Edit Decision Generator

Yt edit

by Jakeschincariol · MIT license · ★ 1,136 on GitHub

Turn a raw recording's transcript into an edit decision list - dead air, filler cues and retakes, with timecodes. Use for "edit this", "cut the dead space", "tighten this video", "I rambled", or any request to shorten footage from a…

---
name: yt-edit
description: >-
  Turn a raw recording's transcript into an edit decision list - dead air,
  filler cues and retakes, with timecodes. Use for "edit this", "cut the
  dead space", "tighten this video", "I rambled", or any request to shorten
  footage from a transcript.
---

# yt-edit

An edit decision list from a timestamped transcript. It prints the cuts. You apply them.

```bash
python3 deadair.py transcript.srt              # srt, vtt or whisper json
python3 deadair.py transcript.srt --floor 0.35 --json
```

Overview

An edit decision list from a timestamped transcript. It prints the cuts. You apply them.

Manual install (npx, ZIP)

Claude Codenpx skills add Jakeschincariol/youtube-agent-skill --skill yt-edit -g -a claude-code

Claude Code (degit)npx degit Jakeschincariol/youtube-agent-skill/skills/yt-edit#main ~/.claude/skills/yt-edit

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md1.6 KB

Read SKILL.md here

Jakeschincariol/main1 file shown

SKILL.md1.6 KB

Browse every file on GitHub↗

SKILL.md

Show the full text40 lines

yt-edit/SKILL.md40 lines · 1.6 KB

PreviewCode

Outline

RawView on GitHub

yt-edit

An edit decision list from a timestamped transcript. It prints the cuts. You apply them.

python3 deadair.py transcript.srt              # srt, vtt or whisper json
python3 deadair.py transcript.srt --floor 0.35 --json

No transcript yet? Ask for one, or produce one first - whisper, faster-whisper, or the caption track YouTube generates on an unlisted upload all work. Do not guess at timings.

What it finds

DEAD - gaps longer than the floor, trimmed from the MIDDLE so both sides keep a breath. Cutting flush against speech is what makes a tightened take sound gasping.
FILLER - cues that are nothing but "um", "so yeah", "basically".
REPEAT - a sentence restarted. Compared against the last cue that was actually speech, not the literal previous cue, because most retakes have an "um" between the two attempts.

What it will not do

It does not touch media. It has no opinion about your B-roll. A 40% cut on the report is a 40% cut of SPEECH, and if the video has a long silent demo in it that number is wrong - check the report against the footage before you trust the runtime at the bottom.

The gate

Nothing here publishes. This skill writes and you publish. Every output ends in a block the user copies, and the last line of every run is the question: ship it, or change it?

1	---
2	name: yt-edit
3	description: >-
4	Turn a raw recording's transcript into an edit decision list - dead air,
5	filler cues and retakes, with timecodes. Use for "edit this", "cut the
6	dead space", "tighten this video", "I rambled", or any request to shorten
7	footage from a transcript.
8	---
9
10	# yt-edit
11
12	An edit decision list from a timestamped transcript. It prints the cuts. You apply them.
13
14	```bash
15	python3 deadair.py transcript.srt # srt, vtt or whisper json
16	python3 deadair.py transcript.srt --floor 0.35 --json
17	```
18
19	No transcript yet? Ask for one, or produce one first - `whisper`, `faster-whisper`, or the caption
20	track YouTube generates on an unlisted upload all work. Do not guess at timings.
21
22	## What it finds
23
24	- DEAD - gaps longer than the floor, trimmed from the MIDDLE so both sides keep a breath.
25	Cutting flush against speech is what makes a tightened take sound gasping.
26	- FILLER - cues that are nothing but "um", "so yeah", "basically".
27	- REPEAT - a sentence restarted. Compared against the last cue that was actually speech, not
28	the literal previous cue, because most retakes have an "um" between the two attempts.
29
30	## What it will not do
31
32	It does not touch media. It has no opinion about your B-roll. A 40% cut on the report is a 40% cut
33	of SPEECH, and if the video has a long silent demo in it that number is wrong - check the report
34	against the footage before you trust the runtime at the bottom.
35
36	## The gate
37
38	Nothing here publishes. This skill writes and you publish. Every output ends in a block the user
39	copies, and the last line of every run is the question: ship it, or change it?
40