Cut filler

Skill jperrello/C0BALT_CUT/.claude/skills/cut-filler

Investigation on using Claude Code to automatically generate profitable YouTube videos.

Install

npx -y skills add jperrello/C0BALT_CUT --skill cut-filler

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Apply a trim-filler keeps.json to a clip's video. Reads the kept time ranges and re-encodes the clip with ffmpeg select/aselect so kept ranges are concatenated and removed spans (filler, trail-offs, digressions) disappear. Output aligns with the trimmed transcript trim-filler wrote, so downstream subtitle / caption / title skills stay in sync.

SKILL.md

1.4 KB, 291 tokens by cl100k_base, as published. Nobody here has run it

cut-filler

Video-side companion to trim-filler. Takes the clip-local keeps.json (a list of [t0, t1] ranges to keep) plus the input clip, and re-encodes a new clip containing only the kept ranges, concatenated in order.

Invoke

.claude/skills/cut-filler/cut-filler.sh <in_clip> <keeps.json> <out_clip>

in_clip — clip-local mp4 (post cut-clip + rebase, pre tighten-pace)
keeps.json — emitted by trim-filler
out_clip — written mp4 with filler ranges removed

How

Builds a single select / aselect filter expression over the keep ranges and re-encodes once with libx264 + AAC. If keeps covers the entire clip (nothing to cut), the input is copied through unchanged.

Idempotent via <out>.cfmeta (clip mtime + keeps mtime).

Pairs with

trim-filler — produces the keeps.json this skill consumes.

Caveats

Always re-encodes (ffmpeg select cannot stream-copy).
The trimmed transcript is written by trim-filler, not by this skill — downstream skills consume it directly.