Extract video transcripts: yt-dlp subtitles to clean paragraphs.
npx skills add https://github.com/notque/vexjoy-agent --skill video-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>'.
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.
Cause: platform rate-limiting the host.
Solution: wait and retry with --sleep-requests 2; keep request volume low.
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.
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.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
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.
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
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.