yt-edit — Claude Code skill: what it does, how to install
yt-edit — a skill for Claude Code that converts video transcripts into an edit decision list. It identifies timestamps for removing dead air, filler words, and retakes.
MIT 1,300 installs ★ 6,796 updated 2026-09-16
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-edit -a claude-codeWhat yt-edit does
This skill parses video transcripts to generate a list of cuts for editing. It identifies gaps exceeding a specific duration, filler cues, and sentence retakes.
It supports srt, vtt, and json formats from Whisper. You need python3 installed to run the underlying deadair.py script. The tool does not touch media files, so verify the report against your footage before finalizing the edit.
If you lack a transcript, generate one first using whisper or faster-whisper. The skill outputs a list of timestamps, and you apply the cuts manually to your project.
What it helps with
- Remove long pauses from raw footage
- Filter out filler words like um
- Identify retakes in recorded speech
- Generate a timestamped edit decision list
Example prompts for the agent
- /skill:yt-edit python3 deadair.py transcript.srt
- /skill:yt-edit python3 deadair.py transcript.srt --floor 0.35 --json
How to install yt-edit
1Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-edit -a claude-code2Manually: put the files in place
~/.claude/skills/yt-edit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/yt-edit/
1Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-edit -a codex2Manually: put the files in place
.agents/skills/yt-edit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-edit -a cursor2Manually: put the files in place
.cursor/skills/yt-edit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Jakeschincariol/youtube-agent-skill skills/yt-edit2Manually: put the files in place
.github/skills/yt-edit/SKILL.md1Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-edit -a gemini-cli2Platform CLI
gemini skills install https://github.com/Jakeschincariol/youtube-agent-skill --path skills/yt-editManually: put the files in place
.devin/skills/yt-edit/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-edit -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about yt-edit
How do I install yt-edit in Claude Code?
Run the command npx skills add Jakeschincariol/youtube-agent-skill --skill yt-edit -a claude-code.
What does yt-edit do?
It analyzes video transcripts to find timestamps for removing dead air, fillers, and retakes.
What do I need to use yt-edit?
You need python3 installed and a transcript file in srt, vtt, or json format.
Source text
SKILL.md · MIT
--- 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 ``` 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?**
© Jakeschincariol · MIT · Jakeschincariol/youtube-agent-skill