video-trimming — Claude Code skill: cut video with each::sense
A skill that trims and splits video through each::sense AI: timestamp cuts, intro removal, silence cleanup, scene detection.
npx skills add eachlabs/skills --skill video-trimming -a claude-codeWhat video-trimming does
video-trimming ships in the eachlabs/skills collection and turns plain-language requests into video edits. Under the hood the agent calls each::sense AI at https://eachsense-agent.core.eachlabs.run/v1/chat/completions with the eachsense/beta model, passing footage as links in video_urls. The operation list covers duration cuts from the start, extraction between two timestamps, dropping the opening or closing seconds, splitting a long file into parts, pulling highlight moments, cutting silent stretches, and dividing footage where the scene changes.
Social presets are built in: 15, 30 and 60 second lengths, plus loop-friendly edits. Batch runs apply one set of rules across several files, and session continuity keeps context between calls. The skill installs into Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode.
An EACHLABS_API_KEY is required — requests fail without it. Footage has to be reachable by URL, so a local file path will not work in video_urls.
What it helps with
- pull a clip between two timestamps
- strip the intro and end card
- split a long recording into short clips
- fit a video to 15, 30 or 60 seconds
- cut silent gaps out of a podcast recording
Example prompts for the agent
- Trim this video to the first 30 seconds
- Cut the segment from 1:30 to 2:45 and save it as a standalone clip
- Remove every silent stretch longer than two seconds
How to install video-trimming
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-trimming -a claude-code2Manually: put the files in place
~/.claude/skills/video-trimming/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/video-trimming/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-trimming -a codex2Manually: put the files in place
.agents/skills/video-trimming/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-trimming -a cursor2Manually: put the files in place
.cursor/skills/video-trimming/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills video-trimming2Manually: put the files in place
.github/skills/video-trimming/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-trimming -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/video-trimmingManually: put the files in place
.devin/skills/video-trimming/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-trimming -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 video-trimming
How do I install video-trimming in Claude Code?
Run npx skills add eachlabs/skills --skill video-trimming -a claude-code. The skill lands in ~/.claude/skills/video-trimming/SKILL.md.
What does video-trimming do?
It cuts video by timestamp or duration, removes intros, outros and silence, splits footage on scene changes, and runs the same rules over several files.
What do I need before using it?
An EACHLABS_API_KEY and a video URL — calls go to https://eachsense-agent.core.eachlabs.run/v1/chat/completions with the eachsense/beta model.
