Menu
Use when user asks to convert, compress, trim, resize, extract audio, add subtitles, create GIFs, or process video/audio files
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | ffmpeg-skill |
| description | Use when user asks to convert, compress, trim, resize, extract audio, add subtitles, create GIFs, or process video/audio files |
| allowed-tools | Bash(ffmpeg *), Bash(ffprobe *) |
FFmpeg is a universal media converter that reads from multiple inputs, applies filters/transformations, and writes to multiple outputs.
Invoke this skill when the user wants to:
| User Says | Claude Does |
|---|---|
| "Convert video.mkv to mp4" | ffmpeg -i video.mkv output.mp4 |
| "Extract audio from movie.mp4" | ffmpeg -i movie.mp4 -vn audio.mp3 |
| "Compress this video" | ffmpeg -i input.mp4 -crf 23 output.mp4 |
| "Make a GIF from the first 5 seconds" | ffmpeg -t 5 -i input.mp4 -vf "fps=10,scale=320:-1" output.gif |
| "Add subtitles to my video" | ffmpeg -i input.mp4 -vf subtitles=subs.srt output.mp4 |
ffmpeg [global_options] {[input_file_options] -i input_url} ... {[output_file_options] output_url} ...
IMPORTANT: Order matters! Options apply to the next specified file and reset between files.
| Option | Purpose |
|---|---|
-i url | Specify input file |
-c copy | Stream copy (no re-encode, fast) |
-c:v codec | Set video codec (libx264, libx265, libvpx-vp9) |
-c:a codec | Set audio codec (aac, libmp3lame, libopus) |
-vf filter | Apply video filter |
-af filter | Apply audio filter |
-ss time | Seek to position |
-t duration | Limit duration |
-y | Overwrite output |
-vn | No video |
-an | No audio |
ffmpeg -i input.mkv output.mp4
ffmpeg -i input.mp4 -c:v libvpx-vp9 -c:a libopus output.webm
ffmpeg -i video.mp4 -vn -c:a copy audio.aac
ffmpeg -i video.mp4 -vn -c:a libmp3lame -b:a 192k audio.mp3
ffmpeg -i input.mp4 -c:v libx264 -crf 23 -c:a copy output.mp4
ffmpeg -ss 00:01:00 -i input.mp4 -t 00:00:30 -c copy output.mp4
ffmpeg -i input.mp4 -vf scale=1280:720 output.mp4
ffmpeg -i input.mp4 -vf scale=640:-1 output.mp4
ffmpeg -i input.mp4 -vf "fps=10,scale=320:-1" output.gif
ffmpeg -i input.mp4 -vf "drawtext=text='Hello':fontsize=36:fontcolor=white:x=(w-text_w)/2:y=(h-text_h)/2" output.mp4
ffmpeg -i input.mp4 -vf "subtitles=subs.srt" output.mp4
ffmpeg -i input.mp4 -vf fps=1 frame_%04d.png
# 2x speed
ffmpeg -i input.mp4 -filter_complex "[0:v]setpts=0.5*PTS[v];[0:a]atempo=2.0[a]" -map "[v]" -map "[a]" output.mp4
# Create filelist.txt with: file 'part1.mp4' (one per line)
ffmpeg -f concat -safe 0 -i filelist.txt -c copy output.mp4
| Option | Purpose |
|---|---|
-r fps | Set frame rate |
-s WxH | Set resolution |
-crf N | Quality (0-51, lower=better, default 23) |
-b:v bitrate | Set video bitrate |
-preset name | Encoding speed (ultrafast to veryslow) |
| Option | Purpose |
|---|---|
-ar freq | Sample rate (44100, 48000) |
-ac N | Channels (1=mono, 2=stereo) |
-b:a bitrate | Audio bitrate |
| Filter | Example | Purpose |
|---|---|---|
| scale | scale=1280:720 | Resize |
| crop | crop=640:480:100:50 | Crop (w:h:x:y) |
| transpose | transpose=1 | Rotate 90° CW |
| hflip/vflip | hflip | Mirror |
| fade | fade=t=in:d=2 | Fade in/out |
| drawtext | drawtext=text='Hi' | Text overlay |
| subtitles | subtitles=subs.srt | Burn subtitles |
| overlay | overlay=10:10 | Image overlay |
ffprobe input.mp4
ffprobe -v quiet -print_format json -show_format -show_streams input.mp4
-c copy when possible (fast, no quality loss)-ss before -i for fast seeking-y to overwrite without prompts-crf 18-28 for quality controlffprobe firstFor complete reference, see REFERENCE.md, CONCEPTS.md, and ADVANCED.md.
End-to-end QCut CLI workflow for cleaning talking-head and vlog footage, applying restrained portrait filters and skin smoothing, optionally cutting out the speaker and replacing the background, regenerating time-aligned SRT captions after the cuts, and exporting both an editable MP4 plus SRT and a hard-captioned MP4. Use for vlog editing, talking-head cleanup, portrait enhancement, background replacement, 口播剪辑, 剪口播, 去口头词, 去停顿, 人像滤镜, 美颜, 抠像换背景, 自动字幕, 中文字幕, or exporting a captioned social video.
Unified QCut media toolkit — organize project files, process media with FFmpeg, generate AI content, control the QCut editor with native CLI commands, generate video prompts, and test MCP preview. Use when the user asks about any media workflow, file organization, video processing, AI generation, editor control, video prompts, or content pipeline task.
Unified QCut media toolkit — organize project files, process media with FFmpeg, generate AI content, control the QCut editor with native CLI commands, generate video prompts, and test MCP preview. Use when the user asks about any media workflow, file organization, video processing, AI generation, editor control, video prompts, or content pipeline task.
Run QCut's native TypeScript pipeline CLI for AI content generation, video analysis, transcription, YAML pipelines, ViMax agentic video production, and project management. Also use for editor HTTP automation tasks (state snapshots, events, transactions, and notification bridge control) when user needs deterministic state-aware control.
agent-im 会话技能 - 通过 liblib.tv 的 AI 能力生成和编辑图片/视频。覆盖场景包括：生成（文生图、文生视频、图生视频、做动画、画一个xxx、来段xxx）、编辑修改（把xxx换成yyy、去掉xxx、加上xxx、改成xxx、调整xxx、局部修改、改镜头）、风格转换（风格迁移、转绘、换风格）、视频续写延长、复刻视频/TVC/宣传片、短剧/短漫剧生成、音乐MV生成、产品广告/展示片制作、分镜/故事板设计、教育视频/短视频制作。当用户提到 liblib、libtv、上传参考图/视频、查看生成进度时也应触发。关键判断：只要用户的请求涉及 AI 图片或视频的创作、生成、编辑、修改，无论措辞如何（如"画只猫"、"做个海报"、"把纸船换成爱心"、"这个视频帮我改一下"、"帮我复刻这段视频"、"用这首歌做个MV"、"一句话生成短剧"），都必须触发此技能。
Export, preprocess, and fix GitHub PR review comments. Use when user wants to export PR comments, evaluate code reviews, or fix review feedback from CodeRabbit/Gemini/Devin bots.