video-noise-reduction — Claude Code skill
video-noise-reduction strips noise and grain from video through each::sense: dim footage, high ISO, security cams, old tapes. Runs over the API with an EACHLABS_API_KEY.
no license 233 installs ★ 48 updated 2026-10-07
npx skills add eachlabs/skills --skill video-noise-reduction -a claude-codeWhat video-noise-reduction does
The skill hands a video link to the each::sense agent along with a plain-language note on what should be cleaned up. Model eachsense/beta, streamed response, max mode. You steer it by wording: how hard to suppress noise, how much texture to keep, frame-to-frame stability, separate chroma cleanup.
Everything goes to https://eachsense-agent.core.eachlabs.run/v1/chat/completions with an X-API-Key header. No EACHLABS_API_KEY in the environment means the call fails, so export the key before the first run. Clips travel as links in video_urls.
Worth reaching for on night footage, high-ISO recordings or heavily compressed files. Push strength too far and fine texture vanishes, so name the faces and edges you want kept.
What it helps with
- clean grain from night footage without smearing faces
- strip luminance and colour noise from high-ISO clips
- make plates and faces legible on security camera recordings
- remove blocking and ringing from over-compressed video
- take film grain off a scanned reel
Example prompts for the agent
- Denoise
night.mp4and keep the faces sharp while the grain goes away. - Clean up
cam-01.mp4from the security camera so plates and faces read better. - Restore
vhs.mov— kill the tape noise and colour bleed but keep it looking natural.
How to install video-noise-reduction
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-noise-reduction -a claude-code2Manually: put the files in place
~/.claude/skills/video-noise-reduction/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/video-noise-reduction/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-noise-reduction -a codex2Manually: put the files in place
.agents/skills/video-noise-reduction/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-noise-reduction -a cursor2Manually: put the files in place
.cursor/skills/video-noise-reduction/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills skills/video-noise-reduction2Manually: put the files in place
.github/skills/video-noise-reduction/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-noise-reduction -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/video-noise-reductionManually: put the files in place
.devin/skills/video-noise-reduction/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill video-noise-reduction -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-noise-reduction
How do I install video-noise-reduction in Claude Code?
Run npx skills add eachlabs/skills --skill video-noise-reduction -a claude-code. The skill lands at ~/.claude/skills/video-noise-reduction/SKILL.md.
What does video-noise-reduction do?
It clears noise, grain and compression artifacts from video through each::sense while holding on to detail. Built for dim shoots, high-ISO recordings and old tapes.
What do I need before running it?
An EACHLABS_API_KEY exported in your environment, since calls hit https://eachsense-agent.core.eachlabs.run/v1/chat/completions with an X-API-Key header. The clip itself goes in as a link in video_urls.