CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

63

Quality

75%

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 well-structured with a clear Check/Fix sequence, explicit validation checkpoints, and a clean one-level reference split to references/rule.md. It is held back by redundant conceptual explanation (motivational stats and the twice-stated captions-vs-subtitles distinction) and minor actionability gaps (no full markup or .vtt cue example).

Suggestions

Trim the opening statistics/legal paragraph and remove the duplicated captions-vs-subtitles explanation from either Quick Reference or Explain.

Add a complete minimal example: a `<video>` element containing the `<track>` child, plus a short .vtt file showing WEBVTT header and a timed cue.

Make the feedback loop explicit in Fix: after adding/creating captions, re-run the Check steps to confirm the track resolves and the file is valid.

DimensionReasoningScore

Conciseness

Mostly efficient but includes unnecessary explanation: the opening statistics ('Approximately 15% of adults have some degree of hearing loss... legal compliance failure under the ADA, EN 301 549') is motivational padding, and the captions-vs-subtitles distinction is explained twice ('Subtitles and captions are different...' in Quick Reference and again in the Explain section), repeating a concept Claude already knows. Matches anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened'). Not 2: the padding is limited and the Check/Fix sections are lean and task-focused; not 4: the duplicated conceptual explanation is a clear instance of over-explanation.

3 / 5

Actionability

Concrete, attribute-level guidance: 'Add `<track kind='captions' srclang='en' label='English' src='captions-en.vtt' default>`', 'include... descriptions of relevant sounds (e.g., `'[applause]'`, `'[upbeat music]'`)', and specific check criteria ('not empty, not just music notes'). Matches anchor 4 ('mostly executable guidance; concrete code or commands with minor gaps'). Not 5: no complete `<video>` markup example and no sample .vtt cue syntax with timestamps, so it is not fully copy-paste ready; not 3: the guidance is executable and specific, not high-level hints.

4 / 5

Workflow Clarity

Clear Check → Fix → Explain → Code Review sequence with explicit checkpoints: 'check that the `.vtt` file exists and is valid (not empty, not just music notes)' and 'note how to verify the fix with browser accessibility tooling or assistive tech'. Matches anchor 4 ('clear sequence with most checkpoints present; minor validation gaps'). Not 5: no explicit fix-then-re-check feedback loop is articulated; not 3: validation checkpoints are present and explicit, not missing or implicit.

4 / 5

Progressive Disclosure

The body is a clear overview with well-organized sections (Quick Reference, Check, Fix, Explain, Code Review) and a single, clearly signaled one-level reference: 'see `references/rule.md`', which exists as a real 94-line file with only external links (no nested .md references). Matches anchor 5 ('clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation'). Not 4: there are no organization gaps — the split between overview and detail reference is clean.

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 specific and domain-distinct with explicit what/when guidance and good natural trigger terms. Its main weaknesses are the garbled 'Use when applies to all' phrasing and a requirements-checking framing that undersells the skill's actions (check/fix/verify).

Suggestions

Fix the trigger clause grammar, e.g., 'Use when auditing or adding captions to `<video>` elements or embedded YouTube/Vimeo videos on pages you control.'

Frame the what as actions the skill performs (check, add, fix captions) rather than only stating WCAG requirements for content types.

Add common trigger synonyms such as 'subtitles', 'WebVTT', and 'track kind=captions' to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Quotes several concrete actions: 'Prerecorded videos require `.vtt` caption files via `<track>`', 'check that the video platform captions are enabled', 'Audio-only content requires transcripts instead', 'Video-only content (no audio) requires a text alternative'. This matches the 'lists several specific actions; minor gaps' anchor. Not 5: coverage is framed as requirements/checks rather than a comprehensive set of actions the skill performs; not 3: it goes well beyond 1-2 actions.

4 / 5

Completeness

Both parts are present: what ('Prerecorded videos require `.vtt` caption files via `<track>`... check that the video platform captions are enabled') and when ('Use when applies to all `<video>` elements and third-party video embeds'). Matches anchor 4 ('both what and when; when could be more explicit or specific') because the trigger clause is awkwardly phrased ('Use when applies to all') and less natural than the anchor-5 example. Not 3: 'when' is explicitly stated, not weakly implied; not 5: the garbled trigger phrasing keeps it below the clean 'concrete trigger phrases' anchor.

4 / 5

Trigger Term Quality

Natural keywords present: 'captions', 'video', 'YouTube', 'Vimeo', '`.vtt`', 'transcripts', '`<track>`'. This fits 'good keyword coverage; a few natural terms missing' — e.g., 'subtitles', 'WebVTT', 'track kind', and 'accessibility' are absent. Not 5: not comprehensive with synonyms; not 3: coverage is well beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

Clear niche — video captions on `<video>` elements and YouTube/Vimeo embeds — with distinct triggers ('`.vtt`', '`<track>`', 'captions', 'YouTube', 'Vimeo') that would not fire for other accessibility or media skills. Matches anchor 5 ('clear niche with distinct triggers; minimal conflict risk'). Not 4: the overlap risk with, say, a general media skill is minimal given the explicit scope boundaries (audio-only → transcripts, video-only → text alternative).

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
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.