video-watermark — Claude Code skill: video watermarks
A skill that stamps logos or text onto video and strips existing watermarks. Runs through each::sense AI over HTTP.
npx skills add eachlabs/skills --skill video-watermark -a claude-codeWhat video-watermark does
Both directions of the job live in one skill: put your mark on a clip, or take someone else's off. A logo goes in with a chosen opacity and corner; text overlays take custom fonts and outlines. Animated marks are covered too, with pulsing or drifting placement. There is also a path for clearing TikTok logos and usernames, plus stock footage marks on material you have licensed.
What ships is a skill definition with worked request examples rather than a script. Calls go to POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions against the eachsense/beta model with streaming on. Video and logo arrive as links in image_urls, and the instruction itself is plain text in messages. Placement options are laid out in a table: bottom right, bottom left, top right, top left, center, and a diagonal across the frame.
An EACHLABS_API_KEY is required, otherwise the request fails. Inputs have to be reachable URLs, so a local file path will not work in image_urls. Batch processing is listed among the capabilities, though the description does not show how it is wired.
What it helps with
- stamp a channel logo into a corner with partial opacity
- lay a copyright line over a finished clip
- strip the TikTok logo and username from a downloaded video
- clear a stock footage mark from licensed material
- put a large diagonal DRAFT label on a preview cut
Example prompts for the agent
- Add
logo.pngas a watermark in the bottom right corner, 40% opacity - Put a text watermark reading "Copyright MyBrand" in the bottom left, white with a black outline
- Remove the watermark from the bottom right corner of this video
How to install video-watermark
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-watermark -a claude-code2Manually: put the files in place
~/.claude/skills/video-watermark/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/video-watermark/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-watermark -a codex2Manually: put the files in place
.agents/skills/video-watermark/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-watermark -a cursor2Manually: put the files in place
.cursor/skills/video-watermark/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills video-watermark2Manually: put the files in place
.github/skills/video-watermark/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-watermark -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/video-watermarkManually: put the files in place
.devin/skills/video-watermark/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-watermark -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-watermark
How do I install video-watermark in Claude Code?
Run npx skills add eachlabs/skills --skill video-watermark -a claude-code. The skill lands at ~/.claude/skills/video-watermark/SKILL.md.
What does video-watermark do?
It adds logo or text watermarks to video with control over opacity and placement, including animated marks, and removes watermarks that are already there.
What do I need before using it?
An EACHLABS_API_KEY and URLs for the video and logo — requests go to https://eachsense-agent.core.eachlabs.run/v1/chat/completions.
