View Video — Development skill for Claude Code
Extract frames from a video using ffmpeg so Claude can visually analyze the content.
How to install View Video
Installs to ~/.claude/skills/zalogarcia-zalo-claude-code-setup-view-video/SKILL.md
mkdir -p ~/.claude/skills/zalogarcia-zalo-claude-code-setup-view-video && curl -fsSL https://raw.githubusercontent.com/zalogarcia/zalo-claude-code-setup/HEAD/commands/view-video.md -o ~/.claude/skills/zalogarcia-zalo-claude-code-setup-view-video/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What View Video does
Extract frames from a video using ffmpeg so Claude can visually analyze the content.
Usage
Provide the local video file path and optionally the number of frames:
/view-video /path/to/video.mp4
/view-video /path/to/video.mp4 10
Instructions
- First, get video metadata using ffprobe:
ffprobe -v quiet -print_format json -show_format -show_streams "$VIDEO_PATH"
Report: duration, resolution, codec, fps, and file size.
- Extract frames to a temp directory. Default is 6
Alternatives in Development
- Generic Extract Skill — You are an Autonomous 3D Technical Artist Agent 14.1k ★
- Setup Video Vision — Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies 1.3k ★
- Video Comparer — Compare video files and content 653 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Mindmap Knowledge
Watch the video frames and listen to the audio. When concepts are shown visually (slides, diagrams, code, demo
Mindmap Light
Watch the video frames and listen to the audio. When concepts are shown visually (slides, diagrams, code, demo
Yt.Analyze
Analyze video content to extract keywords, audience insights, and competitive research
Asset Map
Scan, filter, and position images from the PDF outline into chapter locations for epub/docx export. Visually a
Xhs To Claude
A Claude Code skill: paste a Xiaohongshu / Bilibili share link → Claude gets local title, cover, video frames,
03 Produce Zoom
Apply dynamic zoom sections from JSON to a video using face detection and ffmpeg cropping
Related Agents
Broll Worker
Cheap, narrow B-roll worker. Executes specific footage tasks from a B-roll GOD plan (stock video, images, clip
Frame Describer
Describes video frames as detailed text. Used when frame_mode is "descriptions" to convert visual frames into
Slide Reader
Read on-screen text (slides, signage, handwriting, app screens) out of video frames at full resolution and ret