Videogrep — guide skill for cuts & pacing
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page.
Search spoken words across videos and auto-build supercuts of every match.
- Type: Guide · Cuts & pacing
- Slug:
videogrep - Status: live
- Publisher: Sam Lavigne (community)
- License: custom (see repo)
- Source: https://github.com/antiboredom/videogrep
- Works in: Claude Code, Codex, Cursor
- Cost: Free/open source (custom license)
- Adoption: 3,465 GitHub stars (GitHub, 2026-10-27)
What it does
A Python CLI and library by Sam Lavigne that transcribes or reads subtitles, searches for words or phrases (including n-grams and regex) and concatenates every match into a supercut. Handy for agents that need to find and pull every moment someone says something.
Use when
- make a supercut of a phrase
- find every mention of a topic in footage
- pull quotes across many videos
Install
- Claude Code:
pip install videogrep
More cuts & pacing skills
- SmartCut (capcut-ai-editor): MCP that reads CapCut auto-captions to cut silences and duplicate takes right inside your CapCut project.
- Auto-Editor: CLI that cuts dead space by loudness or motion and exports MP4 or editor timelines; now also an agent skill.
- AutoCut: Edit video in a text editor: Whisper transcribes, you delete lines in Markdown, AutoCut cuts the video.
- Cut Video: Claude Code skill that tightens long recordings with forced-aligned cuts, keeping laughs and comedic pauses.
- PySceneDetect: Find cuts, fades and scene changes in a video, then split it or export scene lists for the edit.
- video-editing-skill (Bash + FFmpeg): Pure Bash skill for OpenClaw, Claude Code and Codex: trim, jump cut, captions, text overlay, speed.