each step') plus four named SR/platform targets, matching the 'multiple specific concrete actions' anchor rather than the partial coverage of score 2.

3 / 3

Completeness

Explicitly answers both 'what' (builds a step-by-step manual test script that exercises a flow and captures expected announcements) and 'when' via an explicit 'Use when authoring an accessibility-acceptance test... OR when scripting a manual a11y audit' trigger clause, matching the score-3 anchor rather than the implied-when of score 2.

3 / 3

Trigger Term Quality

Surfaces natural terms a user would actually say ('screen-reader test', 'NVDA', 'JAWS', 'VoiceOver', 'TalkBack', 'accessibility-acceptance test', 'a11y audit', 'sign-off') with good coverage of common variations, matching the score-3 anchor rather than the partial keyword set of score 2.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (manual screen-reader test authoring) with distinct triggers unlikely to overlap with general accessibility or automated-tool skills, matching the score-3 'clear niche with distinct triggers' anchor.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents