Claude Video Skill
An open-source Claude skill that watches and analyzes videos (YouTube, TikTok, Zoom, Loom) frame by frame, not just via transcript.
Before & after
Same prompt, same agent — the only difference is the skill.
I can help analyze video hooks. The most common approach is reading the transcript to see what's said in the first 5 seconds. If you paste the transcript or a transcript link, I can look for hook patterns—questions, curiosity gaps, that kind of thing. That said, the visual story matters too, but I'd be working mostly from your description of what's on screen.
VIDEO HOOK ANALYSIS: "Why Startups Fail" (2:43-3:18)
FRAME-BY-FRAME BREAKDOWN
0:00-0:08: Host looks directly at camera, close-up (forehead to shoulders)
Verbal: "Nobody tells you this."
Effect: Eye contact kills scroll (attention peak)
Retention: 94% (internal benchmark)
0:08-0:16: Cut to B-roll of startup closing down (signage coming off wall)
Verbal: "90% of startups fail by year three."
Effect: Pattern-interrupt (visual shift), stakes raised
Retention: 87%
0:16-0:24: Return to host, now leaning forward
Verbal: "But nobody teaches WHY."
Effect: Intrigue (promise of secret knowledge)
Retention: 91%
HOOK VERDICT
Score: 8.2/10 (top 8% of this channel)
Strength: Direct address + visual cut at 0:08 (pattern-interrupt)
Weakness: Title oversells ("Why" answer delayed until 2:15)
RECOMMENDATION
Move the root cause to 0:20 to avoid drop-off. Tested on 12 peers: 3-4% retention lift.About this skill
name: claude-video-skill description: Use when An open-source Claude skill that watches and analyzes videos (YouTube, TikTok, Zoom, Loom) frame by frame, not just via transcript.
Claude Video Skill
Built by the original author and open-sourced, this skill lets Claude watch a public or local video and break down what happens on screen (including opening-hook analysis and scene-change extraction), rather than relying on the transcript alone. Referenced and extended by multiple other creators. youtube.com/@bradbonanno
What you get
- Frame-aware video watching and summarization for Claude.
Customize your output
- Extended versions add hook-microscope analysis and automatic note-taking integrations.
Example output
A breakdown of a video hook (what was on screen as each word landed) plus a full summary.
Best for
Creators and researchers who need Claude to actually watch a video, not just read its transcript.
SKILL.md preview
---
name: claude-video-skill
description: Use this skill to watch and analyze a video frame by frame, including opening hooks and scene changes, rather than relying only on its transcript.
version: 1.0.0
category: Development / Media
author: AgentVolt
license: proprietary
tags:
- development
- media
- standard
---
# Claude Video Skill
Watches a video (from YouTube, TikTok, Zoom, or a local file) and analyzes what happens on screen, catching visual structure a transcript alone would miss.
## When to use
… (sign up to view the full skill)More video & editing skills
View all Video & Editing skills →Matts Peeker
A Claude skill that watches any video (not just its transcript) to capture visual context Claude would otherwise miss.
Claude + Gemini Video Understanding Skill
A free custom Claude skill that connects Claude Code to Gemini Video Understanding API so Claude can watch, summarize, and batch-rename video clips.
Mograph Builder
Motion graphics from an AI video model: one style-locked motion sheet, then transcript-timed prompt packs for collage, type and B-roll.
Remotion Builder
Motion graphics as code: a script becomes deterministic Remotion scenes with charts, counters, maps and particle worlds, frame-exact.