About media-toolkit
Media Toolkit is a collection of focused scripts for common audio and video operations. It helps users select a specific operation for a given input and output, while keeping transformations explicit and encouraging checks of relevant output properties.
Key features
- 01Analyze, convert, normalize, and trim audio
- 02Split podcasts and generate sound effects
- 03Caption, clip, and inspect video metadata
- 04Extract thumbnails and create GIFs
- 05Create timelapses and thumbnails
Use cases
- 01Convert or normalize audio files
- 02Trim audio or split podcast recordings
- 03Caption or clip video footage
- 04Extract thumbnails or build a timelapse
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ dkyazzentwatwa/ chatgpt-skills --skill media-toolkitAfter installing, type/media-toolkitin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
agents/openai.yamlscripts/audio_analyzer.pyaudio_converter.pyaudio_normalizer.pyaudio_trimmer.pygif_workshop.pypodcast_splitter.pyrequirements.txtsfx_generator.pythumbnail_gen.pytimelapse_creator.pyvideo_captioner.pyvideo_clipper.pyvideo_metadata_inspector.pyvideo_thumbnail_extractor.pyDetails
From the project READMEMedia Toolkit
Use this suite for practical audio and video operations that were previously spread across many narrow skills.
Included Tools
- Audio:
audio_analyzer.py,audio_converter.py,audio_normalizer.py,audio_trimmer.py,podcast_splitter.py,sfx_generator.py - Video:
video_captioner.py,video_clipper.py,video_metadata_inspector.py,video_thumbnail_extractor.py,gif_workshop.py,thumbnail_gen.py,timelapse_creator.py
Workflow
- Identify the medium, input format, and target output.
- Pick the narrowest script that completes the job.
- Keep transformations explicit: clip times, output codec, target size, caption source, or thumbnail cadence.
- Verify output duration, dimensions, and bitrate-sensitive settings when the request depends on platform limits.
Guardrails
- Avoid recompression churn when a simple trim or extract is enough.
- Call out when generated captions or “best frame” choices are heuristic.
Comments
Markdown supported