CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

video-transcript-downloader

yt-dlp downloads: video, audio, subtitles, transcripts, clips, playlists.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/video-transcript-downloader/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A tight, highly actionable CLI skill: every documented command is executable and matches the bundled vtd.js, structure is clear, and guidance like defaults and arg passthrough is exactly what an agent needs. The only real weaknesses are minor — slight repetition across example blocks and undocumented capabilities (clips, playlists) claimed by the description.

DimensionReasoningScore

Conciseness

The body is lean and command-first with almost no explanation of concepts Claude already knows, though the near-identical example blocks (repeated "--url 'https://…' --output-dir ~/Downloads" lines) and the Notes section restating defaults could be trimmed slightly. This matches the efficient-with-minor-trimmable-instances anchor, not the 5 where every token is maximally earned.

4 / 5

Actionability

Every example is a fully executable, copy-paste-ready command (setup via npm ci, transcript/download/audio/subs/formats invocations, format selection with "-- --format 137+140", remux, yt-dlp arg passthrough), and the commands verified against the actual vtd.js CLI. The examples cover all common cases including the transcript fallback behavior.

5 / 5

Workflow Clarity

Setup → per-command usage → troubleshooting is clearly sequenced, subcommand help is pointed out, and error behavior is documented ("Empty cleaned subtitles exit with an error and remove their temporary files"), with verification commands in Troubleshooting. Minor gaps keep it below 5: the description's "clips" and "playlists" capabilities have no usage examples, and there is no guidance on choosing between transcript and subs.

4 / 5

Progressive Disclosure

The body is well-sectioned and its single reference, "./scripts/vtd.js", is a real bundle file clearly signaled and central to the skill; helper scripts (html-entities.js, vtd.test.mjs) are appropriately not inlined. At ~86 lines the body exceeds the under-50-line simple-skill exemption, and the unmentioned bundle files plus some content that could live in a reference keep this at good-structure-with-minor-gaps rather than 5.

4 / 5

Total

17

/

20

Passed

Description

66%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.

A concise, concrete, tool-anchored description that clearly states what the skill does, but it omits any "when to use" trigger clause, which both caps completeness and weakens its usefulness for skill selection. Adding explicit trigger guidance and a couple of natural synonyms (YouTube, captions) would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants to download videos, audio (mp3), subtitles, or transcripts from YouTube or other yt-dlp-supported sites."

Add natural synonyms users actually say — "YouTube", "captions", "rip/extract audio" — to improve trigger term coverage.

Ensure every listed capability is backed by the body: "clips" and "playlists" appear in the description but have no corresponding commands in SKILL.md, which risks over-claiming.

DimensionReasoningScore

Specificity

The description lists six concrete download objects ("video, audio, subtitles, transcripts, clips, playlists") anchored to a specific tool ("yt-dlp downloads"), which is several specific actions with only minor gaps (no format selection or YouTube mention). It falls short of a 5 because it uses a single action verb applied to nouns rather than the multiple distinct concrete actions of the top anchor.

4 / 5

Completeness

The "what" is clear (yt-dlp downloads of video, audio, subtitles, transcripts, clips, playlists) but there is no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. It is not a 4 because the "when" is entirely absent rather than merely implicit-but-stated.

3 / 5

Trigger Term Quality

"video", "audio", "subtitles", "transcripts", "playlists", and "yt-dlp" are terms users naturally say when needing this skill. A few natural variants are missing (e.g., "YouTube", "captions", ".mp3"), matching the good-coverage-with-small-gaps anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Naming "yt-dlp" plus the transcript/subtitle focus gives it a clear niche with minimal conflict risk against unrelated skills, though it could still overlap with another generic yt-dlp or video-download skill — the minor-overlap profile of the 4 anchor.

4 / 5

Total

15

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

steipete/agent-scripts

Path

skills/video-transcript-downloader/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.