watch-video
Marcin Sufa v1.0.0
watch-video gives Claude eyes and ears for any video — local files, public URLs (YouTube, Loom, Vimeo, TikTok, ~1,500 sites via yt-dlp), or Jira attachments fetched directly via API token. One comm...
From the developer
License
MIT
Declared components
Skills
Works with
Claude Code
Description
From the marketplace listing
watch-video gives Claude eyes and ears for any video — local files, public URLs (YouTube, Loom, Vimeo, TikTok, ~1,500 sites via yt-dlp), or Jira attachments fetched directly via API token. One command produces a complete evidence bundle: timestamped JPEG frames, a Whisper transcript (local faster-whisper or hosted Groq / OpenAI), optional OCR for on-screen text, and three report formats — report.md, self-contained report.html with base64-embedded frames, and corporate-friendly report.docx. Key features: - LLM-driven highlights: pass a prompt ("summarize the rate decision and inflation outlook", "identify the bug and when it occurs") and Claude picks the N most relevant moments with frame + reason + verbatim quote. - Smart dedup with perceptual hash + transcript-aware protection: typically drops 40-60% of redundant frames on screen recordings without losing narrated moments. - OCR for screen-recording UIs: Tesseract with 2x upscale + auto-invert + PSM 6, output to grep-able ocr.txt. - Per-step content-hash cache: re-runs are nearly free. - Opt-in Jira posting with a confirmation gate BEFORE any attachment upload — declining leaves the ticket untouched, no orphan state. - Batch mode for sprint retros: process a JQL query's worth of bug tickets in one command.
What changed
No changes recorded yet. Follow this plugin to keep track of future changes.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Transcribe video and audio from URLs (YouTube, X/Twitter, TikTok, Vimeo, podcasts) or local media files into plain-text transcripts using...
Shared terms: dlp, local, tiktok, urls
-
A perception layer that gives Claude Code the ability to watch and understand videos. Extracts frames via ffmpeg and processes audio thro...
Shared terms: give, video, watch, frame
-
Give Claude eyes for video. Extracts key frames using scene detection and lets Claude analyze screen recordings, bug reports, tutorials, ...
Shared terms: eyes, give, video, frame
-
Lets Claude analyze video files by extracting key frames using ffmpeg scene detection. Instead of processing video natively, the plugin c...
Shared terms: video, file, frame, key
-
Analyze video files: especially bug report screen recordings, directly in Claude Code. Extracts frames via ffmpeg, transcribes audio via ...
Shared terms: video, file, frame, produce
Keywords
Files & skills
watch-video · catalog manifest
Saved declaration
{}
watch-video · catalog manifest
Saved declaration
{
"name": "watch-video",
"source": {
"sha": "f6b4a2e62f51a045fc789245bb364c9ac8d970c7",
"url": "https://github.com/MarcinSufa/claude-watch-video.git",
"source": "url"
},
"homepage": "https://github.com/MarcinSufa/claude-watch-video",
"description": "watch-video gives Claude eyes and ears for any video — local files, public URLs (YouTube, Loom, Vimeo, TikTok, ~1,500 sites via yt-dlp), or Jira attachments fetched directly via API token. One command produces a complete evidence bundle: timestamped JPEG frames, a Whisper transcript (local faster-whisper or hosted Groq / OpenAI), optional OCR for on-screen text, and three report formats — report.md, self-contained report.html with base64-embedded frames, and corporate-friendly report.docx.\n\nKey features:\n- LLM-driven highlights: pass a prompt (\"summarize the rate decision and inflation outlook\", \"identify the bug and when it occurs\") and Claude picks the N most relevant moments with frame + reason + verbatim quote.\n- Smart dedup with perceptual hash + transcript-aware protection: typically drops 40-60% of redundant frames on screen recordings without losing narrated moments.\n- OCR for screen-recording UIs: Tesseract with 2x upscale + auto-invert + PSM 6, output to grep-able ocr.txt.\n- Per-step content-hash cache: re-runs are nearly free.\n- Opt-in Jira posting with a confirmation gate BEFORE any attachment upload — declining leaves the ticket untouched, no orphan state.\n- Batch mode for sprint retros: process a JQL query's worth of bug tickets in one command."
}
watch-video · catalog manifest
Skills
"./"
Saved declaration
{
"name": "watch-video",
"author": {
"name": "Marcin Sufa",
"email": "sufa.marcin@gmail.com"
},
"skills": "./",
"license": "MIT",
"version": "1.0.0",
"homepage": "https://github.com/MarcinSufa/claude-watch-video",
"keywords": [
"video",
"transcription",
"whisper",
"ffmpeg",
"jira",
"bug-repro",
"screen-recording",
"yt-dlp",
"multimodal"
],
"repository": "https://github.com/MarcinSufa/claude-watch-video",
"description": "Make Claude watch any video. Local file, public URL (yt-dlp), or Jira attachment (fully automated). Extracts keyframes with ffmpeg, transcribes with local faster-whisper or hosted Groq/OpenAI Whisper, and produces a paste-ready evidence-bundle Markdown report."
}
plugin.json observed Nov 6, 2026 · 10:50 UTC. Manifest source ↗
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation instructions
Community
/plugin marketplace add anthropics/claude-plugins-community
/plugin install watch-video@claude-community
Technical details
- Sources
- Community
- First seen
- Oct 3, 2026 · 22:13 UTC
- Last seen
- Nov 7, 2026 · 06:00 UTC
- Latest observed change
- Oct 3, 2026 · 22:13 UTC
- Collection status
- Listed
- Reported installs
- Not provided
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: freshly prepared. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.