Video Transcript Agent Skill
Extract video transcripts: yt-dlp subtitles to clean paragraphs.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/notque/vexjoy-agent --skill video-transcriptThe instruction itself
5 sections, as written by the authorVideo Transcript
Pull a video's transcript as readable paragraphs. Two paths, in order:
Path 1 — uploader subtitles (accurate, prefer when present):
yt-dlp --skip-download --write-subs --sub-langs en --sub-format vtt \
-o '<work-dir>/%(id)s' '<URL>'
Path 2 — auto-generated captions (fallback when path 1 writes no file):
yt-dlp --skip-download --write-auto-subs --sub-langs en --sub-format vtt \
-o '<work-dir>/%(id)s' '<URL>'
Then clean the VTT into paragraphs:
python3 skills/research/video-transcript/scripts/vtt_to_paragraph.py <work-dir>/<id>.en.vtt
Default output is plain paragraph text with [Music]-style cues stripped and the rolling duplicates of auto-captions deduplicated. Use --timestamps for [mm:ss] markers, --keep-brackets to keep cue tags, -o FILE to write to a file.
For other languages, change --sub-langs (e.g. de, en.*). List what a video offers with yt-dlp --list-subs '<URL>'.
Error handling
Both paths write no .vtt file
Cause: video has no subtitles or captions in the requested language.
Solution: run yt-dlp --list-subs '<URL>' and pick an available language; if none exist, report that and offer audio transcription via the markdown-converter skill on a downloaded audio file.
HTTP 429 / "Sign in to confirm"
Cause: platform rate-limiting the host.
Solution: wait and retry with --sleep-requests 2; keep request volume low.
Cleaner output repeats lines
Cause: VTT came from a third path (e.g. translated captions) with cue formats the dedupe misses.
Solution: rerun the cleaner; if repeats remain, file the sample VTT alongside a fix to vtt_to_paragraph.py.
Other skills for the same job
different authors, same section of the catalogue
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and converts Markdown to rich text automatically.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
How to use it
Take notque/video-transcript from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.