What steps does it go through?

It inspects the video, gets a transcript, removes silences, reviews speech mistakes, plans the motion graphics, builds them in HyperFrames and renders a draft before the final.

Does it upload my video to a service?

It may use a transcription service depending on the provider you pick. Before calling any service that is not yet authorized, it explains the uploads and costs.

Do I need to review anything by hand?

Yes. Cut proposals are automated but editorial judgment is still needed, and the draft is reviewed before the final render.

By nateherkaiUpdated 25 Sept 2026

Full talking-head video edit

/edit-video

/edit-video is a Claude Code skill in the Video & Motion section. It is maintained by nateherkai and published under the MIT license. Edits a raw talking-head recording end to end: transcription, silence and mistake cuts, motion graphics and a verified HyperFrames render.

Author's description

Edit a raw talking-head video through transcription, silence trimming, mistake review, visual storytelling, motion graphics, and verified HyperFrames rendering. Use for a complete edit; route a single requested operation directly to its specialist skill.

Use it when

You have a raw talking-head recording and want the finished edited video
You want transcription, cuts and graphics chained into one workflow
You need a reviewed render with a record of what was checked

Not for

A single standalone operation, such as only removing silences: go straight to the specialist skill for that
Replacing editorial judgment: a detector proposes cuts and someone still has to decide

What you get

The path to the final MP4, the edit decisions, the re-timed transcript, the HyperFrames composition and a VERIFY.md listing what was checked and any remaining limitations.

How to ask for it

Edit this raw talking-head video and get it ready to publish
Trim the silences and mistakes from this video and do the full edit
I need a complete edit of my talking-head video, including motion graphics

Install

curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash

After installing with the script, type /edit-video. Using Cursor, Windsurf or Codex? Platform guides

Questions about this skill

What steps does it go through?: It inspects the video, gets a transcript, removes silences, reviews speech mistakes, plans the motion graphics, builds them in HyperFrames and renders a draft before the final.
Does it upload my video to a service?: It may use a transcription service depending on the provider you pick. Before calling any service that is not yet authorized, it explains the uploads and costs.
Do I need to review anything by hand?: Yes. Cut proposals are automated but editorial judgment is still needed, and the draft is reviewed before the final render.

Demo coming soon