donson-intelligent-editingUse when performing video/audio processing tasks including transcoding, filtering, streaming, metadata manipulation, or complex filtergraph operations with FFmpeg.
Install via ClawdBot CLI:
clawdbot install DonsonAICenter/donson-intelligent-editingComprehensive guide for professional video and audio manipulation using FFmpeg and FFprobe.
FFmpeg is the leading multimedia framework, able to decode, encode, transcode, mux, demux, stream, filter and play almost anything that humans and machines have created. It is a command-line tool that processes streams through a complex pipeline of demuxers, decoders, filters, encoders, and muxers.
# Basic Transcoding (MP4 to MKV)
ffmpeg -i input.mp4 output.mkv
# Change Video Codec (to H.265/HEVC)
ffmpeg -i input.mp4 -c:v libx265 -crf 28 -c:a copy output.mp4
# Extract Audio (No Video)
ffmpeg -i input.mp4 -vn -c:a libmp3lame -q:a 2 output.mp3
# Resize/Scale Video
ffmpeg -i input.mp4 -vf "scale=1280:720" output.mp4
# Cut Video (Start at 10s, Duration 30s)
ffmpeg -i input.mp4 -ss 00:00:10 -t 00:00:30 -c copy output.mp4
# Fast Precise Cut (Re-encoding only the cut points is complex, so standard re-encoding is safer for precision)
ffmpeg -ss 00:00:10 -i input.mp4 -to 00:00:40 -c:v libx264 -crf 23 -c:a aac output.mp4
# Concatenate Files (using demuxer)
# Create filelist.txt: file 'part1.mp4' \n file 'part2.mp4'
ffmpeg -f concat -safe 0 -i filelist.txt -c copy output.mp4
# Speed Up/Slow Down Video (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
| Option | Use When |
|-----------|----------|
| -c:v libx264 | Standard H.264 encoding (best compatibility) |
| -c:v libx265 | H.265/HEVC encoding (best compression/quality) |
| -crf [0-51] | Constant Rate Factor (lower is higher quality, 18-28 recommended) |
| -preset | Encoding speed vs compression (ultrafast, medium, veryslow) |
| -c:a copy | Pass-through audio without re-encoding (saves time/quality) |
| Filter | Use When |
|-----------|----------|
| scale | Changing resolution (e.g., scale=1920:-1 for 1080p width) |
| crop | Removing edges (e.g., crop=w:h:x:y) |
| transpose | Rotating video (1=90deg CW, 2=90deg CCW) |
| fps | Changing frame rate (e.g., fps=30) |
| drawtext | Adding text overlays/watermarks |
| overlay | Picture-in-picture or adding image watermarks |
| fade | Adding fade-in/out effects (e.g., fade=in:0:30 for first 30 frames) |
| volume | Adjusting audio levels (e.g., volume=1.5 for 150% volume) |
| setpts | Changing video speed (e.g., setpts=0.5*PTS for double speed) |
| atempo | Changing audio speed without pitch shift (0.5 to 2.0) |
| Tool/Option | Use When |
|-----------|----------|
| ffprobe -v error -show_format -show_streams | Getting detailed technical info of a file |
| -metadata title="Name" | Setting global metadata tags |
| -map | Selecting specific streams (e.g., -map 0:v:0 -map 0:a:1) |
Use filter_complex when you need to process multiple inputs or create non-linear filter chains.
