CtrlK
BlogDocsLog inGet started
Tessl Logo

screen-reader-testing

Practical guide to testing web applications with screen readers for comprehensive accessibility validation.

43

Quality

44%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/screen-reader-testing/SKILL.md

The canonical home for this skill is screen-reader-testing in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

40%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.

The body is appropriately lean but offers almost no actionable, screen-reader-specific guidance and relies entirely on a referenced playbook that does not exist in the bundle. Workflow sequencing is generic and lacks validation checkpoints.

Suggestions

Provide concrete, executable guidance inline — e.g., named screen readers (NVDA, VoiceOver, JAWS), keyboard-only navigation steps, and how to capture the announcement/ARIA output.

Add a real validation checkpoint workflow (e.g., navigate by region/heading, verify focus order, confirm dynamic announcements) instead of generic "apply best practices" steps.

Create the referenced `resources/implementation-playbook.md` (or move it under references/) so the deferred detailed patterns actually resolve, or remove the dangling reference and inline the essential content.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence without explaining what screen readers are. The only minor trim is the opening line restating the description verbatim. It is efficient with a minor redundant instance, fitting the level-4 anchor rather than the fully lean level-5 anchor.

4 / 5

Actionability

The Instructions are generic boilerplate ("Clarify goals", "Apply relevant best practices", "Provide actionable steps") with no concrete commands, named tools, or executable steps — and the only concrete pointer is to an external playbook. This matches the anchor for minimal concrete guidance missing specific steps to execute.

2 / 5

Workflow Clarity

The Instructions give a rough generic sequence (clarify → apply → verify) with no screen-reader-specific steps and no validation checkpoints for a testing workflow. It fits the level-2 anchor of a rough sequence with poorly defined steps and absent validation, not the level-3 anchor which requires an actual concrete sequence.

2 / 5

Progressive Disclosure

The body defers all detail to `resources/implementation-playbook.md`, but no such file exists — neither the standard bundle directories (references/, scripts/, assets/) nor a resources/ directory is present — so the one signaled reference is dangling and navigation fails. This fits the level-2 anchor of minimal structure with a problematic reference rather than the level-3 anchor where references are present and usable.

2 / 5

Total

10

/

20

Passed

Description

48%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.

The description clearly names its domain but is vague on concrete actions and lacks an explicit trigger clause, capping completeness. It is reasonably distinct from other skills but would benefit from concrete actions and natural trigger terms.

Suggestions

Add concrete actions (e.g., verify ARIA roles, capture announcement order, check keyboard navigation) instead of the generic "testing" and "validation".

Append an explicit "Use when..." clause listing natural triggers (e.g., screen reader testing, NVDA/VoiceOver/JAWS, ARIA announcements, WCAG conformance).

Include common tool and standard names (NVDA, VoiceOver, JAWS, ARIA, WCAG) as natural keywords users would actually say.

DimensionReasoningScore

Specificity

It names the domain ("testing web applications with screen readers") but the only actions are the generic verbs "testing" and "validation" — no concrete actions like checking ARIA roles, keyboard navigation, or announcement capture. This matches the anchor that names the domain with minimal/generic actions rather than the level-3 anchor requiring 1-2 concrete actions.

2 / 5

Completeness

It clearly states what the skill does (screen reader testing for accessibility validation) but provides no "Use when..." trigger clause, which per the judging guidelines caps completeness at 3. It is not a 4 because the when is entirely absent rather than weakly present.

3 / 5

Trigger Term Quality

It includes relevant natural terms ("screen readers", "web applications", "accessibility") but omits common synonyms and tool names a user would actually say ("NVDA", "VoiceOver", "JAWS", "ARIA", "WCAG"). This fits the anchor for some relevant keywords missing common variations, not the level-4 anchor with broad natural coverage.

3 / 5

Distinctiveness Conflict Risk

The screen-reader-testing niche is mostly distinct with only minor overlap risk against a broader accessibility skill. It is not a 5 because "comprehensive accessibility validation" is broad enough to invite some overlap with general accessibility skills.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.