ellyseum/claude-vision

ellyseum-Profil

Letzte erfasste Quellaktivität: 11. Februar 2026 um 07:54

SkillsMP-Katalog aktualisiert: 17. Oktober 2026 um 00:09

gesammelte Skills: 5

GitHub-Stars: 1
GitHub-Forks: 0

README des Repositorys

README-Quelldatei: README.md

README-Quelldatei lesen

Vollständige README anzeigen

<p align="center"> <img src="assets/logo.png" alt="claude-vision logo" width="100"> </p> <h1 align="center">claude-vision</h1> <p align="center"> <a href="https://github.com/ellyseum/claude-vision"><img src="https://img.shields.io/badge/Claude_Code-Plugin-blueviolet" alt="Claude Code Plugin"></a> <a href="https://github.com/ellyseum/claude-vision/pkgs/container/claude-vision"><img src="https://img.shields.io/badge/docker-ghcr.io-blue" alt="Docker"></a> <a href="#platform-support"><img src="https://img.shields.io/badge/platform-WSL%20|%20macOS%20|%20Linux-lightgrey" alt="Platform"></a> <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/license-MIT-green" alt="License"></a> </p> Visual context skills for Claude Code. Gives Claude the ability to see your clipboard, screenshots, and videos. ## Why This Exists Claude Code can technically read images—you just paste in the file path and it'll analyze them. But the workflow is clunky: - You screenshot an error, but now you need to find where your OS saved it - You copy something to your clipboard, but there's no way to share it - You want Claude to look at a video, but... you can't This plugin fixes all of that. Instead of hunting for file paths, just: ``` /clipboard what's this? /screenshot explain this error /video summarize this tutorial ``` ### Video Analysis Claude doesn't natively support video. But with some clever extraction, we can give it Gemini-like video understanding: 1. **YouTube videos** → Extract auto-captions + key frames 2. **Local videos** → Scene detection for key frames + optional whisper transcription 3. **Screen recordings** → Same scene detection, finds the moments that matter The `/video` skill spawns a dedicated **analysis agent** with a fresh 200k context. This means: - 100+ frames instead of a handful - Full transcripts without truncation - Thorough analysis without bloating your conversation The result: Claude can "watch" videos by analyzing representative frames and reading the transcript. It handles tutorials, error recordings, meetings, and lectures surprisingly well. ## What's Included | Skill | Description | |-------|-------------| | `/clipboard` | Read text or images from your clipboard | | `/screenshot` | Analyze your latest screenshot | | `/video` | Analyze YouTube videos or local recordings | | `/claude-vision-setup` | Interactive setup wizard | ## Quick Start ```bash # Add the marketplace and install the plugin /plugin marketplace add ellyseum/claude-plugins /plugin install claude-vision # Run setup (auto-runs on first use of any skill) /claude-vision-setup ``` ## Docker Images | Image | Size | Includes | Use Case | |-------|------|----------|----------| | **Lite** | ~500 MB | ffmpeg, yt-dlp | YouTube, screen recordings | | **Full** | ~10 GB | ffmpeg, yt-dlp, whisper | Local videos needing transcription | **Which should I choose?** - **Lite** - For most users. YouTube has auto-captions, screen recordings usually don't need audio. - **Full** - Only if you have local videos where you need to transcribe speech. ### GPU Acceleration (Full image only) Whisper transcription speed: | Setup | Speed | 1 hour video | |-------|-------|--------------| | CPU | ~10x realtime | ~6 minutes | | GPU (CUDA) | ~50x realtime | ~1 minute | To enable GPU: 1. NVIDIA GPU + drivers installed 2. Install [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html) 3. `cv-run` will auto-detect and enable GPU ## Platform Support | Feature | WSL | macOS | Linux | |---------|-----|-------|-------| | Clipboard (text) | Yes | Yes | Yes (xclip) | | Clipboard (image) | Yes | Yes (pngpaste) | Yes (xclip) | | Screenshot | Yes | Yes | Yes | | Video analysis | Yes | Yes | Yes | ### Windows Users: Why WSL? This plugin runs through WSL (Windows Subsystem for Linux), not native Windows. Here's why: **Docker Desktop for Windows requires WSL2 anyway.** If you have Docker installed on Windows, you already have WSL2. The plugin just runs inside that same Linux environment where Docker lives. This keeps the codebase simple—one set of bash scripts instead of maintaining parallel PowerShell versions. **Need native Windows support?