Add Filaxy Watch skill - #1509
Open
Othmaro Fallas Rojas (othmarodev) wants to merge 2 commits into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What problem it solves
Claude can read text and see images, but has no native way to watch a video — no frame decoding, no audio transcription, no built-in logic for how many frames a 5-minute vs 45-minute clip needs. Filaxy Watch closes that gap: it downloads a video (URL or local file), extracts an auto-scaled set of frames with
ffmpeg, pulls a timestamped transcript (native captions or Whisper fallback), and hands both to Claude toReadand answer from — grounded in what it actually saw and heard, not a guess from a title or filename.Who uses this workflow
Diagnosing a bug from a shared screen recording, summarizing a long video instead of watching it at 2x, breaking down a competitor's video/ad, or answering "what happens at the X minute mark?" This is a different job than the existing
Video Downloader(just downloads, no analysis) oryoutube-transcript(transcript only, no visual understanding) entries already in this category — Filaxy Watch is the "understand the video" skill, not the "get the file" or "get the words" skill.Attribution / inspiration source
This is a rebrand/fork of
claude-videoby Brad Bonanno (@bradbonanno), MIT licensed. Credited in the SKILL.md's "Inspired by" section per the contributing guidelines. On top of the rename, this fork adds a download cache (skip re-fetching a URL you already asked about), live extraction progress (ffmpeg's own frame/time stats streamed as a throttled heartbeat instead of the process going silent), and multi-video support (watch.py video1.mp4 video2.mp4 ...in one call). Verified against the original project's full test suite (77/77 passing).Example of how it's used
Full docs, diagram, and install options: https://github.com/othmarodev/Filaxy-whatch_skill_for_claude