watching-videos
Watch Skill processes any video—URLs, local files, streams, recordings—by extracting frames, running OCR, and transcribing audio into a unified searchable index. Query the index directly instead of re-watching, and batch-process playlists or folders in one pass.
Watch Skill extracts frames, transcripts, and OCR text from videos into a searchable index for instant content analysis.
AI-generated summary based on this skill's SKILL.md
Install
oxbshw/watch-skill/watching-videos · repository language: Python
git clone https://github.com/oxbshw/watch-skill
cp -r watch-skill/adapters/claude-skill/skills/watching-videos ~/.claude/skills/watching-videosnpx skillfed install oxbshw/watch-skill/watching-videosFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What can watching-videos extract and index from video content?
watching-videos extracts and indexes video content by processing frames, running OCR on text within those frames, and transcribing audio into a unified searchable index. This lets you query the index directly instead of re-watching videos, making it easy to find specific moments, text, or topics across your video library.
Can watching-videos transcribe meeting recordings automatically?
Yes. watching-videos automatically transcribes video recordings, including meeting recordings, by extracting and processing the audio track. The resulting transcript becomes part of the searchable index, so you can find specific discussion points or phrases without manually reviewing the entire recording.
How does watching-videos handle batch processing of videos?
watching-videos processes multiple videos or playlists in batch mode, allowing you to submit a folder of video files or a playlist URL in one pass. The skill indexes all content together, creating a unified searchable database across the entire batch rather than requiring individual file processing.
What video sources does watching-videos support?
watching-videos handles any video format: URLs (including YouTube and TikTok links), local files (MP4, etc.), screen captures, meeting recordings, lecture videos, HLS streams, and playlists. Whether your content is online or stored locally, watching-videos can extract frames, transcribe audio, and index it for search.
Can I search video content by phrase or timestamp?
Yes. watching-videos lets you search and query the indexed video content by phrase or timestamp. Instead of scrubbing through recordings manually, you can search for specific text, topics, or moments across one or multiple videos at once, with results linked back to their source frames and timestamps.
Does watching-videos work offline or require internet?
watching-videos can transcribe video offline locally, processing video files stored on your machine without requiring an internet connection. This makes it ideal for sensitive recordings, large batches, or environments where streaming isn't practical. The skill is released under the MIT license.
SKILL.md
rendered from the published skill — quoted content, verbatim
Watching videos
You don't have a video input; this skill gives you one. Anything a user hands you — a YouTube link, a TikTok, a lecture, a meeting recording, a screen capture, an .mp4 on disk — goes through the same pipeline: frames (scene-aware, deduplicated), OCR, transcript (captions first, local Whisper offline fallback), all persisted into one index.
Before watching: check the index
watch-skill list
If the video was already analyzed — this session or any earlier one —
do NOT watch it again. Ask it directly (see the asking-with-evidence
skill):
watch-skill ask <video_id> "<question>"
One video
```bash watch-skill watch "<url-or-path>"
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
adapters/claude-skill/skills/watching-videos/SKILL.md