Open-source · agentskills.io · MIT
Give your agents media superpowers
14 portable skills, 97+ deterministic operations, and end-to-end cookbooks for video, audio, captions, timecode, and broadcast workflows.
What do you want to do?
Jump straight to common agent tasks — or press / to search everything.
Skills by category
Each skill ships with SKILL.md routing, recipes, and JSON-scripted operations for agents.
install-media-tools
Detect, verify, and install media processing binaries (ffmpeg, ImageMagick, exiftool, tesseract, yt-dlp, uv) on macOS and Linux. Use before other mediaskills when doctor reports missing tools, when ffprobe/ffmpeg is not found, or when setting up a fresh dev machine or CI runner.
4 recipesinspect
Probe, describe, compare, and batch-inspect video, audio, and image files using ffprobe. Use when you need metadata (duration, resolution, codecs, size), want to compare two files before/after processing, or need structured probe data to answer questions about a media file without modifying it.
5 recipesaudio
Extract, convert, trim, concatenate, normalize, fade, resample, and silence-detect audio using ffmpeg. Use when you need to modify audio tracks, change format or sample rate, edit timeline segments, or prepare audio for muxing back onto video.
5 recipesimage
Convert, resize, crop, rotate, flip, optimize, read EXIF, strip metadata, and OCR images using ImageMagick, exiftool, and Tesseract. Use when you need to transform still images, reduce file size, inspect camera metadata, remove sensitive EXIF before sharing, or extract text from screenshots and scans.
9 recipesprogram-master
TV program segmentation — detect fade-aware black+silent break separators, preserve frame-accurate fade anchors, label content segments, and generate validated thumbnail-led broadcast segment PDF reports. Use when finding commercial breaks, naming episodes/parts, mapping broadcast master structure, or delivering a visual segment report — not hard cuts inside content.
shots
Detect hard cuts (shot boundaries) in video via ffmpeg scene detection and extract midpoint stills per shot. Use when the unit of analysis is a shot — cataloging cuts, QC, or feeding shot-level frames to vision/OCR — not TV program structure or commercial breaks.
3 recipesEnd-to-end cookbooks
Multi-skill workflows with command sequences agents can chain — probe first, transform second.
Broadcast captions package
Speech to SRT, compliance pass, export SCC/SMPTE-TT.
`speech-captions` → `captions-compliance` → (`subtitles` for burn-in if needed)
Deliver H.264 + AAC MP4
Probe first, then transcode for delivery.
`inspect` → `video-transformation` → `inspect`
Exact forced-narrative inventory
Produce an exhaustive, frame-accurate burned-in dialogue report with exclusive-end SMPTE boundaries.
`inspect` → `program-master` → `forced-narrative-exact`
Install in one command
Pin a version for reproducible agent environments. Start with install-media-tools and doctor.sh.
npx skills add timelapsetech/[email protected] --skill inspect