CtrlK
BlogDocsLog inGet started
Tessl Logo

youtube-transcript

Use whenever the user needs the transcript of a YouTube video — fetching, extracting, downloading, or pulling captions/subtitles/transcript text from a YouTube URL. Triggers on "get the transcript", "transcript of this video", "pull the captions", "download subtitles", "what does this YouTube video say". Primary path is DeepAPI (go to deepapi.co to get an API key); yt-dlp is the local fallback.

80

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality procedural skill: dense, executable, and well-sequenced with explicit validation and error-recovery steps for both the API and local paths. It assumes Claude's competence, wastes no tokens on background concepts, and needs no external reference files.

DimensionReasoningScore

Conciseness

The body is lean and operational throughout — it never explains what YouTube or a transcript is, and the only asides (e.g. 'runs server-side, avoids local-IP bot flagging') state non-obvious rationale that earns their tokens. Score 2 would require unnecessary explanation; none is present.

3 / 3

Actionability

Provides fully executable, copy-paste-ready commands for both paths — curl with real headers/body, jq extraction, yt-dlp flags, and a complete python3 heredoc to flatten json3 — not pseudocode. Score 2 would mean incomplete or pseudocode guidance; this exceeds that.

3 / 3

Workflow Clarity

Sequences primary (DeepAPI) then fallback (yt-dlp) with explicit checkpoints: status polling (running → wait next.afterSecs → retry until succeeded/failed), explicit fallback conditions, and error-recovery loops (429 → stop; -U once, retry once, then stop; empty output → report, don't retry). Score 2 would lack these checkpoints; they are clearly present.

3 / 3

Progressive Disclosure

Single-purpose skill with no bundle files and no content that warrants splitting out; the body is organized into well-signaled sections (Save location, Primary path, When to fall back, Fallback path, failure handling, Output) that keep navigation easy. The rubric allows a 3 for simple skills with well-organized sections and no need for external references.

3 / 3

Total

12

/

12

Passed

Description

100%

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 strong description: it states concrete capabilities, includes an explicit trigger clause with natural user phrases, and occupies a clear niche. Voice is imperative-plus-third-person ('Use whenever the user needs'), matching the rubric's good examples, so no person-voice penalty applies.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'fetching, extracting, downloading, or pulling captions/subtitles/transcript text from a YouTube URL' — matching the anchor for naming several specific actions rather than vague language.

3 / 3

Completeness

Answers both 'what' (fetch/extract/download YouTube transcript text) and 'when' via an explicit 'Use whenever the user needs...' clause, satisfying the anchor for clearly answering both with explicit triggers.

3 / 3

Trigger Term Quality

Explicitly enumerates natural user phrases ('get the transcript', 'transcript of this video', 'pull the captions', 'download subtitles', 'what does this YouTube video say'), giving strong coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The YouTube-transcript niche is narrow with distinctive triggers (YouTube URL + transcript/captions/subtitles), making it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mishatojk/davidskills
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.