CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

audio-descriptions

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Provide audio descriptions for video. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Quality

76%

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 ./skills/audio-descriptions/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured and lean, with details appropriately delegated to a single clearly-signaled reference file. The main weakness is actionability: it describes the fix technique in prose without an executable markup example, and the Quick Reference/Fix sections duplicate each other.

Suggestions

Add a short executable markup snippet in the Fix section, e.g. `<video src="demo.mp4"> <track kind="descriptions" src="descriptions.vtt" srclang="en"> </video>`, so the guidance is copy-paste ready.

Merge the Quick Reference bullets with the Check/Fix sections to eliminate the near-duplicate restatement of the same three remediation options.

Name a concrete verification step (e.g. 'pause the video where visual-only action occurs and confirm the description track narrates it') instead of the generic 'browser accessibility tooling' mention.

DimensionReasoningScore

Conciseness

The ~30-line body is lean with no concept over-explanation beyond one brief 'why' sentence, but the Quick Reference bullets and the Fix section restate nearly identical content (both mention the track element with kind='descriptions' and extended/inline alternatives) and could be consolidated.

4 / 5

Actionability

The Fix section names a concrete technique ('track element with kind=descriptions') but provides no executable markup example in the body, and the Check section ('Identify videos where visual content conveys information not available in the audio track') is abstract guidance without key implementation details.

3 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review structure gives a clear sequence for a simple review skill, and verification is mentioned ('note how to verify the fix with browser accessibility tooling or assistive tech'), but no concrete validation step or tool is specified, leaving a minor checkpoint gap.

4 / 5

Progressive Disclosure

The body is a concise overview with implementation details, code examples, and framework guidance correctly split into references/rule.md, which exists, is one level deep, and is clearly signaled with a description of what it contains.

5 / 5

Total

16

/

20

Passed

Description

71%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 has an explicit trigger clause and concrete review actions, giving it solid completeness and specificity. However, the action sentence is templated accessibility boilerplate that neither reflects the skill's actual content (audio description tracks for video) nor distinguishes it from sibling accessibility skills.

Suggestions

Rewrite the 'what' to state the skill's actual capabilities, e.g. 'Add audio description tracks to video elements, verify visual-only content is described, and review description track implementation' instead of the generic keyboard/focus/screen-reader inspection boilerplate.

Add natural trigger synonyms users would say, such as 'audio description track', 'video narration for blind users', or 'video accessibility', to improve trigger term coverage.

Tighten the 'when' clause to a natural phrasing like 'Use when videos contain visual-only information (actions, on-screen text, scene changes) not conveyed in the audio track.'

DimensionReasoningScore

Specificity

The description lists several concrete actions ('Check native semantics first', 'inspect keyboard behavior, focus flow, accessible names, and screen-reader output'), but these are generic accessibility-review actions rather than the skill's actual capability of adding audio description tracks to video, leaving minor gaps in coverage.

4 / 5

Completeness

Both an explicit 'Use when...' trigger clause and a concrete action statement are present, but the 'what' describes generic accessibility inspection rather than the skill's actual purpose, and the 'when' phrasing ('related to Provide audio descriptions for video') is awkward rather than fully explicit.

4 / 5

Trigger Term Quality

Good keyword coverage including natural phrases like 'audio descriptions for video', 'rendered HTML', and 'screen-reader output', though common variations such as 'audio description track', 'narration', or 'video accessibility' are missing.

4 / 5

Distinctiveness Conflict Risk

The topic qualifier 'Provide audio descriptions for video' narrows the scope, but the second sentence is generic accessibility-review boilerplate that would appear identically in sibling checklist skills (captions, focus order, alt text), creating real overlap risk with closely related skills.

3 / 5

Total

15

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/audio-descriptions/SKILL.md

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.