# Example: Adding a watermark at the bottom right
ffmpeg -i input.mp4 -i watermark.png -filter_complex "overlay=main_w-overlay_w-10:main_h-overlay_h-10" output.mp4
# Example: Vertical Stack (2 videos)
ffmpeg -i top.mp4 -i bottom.mp4 -filter_complex "vstack=inputs=2" output.mp4
# Example: Side-by-Side (2 videos)
ffmpeg -i left.mp4 -i right.mp4 -filter_complex "hstack=inputs=2" output.mp4
# Example: Grid (4 videos 2x2)
ffmpeg -i v1.mp4 -i v2.mp4 -i v3.mp4 -i v4.mp4 -filter_complex "[0:v][1:v]hstack=inputs=2[top];[2:v][3:v]hstack=inputs=2[bottom];[top][bottom]vstack=inputs=2" output.mp4
# Example: Fade Transition (Simple crossfade between two clips)
# Requires manual offset calculation, using xfade is better
ffmpeg -i input1.mp4 -i input2.mp4 -filter_complex "xfade=transition=fade:duration=1:offset=9" output.mp4
Standard conversion often results in poor colors. Use a palette for best results:
ffmpeg -i input.mp4 -vf "fps=15,scale=480:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse" output.gif
Mix background music at 30% volume with the main audio:
ffmpeg -i voice.mp4 -i bgm.mp3 -filter_complex "[1:a]volume=0.3[bg];[0:a][bg]amix=inputs=2:duration=first" -c:v copy output.mp4
Two-pass process to fix shaky footage:
# Pass 1: Analyze
ffmpeg -i shaky.mp4 -vf vidstabdetect -f null -
# Pass 2: Transform
ffmpeg -i shaky.mp4 -vf vidstabtransform,unsharp=5:5:0.8:3:3:0.4 output.mp4
Adjust brightness, contrast, and saturation:
# brightness=0.05, contrast=1.1, saturation=1.2
ffmpeg -i input.mp4 -vf "eq=brightness=0.05:contrast=1.1:saturation=1.2" output.mp4
Create a 3x3 grid of frames:
ffmpeg -i input.mp4 -vf "select='not(mod(n,100))',scale=320:-1,tile=3x3" -frames:v 1 preview.png
Automatically cut silent parts from the beginning and end:
ffmpeg -i input.mp4 -af silenceremove=start_periods=1:start_silence=0.1:start_threshold=-50dB:stop_periods=1:stop_silence=0.1:stop_threshold=-50dB output.mp4
| Platform | Codec | Command |
|----------|-------|---------|
| NVIDIA (NVENC) | H.264 | -c:v h264_nvenc |
| Intel (QSV) | H.264 | -c:v h264_qsv |
| Apple (VideoToolbox) | H.265 | -c:v hevc_videotoolbox |
-map for complex files to ensure you get the right audio/subtitle tracks.-ss before -i for fast seeking (input seeking), or after -i for accurate seeking (output seeking).Generated Mar 1, 2026
Content creators and marketers use this skill to transcode, resize, and add watermarks to videos for platforms like YouTube and Instagram. It enables efficient batch processing of clips, such as converting to H.265 for smaller file sizes and applying filters like fade effects to enhance engagement.
Video editors and production studios leverage advanced filtergraphs for tasks like color correction, stabilization, and complex overlays. This includes creating high-quality GIFs, mixing audio tracks, and generating thumbnail sheets for client previews, streamlining workflows in film and advertising.
Educational institutions and e-learning platforms use this skill to cut, concatenate, and transcode lecture videos. It supports operations like removing silence from audio, adjusting playback speed for subtitles, and adding text overlays for clarity, enhancing accessibility and learning outcomes.
Broadcasters and streaming services apply hardware acceleration for real-time transcoding to formats like H.264, ensuring low-latency delivery. They use metadata manipulation and quality adjustments to optimize streams for various devices, improving viewer experience in live events and on-demand content.
Libraries, museums, and media archives utilize this skill to convert legacy formats to modern codecs like H.265 for long-term storage. It includes metadata extraction with FFprobe, stabilization of old footage, and batch processing to maintain quality while reducing file sizes for digital preservation.
Offer specialized editing services such as color correction, stabilization, and custom filtergraph creation for clients in marketing or entertainment. Charge per project or hourly, with upselling for complex tasks like GIF creation or audio mixing to increase revenue.
Develop a cloud-based service that automates common FFmpeg tasks like transcoding, resizing, and watermarking via an API. Target businesses needing bulk processing, with subscription tiers based on usage volume and advanced features like hardware acceleration support.
Provide workshops, online courses, or one-on-one consulting to teach advanced FFmpeg techniques, such as complex filtergraphs and hardware optimization. Cater to industries like broadcasting or education, with revenue from course sales and certification programs.
💬 Integration Tip
Integrate this skill into existing workflows by using shell scripts or APIs to automate repetitive tasks, and ensure compatibility with hardware acceleration for faster processing on supported platforms.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.