How do I install the Bookend Trim skill?

Run npx skillmds@latest add jperrello/bookend-trim in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Bookend Trim safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Bookend Trim?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Bookend Trim free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Bookend Trim?

jperrello (@jperrello) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Bookend Trim by jperrello — Agent Skill

Name: Bookend Trim
Author: jperrello

Bookend Trim

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.

jperrello 983d21a 5 files · 11.2 KB Updated Sep 17, 2026

File contents

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 of verify-coherence (or pick-segments)
transcript: full-source transcript (whisper output with segments[])
out: same shape as input, with t0 / t1 adjusted and a bookend_note
extend: 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 ±extend of [t0, t1].
Ask Claude (single batched claude -p call across all spans) to pick a new t0 that starts at a sentence start and a new t1 that 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.

---name: bookend-trimdescription: 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.---# bookend-trimPicked 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 feelslike a complete thought.## Invoke```.claude/skills/bookend-trim/bookend-trim.sh <segments.json> <transcript.json> <out.json> [extend=6.0] [dmin=20]```- `segments`: output of `verify-coherence` (or `pick-segments`)- `transcript`: full-source transcript (whisper output with `segments[]`)- `out`: same shape as input, with `t0` / `t1` adjusted and a `bookend_note`- `extend`: max seconds Claude may push outward in either direction (default 6.0)- `dmin`: min surviving duration; an adjustment that collapses below this is rejected## HowThis project's `transcribe` skill runs whisper.cpp with `--max-len 1--split-on-word`, which strips punctuation. So a pureends-with-`.`/`?`/`!` snap finds nothing and inter-word gaps are alsocollapsed. Instead we delegate to Claude:1. For each span, build a context window: every whisper transcript line (`segments[]`, each ~5s of speech) within `±extend` of `[t0, t1]`.2. Ask Claude (single batched `claude -p` call across all spans) to pick a new `t0` that starts at a sentence start and a new `t1` that lands on a sentence end. New values must be transcript-line boundaries within the window.3. 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. Pairswell with `tighten-pace` downstream, which removes dead air inside there-bookended clip.

Frequently asked questions