CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

video-captions

Use when applies to all `<video>` elements and third-party video embeds (YouTube, Vimeo) where the page owner controls the content. Prerecorded videos require `.vtt` caption files via `<track>`. For videos embedded via `<iframe>`, check that the video platform captions are enabled. Audio-only content requires transcripts instead (SC 1.2.1). Video-only content (no audio) requires a text alternative or audio description instead (SC 1.2.3).

Quality

79%

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/video-captions/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 a well-organized check/fix/explain overview with concrete, actionable caption guidance and a clean pointer to references/rule.md for depth. Its weaknesses are the motivational statistics and duplicated captions-vs-subtitles explanation that could be trimmed or moved to the reference, plus a generic Code Review section.

Suggestions

Trim the intro paragraph's hearing-loss statistics and legal-compliance framing (or move them to references/rule.md's 'Why It Matters') — the body's job is check/fix guidance, and Claude already knows why captions matter.

Cut the duplicated captions-vs-subtitles explanation: keep the one-line Quick Reference bullet and drop the restated distinction in 'Explain', pointing to the reference for the full comparison.

Replace the generic 'Code Review' boilerplate with video-caption-specific review cues, e.g., how to inspect the `<video>` element's track list in the browser accessibility tree and how to verify the 'default' attribute behavior.

DimensionReasoningScore

Conciseness

The intro paragraph ('Approximately 15% of adults have some degree of hearing loss... legal compliance failure under the ADA, EN 301 549') and the 'Explain' section restate the captions-vs-subtitles distinction already given in Quick Reference ('Subtitles and captions are different: captions include non-speech audio; subtitles translate dialogue only'), duplicating material Claude knows and that also appears in references/rule.md. Mostly efficient, but noticeably tighten-able.

3 / 5

Actionability

Check and Fix give concrete, near-executable guidance ('check for a `<track>` child element with kind='captions' and a valid src pointing to a .vtt file'; the copy-paste-ready `<track kind='captions' srclang='en' label='English' src='captions-en.vtt' default>` snippet), but the 'Code Review' section is generic boilerplate not specific to video captions. Not 5 because the WebVTT file format and full markup examples live only in the reference, and not 3 because the inline track snippet and specific check criteria go beyond pseudocode.

4 / 5

Workflow Clarity

A clear Check → Fix → Explain sequence with numbered fix steps and an explicit validation checkpoint ('check that the .vtt file exists and is valid (not empty, not just music notes)' and the 'default' attribute check). Not 5 because there is no fix-then-revalidate feedback loop, and this is not a destructive/batch skill so the cap-at-3 rule does not apply.

4 / 5

Progressive Disclosure

A well-sectioned ~35-line overview (Quick Reference, Check, Fix, Explain, Code Review) that defers full code examples, WebVTT format, exceptions, and verification detail to a single clearly-signaled one-level-deep pointer ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md'), which is verified to exist. Content is appropriately split and navigation is easy.

5 / 5

Total

16

/

20

Passed

Description

78%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 is concrete, technically specific, and well-bounded, with strong natural trigger terms and explicit deflection of adjacent media types to other rules. Its main weakness is the garbled 'Use when applies to all...' opening and a requirement-based framing that never explicitly states the skill's action.

DimensionReasoningScore

Specificity

Lists several concrete technical specifics — 'Prerecorded videos require .vtt caption files via <track>', 'check that the video platform captions are enabled' for '<iframe>' embeds, 'Audio-only content requires transcripts instead (SC 1.2.1)', 'Video-only content... requires a text alternative or audio description instead (SC 1.2.3)'. Not 5 because it frames requirements rather than the skill's actions, leaving minor coverage gaps in what the skill actually does.

4 / 5

Completeness

Both parts are present: the 'when' is explicit ('Use when applies to all `<video>` elements and third-party video embeds (YouTube, Vimeo) where the page owner controls the content') and the 'what' is conveyed through the concrete requirement/check statements. Not 5 because the ungrammatical opening 'Use when applies to all...' weakens the trigger clause, and the skill's action (check/fix captions) is stated via requirement framing rather than an explicit capability verb.

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'video', 'captions', 'YouTube', 'Vimeo', 'transcripts', '.vtt', 'iframe' are terms users would actually say. Not 5 because common variations like 'subtitles', 'WebVTT', and 'video embeds' as a bare phrase are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche — video caption compliance — with distinct technical triggers (`<video>`, `<track>`, `.vtt`, YouTube/Vimeo embeds). It also explicitly redirects adjacent cases ('Audio-only content requires transcripts instead', 'Video-only content... requires a text alternative or audio description instead'), minimizing overlap with sibling media-accessibility skills.

5 / 5

Total

17

/

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/video-captions/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.