Watch
Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analysis into your Obsidian vault (configurable via `$WATCH_VAULT_DIR`) — tied to *why* the user watched it.
Install
npx skills add taoufik123-collab/claude-watch --skill watchgit clone --depth 1 https://github.com/taoufik123-collab/claude-watch.git /tmp/claude-watch
mkdir -p ~/.claude/skills
cp -r /tmp/claude-watch/. ~/.claude/skills/watchPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# /watch — Claude watches a video You don't have a video input; this skill gives you one. A Python script downloads the video, extracts frames as JPEGs (one per detected shot via scene-change), gets a timestamped transcript (native captions first, then Whisper API as fallback), runs editorial pacing metrics, and microscopes the first 10 seconds at higher density. You then `Read` each frame path to see the images, combine them with the transcript to answer the user, fill the structured `report.md`, and offer to ingest the analysis into Taoufik's Second Brain. ## What v2 does differently - **Scene-change frame sampling** — one frame per detected shot instead of uniform ticks. Cuts the frame budget on long videos while capturing every transition. - **Editorial pacing metrics** — cuts/min, mean shot length, motion (when available). Lets you reason about pacing the way an editor does. - **Hook microscope** — first 10s auto-runs at 2 fps + word-level Whisper. The single most leveraged 10 seconds of any video deserves dense treatment. - **Structured `report.md`** — every watch emits an ingest-shaped report at `<workdir>/report.md` with TL;DR, key moments, hook breakdown, editorial profile, quotable moments, entities, concepts, and transcript. Narrative sections are emitted as `` markers — you fill them in before offering ingest.
Details
- Skill name
watch- Repository
- taoufik123-collab/claude-watch
- License
- MIT
- Repo updated
- 24 July 2026
FAQ
What does the Watch skill do?
Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analysis into your Obsidian vault (configurable via `$WATCH_VAULT_DIR`) — tied to *why* the user watched it.
How do I install the Watch skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add taoufik123-collab/claude-watch --skill watch. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Watch popular?
It lives in taoufik123-collab/claude-watch, which has 1,091 GitHub stars and 216 forks.
Related skills
Firecrawl Search
676firecrawl/cli
Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or finding structured records, listings, transcripts, and datasets. Supports semantic tool discovery, domain matching, and progressive catalogue browsing.
Ppt Image First
1.2kNyxTides/ppt-image-first
Build presentation plans for PPT / slides / decks through a conversation-first workflow, then propose multiple visual directions with preview images before writing deck specs. Use when the user asks to create a PPT, presentation, deck, 答辩稿, 路演 deck, 产品介绍 PPT, 汇报 PPT, or when the user has only a topic or rough materials and needs help clarifying structure, style, and page planning before generation.
Video Spec Builder
1.1kfeicaiclub/video-spec-builder
当用户说想做一个视频、宣传片、产品演示、动画短片、抖音/YouTube 内容，或者说要改分镜、调节奏、换镜头、调字幕、加配音、改转场时使用。通过苏格拉底式追问收集视频需求，主动激发渲染层的全部能力（TTS / 字幕 / 3D / shader / 音频反应等），输出标准化的 video-spec.md 用于渲染。
Guizang Material Illustration
1.2kop7418/guizang-material-illustration
Generate Guizang-style material illustrations, labeled explanatory visuals, material-styled chart illustrations, and data-first editorial images from articles, notes, product concepts, workplace reports, creator posts, tutorials, school materials, humanities topics, science explanations, screenshots, or chart data. Use when the user asks for 配图, 带字插图, 解释图, 图解插画, 概念拆解图, 图表美化, 数据图美化, 3D 图表, 汇报配图, 内容配图, 小学课文配图, 生物/化学/物理解释图, 人文类配图, process/loop/system diagrams, or wants GPT-Image / image generation to create supporting images that can sit inside social cards, docs, slides, PPTs, or posts.
Visio Image Rebuilder
1.1kpengjunchi0/codex-visio-paper-figure-skill
Rebuild or restyle editable Microsoft Visio diagrams from reference images and existing .vsdx files, then export deliverables as .vsdx, PNG, SVG, PDF, or PPTX. Use when the user asks Codex to open Visio, recreate a diagram from a PNG/JPG/screenshot/reference image, match a scientific model figure, update colors/typography/layout in a .vsdx, calibrate panel coordinates to avoid shifted or overlapping submodules, or make publication/presentation outputs while preserving Visio native editable shapes rather than embedding the reference image as a flat picture.
Edit Timeline Studio
926MartinDelophy/ai-video-editor
Analyze images, video, speech, motion, products, and websites; route local vision, audio, depth, tracking, matting, identity, and restoration models; auto-edit, replicate, enhance, caption, voice, assemble, annotate, validate, and export editable Timeline Studio projects and videos. Use for reference-video remakes, filter and repeated-shot reconstruction, subject-aware reframing, clip splitting, source-time speed curves, Color Wheels grading, ramps and holds, person or product cutout, person or object outline, authorized face swap, shot and timing reconstruction, timeline markers, chapters, be
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.