** If you have a use case that requires native Windows commands or a non-Docker workflow, [open an issue](https://github.com/ellyseum/claude-vision/issues) and we'll consider it. ### Prerequisites **Clipboard/screenshot:** - **WSL:** PowerShell (built-in) - **macOS:** `brew install pngpaste` (for images) - **Linux:** `apt install xclip` **Video processing:** Docker (required) ## Usage ### Clipboard ```bash /clipboard what is this? /clipboard explain this code /clipboard describe what you see ``` ### Screenshot Auto-detects your screenshot directory (configured during setup) and finds the most recent file by timestamp. ```bash /screenshot what's the error here? /screenshot # Describes what it sees /screenshot analyze the last 3 screenshots /screenshot compare these two screenshots ``` ### Video ```bash # YouTube (uses auto-captions) /video https://youtube.com/watch?v=xyz summarize this # Local recordings /video what went wrong in my screen recording # Follow-up questions (cached) /video follow-up what was the error message? # Cache management /video --list /video --clear ``` ## cv-run CLI The `cv-run` script manages Docker: ```bash cv-run ffmpeg -i video.mp4 ... # Run ffmpeg in container cv-run yt-dlp https://... # Run yt-dlp cv-run whisper audio.mp3 # Run whisper (full image only) # Get images (pick one) cv-run --pull-lite # Pull lite from ghcr.io (fast) cv-run --pull-full # Pull full from ghcr.io (fast) cv-run --build-lite # Build lite locally (~1 min) cv-run --build-full # Build full locally (~6 min) # Container management cv-run --status # Show detailed status cv-run --stop # Stop container cv-run --rm # Remove container ``` Images are hosted at `ghcr.io/ellyseum/claude-vision`. ## Configuration Config file: `~/.claude/claude-vision/config.json` ```json { "mode": "docker", "os": "wsl", "image_variant": "lite", "screenshot_dir": "/mnt/c/Users/yourname/Pictures/Screenshots", "created": "2026-02-02T...", "version": "1.0" } ``` ## Project Structure ``` claude-vision/ ├── .claude-plugin/ # Plugin metadata ├── Dockerfile # Full image (ffmpeg, yt-dlp, whisper) ├── Dockerfile.lite # Lite image (ffmpeg, yt-dlp only) ├── README.md ├── bin/ │ └── cv-run # Docker/local command router ├── hooks/ │ └── session-start.sh └── skills/ ├── clipboard/ ├── screenshot/ ├── video/ └── claude-vision-setup/ ``` ## Troubleshooting ### Docker not running ```bash # Start Docker daemon sudo systemctl start docker # Or open Docker Desktop ``` ### Image not found ```bash cv-run --pull-lite # or --pull-full (recommended, fast) cv-run --build-lite # or --build-full (if pull fails) ``` ### GPU not working in container ```bash # Check nvidia-smi works on host nvidia-smi # Install nvidia-container-toolkit # See: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html # Recreate container cv-run --rm cv-run ffmpeg -version # Will recreate with GPU ``` ### Clipboard permission denied (WSL) Make sure you're in a proper terminal, not a headless SSH session. ### xclip not found (Linux) ```bash sudo apt install xclip ``` ### pngpaste not found (macOS) ```bash brew install pngpaste ``` ## License MIT

README des Repositorys wird geladen…

Skills in diesem Repository

Softwareentwickler

1 Berufskategorien · 100% klassifiziert

Skill

Beruf

Beschreibung

Aktualisiert

claude-vision-setup

Softwareentwickler

Interactive setup wizard for claude-vision - configures Docker images and platform settings

Quellsprache: Englisch

2026-02-11

clipboard

Softwareentwickler

Read clipboard contents (text or image) and respond to a prompt about it

Quellsprache: Englisch

2026-02-11

imagesearch

Softwareentwickler

Visual research - search the web, find images, analyze them visually

Quellsprache: Englisch

2026-02-11

screenshot

Softwareentwickler

Read the latest screenshot and respond to a prompt about it

Quellsprache: Englisch

2026-02-11

video

Softwareentwickler

Analyze a video or screen recording by extracting frames and spawning an analysis agent

Quellsprache: Englisch

2026-02-11

Es werden 5 von 5 gesammelten Skills angezeigt.

Mit einem KI-Assistenten installieren

Diesen Prompt kopieren und in den verwendeten KI-Assistenten einfügen.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/ellyseum/claude-vision.