How do I install the Watching Videos skill?

Run npx skillmds@latest add oxbshw/watching-videos in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Watching Videos safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Watching Videos?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Watching Videos free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Watching Videos?

oxbshw (@oxbshw) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Watching Videos by oxbshw — Agent Skill

Name: Watching Videos
Author: oxbshw

Watching Videos

The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording, a meeting recording, or a playlist/folder of videos — "watch this", "summarize this video", "what's in this recording". Use this to actually watch the video — download, extract frames, OCR, transcribe, and index it — instead of guessing from the title or asking the user to describe it.

oxbshw Updated Sep 17, 2026

File contents

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

watch-skill watch "<url-or-path>" [--start T --end T] [--max-frames N] [--transcript-only]

Works on any yt-dlp-supported site (1800+), direct media URLs, HLS/DASH manifests (--duration 60 bounds live streams), and local files.
Video over ~10 minutes and the user cares about one part → use --start/--end for dense sampling of that window.
User only needs what was said → --transcript-only (fastest, often no video download at all).

The report prints Indexed: <video_id>, frames with t=MM:SS timestamps, OCR text, and the transcript. Read every frame path listed — in a single message, parallel Read calls — then answer from frames + OCR

transcript, citing timestamps.

Many videos (playlist, channel, folder)

watch-skill batch "<playlist-url-or-folder>" [--limit N]

Everything lands in the same index; one broken video never stops the rest. Afterwards a single watch-skill search "<phrase>" spans the whole batch.

First run on a machine

If any command fails with a dependency error, run watch-skill doctor once — it installs missing ffmpeg/yt-dlp itself. No API key is required for any of this; transcription is local by default and the video file never leaves the machine.

---name: watching-videosdescription: The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording, a meeting recording, or a playlist/folder of videos — "watch this", "summarize this video", "what's in this recording". Use this to actually watch the video — download, extract frames, OCR, transcribe, and index it — instead of guessing from the title or asking the user to describe it.license: MIT---# Watching videosYou don't have a video input; this skill gives you one. Anything a userhands you — a YouTube link, a TikTok, a lecture, a meeting recording, ascreen capture, an .mp4 on disk — goes through the same pipeline: frames(scene-aware, deduplicated), OCR, transcript (captions first, localWhisper offline fallback), all persisted into one index.## Before watching: check the index```bashwatch-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):```bashwatch-skill ask <video_id> "<question>"```## One video```bashwatch-skill watch "<url-or-path>" [--start T --end T] [--max-frames N] [--transcript-only]```- Works on any yt-dlp-supported site (1800+), direct media URLs, HLS/DASH manifests (`--duration 60` bounds live streams), and local files.- Video over ~10 minutes and the user cares about one part → use `--start`/`--end` for dense sampling of that window.- User only needs what was said → `--transcript-only` (fastest, often no video download at all).The report prints `Indexed: <video_id>`, frames with `t=MM:SS`timestamps, OCR text, and the transcript. Read every frame path listed —in a single message, parallel Read calls — then answer from frames + OCR+ transcript, citing timestamps.## Many videos (playlist, channel, folder)```bashwatch-skill batch "<playlist-url-or-folder>" [--limit N]```Everything lands in the same index; one broken video never stops therest. Afterwards a single `watch-skill search "<phrase>"` spans the wholebatch.## First run on a machineIf any command fails with a dependency error, run `watch-skill doctor`once — it installs missing ffmpeg/yt-dlp itself. No API key is requiredfor any of this; transcription is local by default and the video filenever leaves the machine.

Frequently asked questions