Multimodal Extraction

Given a local video or video URL, downloads the media if needed, extracts slide frames and key moments, transcribes the audio, and writes a Markdown timeline that interleaves screenshots with the transcript at the associated timestamps. Use when asked to turn a video into a multimodal notes file, slide-synced transcript, screenshot-enhanced transcript, or talk recap with images.

201 stars 12 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add swyxio/skills --skill multimodal-extraction
Manual install
git clone --depth 1 https://github.com/swyxio/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/multimodal-extraction ~/.claude/skills/multimodal-extraction

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Multimodal Extraction

## Overview

This skill composes the existing video workflows into one artifact:

- `download-video` for URL inputs
- `thumbnail-extraction` for slide frames and key screenshots
- `transcribe-anything` for transcript strategy

The implementation is intentionally speed-first:

1. Download only when the input is a URL
2. Reuse the fast slide/key-frame heuristics from `thumbnail-extraction`
3. Use local `whisper` JSON output for timestamped transcript segments
4. Merge everything into one Markdown timeline with relative image links

## When To Use

- "Turn this talk into multimodal notes"
- "Make me a markdown transcript with screenshots"
- "Extract slides and transcript together"
- "Build a recap doc from this video"
- "Given this YouTube URL, produce a slide-synced transcript"

## Requirements

```bash
brew install ffmpeg yt-dlp
pip3 install --break-system-packages openai-whisper
```

The following existing local script is reused:

- `../thumbnail-extraction/thumbnail_extractor.py`

## Command

```bash
python3 multimodal_extract.py <video_or_url> [output_dir] [--language en] [--whisper-model turbo] [--top-n 4]
```

## What It Does

### Step 1: Resolve the Source

- If the input is a local file, use it directly
- If the input starts with `http://` or `https://`, download it first with `yt-dlp`
- For YouTube URLs, direct `yt-dlp` is usually enough
Read the full skill on GitHub

Details

Skill name
multimodal-extraction
Repository
swyxio/skills
Path
multimodal-extraction/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Multimodal Extraction skill do?

Given a local video or video URL, downloads the media if needed, extracts slide frames and key moments, transcribes the audio, and writes a Markdown timeline that interleaves screenshots with the transcript at the associated timestamps. Use when asked to turn a video into a multimodal notes file, slide-synced transcript, screenshot-enhanced transcript, or talk recap with images.

How do I install the Multimodal Extraction skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add swyxio/skills --skill multimodal-extraction. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Multimodal Extraction popular?

It lives in swyxio/skills, which has 201 GitHub stars and 12 forks.

Related skills

Accelevents API

201

swyxio/skills

Use when reading or updating AI Engineer Europe speaker records through the Accelevents REST API, especially for full-record PUT updates, auth header quirks, and preserving existing speaker fields.

Software Development12

Accelevents Speaker Sync

201

swyxio/skills

Use when website speaker, session, schedule, room, track, or headshot changes must be synchronized back to Accelevents for AI Engineer Europe 2026.

AI, LLMs & Agents12

Agents SDK

201

swyxio/skills

Build or debug stateful applications that specifically use Cloudflare's `agents` package, including Agent classes, routing, callable methods, synchronized state, scheduling, AIChatAgent, durable execution, or Agents SDK client hooks. Do not trigger for generic AI-agent design, the OpenAI Agents SDK, or ordinary Durable Object work that does not use the Cloudflare Agents SDK.

AI, LLMs & Agents12

Musical Dna

191

jwynia/agent-skills

Extract descriptive musical characteristics from any artist or band without using their name, building a vocabulary of sonic qualities for AI music generation, music description, or creative recombination.

Images, Video & Audio24

Media Transform

201

swyxio/skills

Generic media transformation orchestrator — download videos from any source (X/Twitter, Zoom, YouTube, web embeds), upload to YouTube, transcribe with timestamps, generate chapters, create thumbnails with GPT-Image-2, and A/B test titles. Use when the user wants to move a video from one platform to another, or asks to "download and upload this video to YouTube", "publish this recording", "save and transcribe this", or any video pipeline task. Encodes learned best practices and preferences for each stage.

Images, Video & Audio12

Podcast Interview

150

guia-matthieu/clawfu-skills

Master the art of podcast interviewing using NPR training methodology and Tim Ferriss's preparation techniques to extract compelling stories and insights from any guest. Use when: Preparing for a podcast interview with a guest; Designing questions that elicit stories, not soundbites; Struggling to get guests to open up authentically; Planning a new interview-format podcast; Improving your interviewing technique

Images, Video & AudioIn 1 list32

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.