Bookend trim
Investigation on using Claude Code to automatically generate profitable YouTube videos.
npx -y skills add jperrello/C0BALT_CUT --skill bookend-trimAssembled 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
Snap each picked segment's [t0, t1] to a sentence boundary so shorts begin and end on full thoughts instead of mid-sentence. Claude reads ±extend seconds of context per span and picks clean sentence-completing endpoints from whisper transcript-line boundaries. Runs after verify-coherence, before cut-clip.
SKILL.md
2.0 KB, as published. Nobody here has run it
bookend-trim
Picked segments tend to begin or end mid-sentence because pick-segments and
verify-coherence choose by topic, not prosody. This skill nudges each span's
[t0, t1] to the nearest clean sentence boundary so the resulting short feels
like a complete thought.
Invoke
.claude/skills/bookend-trim/bookend-trim.sh <segments.json> <transcript.json> <out.json> [extend=6.0] [dmin=20]
segments: output ofverify-coherence(orpick-segments)transcript: full-source transcript (whisper output withsegments[])out: same shape as input, witht0/t1adjusted and abookend_noteextend: max seconds Claude may push outward in either direction (default 6.0)dmin: min surviving duration; an adjustment that collapses below this is rejected
How
This project's transcribe skill runs whisper.cpp with --max-len 1 --split-on-word, which strips punctuation. So a pure
ends-with-./?/! snap finds nothing and inter-word gaps are also
collapsed. Instead we delegate to Claude:
- For each span, build a context window: every whisper transcript line
(
segments[], each ~5s of speech) within±extendof[t0, t1]. - Ask Claude (single batched
claude -pcall across all spans) to pick a newt0that starts at a sentence start and a newt1that lands on a sentence end. New values must be transcript-line boundaries within the window. - Cache on input mtimes; out-of-window or too-short adjustments are
rejected and the original
[t0, t1]is kept.
Per-span bookend_note records Δt0 / Δt1 and Claude's reason. Pairs
well with tighten-pace downstream, which removes dead air inside the
re-bookended clip.