eachlabs-video-edit — Claude Code skill: what it does, how to install
Routes video editing, upscaling, lip sync, and extension tasks to 25+ AI models through the EachLabs Predictions API.
npx skills add eachlabs/skills --skill eachlabs-video-edit -a claude-codeWhat eachlabs-video-edit does
The skill provides an AI coding assistant with instructions to work with the EachLabs Predictions API. Before dispatching any workload, the agent calls GET https://api.eachlabs.ai/v1/model?slug=<slug> to inspect the expected input schema. It then initiates the prediction via POST with version 0.0.1 and polls the job ID until it finishes.
The catalog includes more than 25 specialized engines. Available workflows cover video extension with Veo 3.1 or PixVerse, lip synchronization through Sync Lipsync v2 Pro, upscaling with Topaz, style transfer, face swapping, and automatic subtitle generation.
All API calls fail without a valid token stored in the EACHLABS_API_KEY environment variable.
What it helps with
- extend existing footage using Veo 3.1
- synchronize talking-head lip movement with a fresh audio track
- upscale low-resolution clips via Topaz
- generate and burn subtitles onto a video file
Example prompts for the agent
- Extend my clip using Veo 3.1 with a prompt to slowly pull the camera back.
- Apply lip sync to this speaker video with a new audio file using
sync-lipsync-v2-pro. - Upscale the video to higher resolution using
topaz-upscale-video.
How to install eachlabs-video-edit
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-edit -a claude-code2Manually: put the files in place
~/.claude/skills/eachlabs-video-edit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/eachlabs-video-edit/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-edit -a codex2Manually: put the files in place
.agents/skills/eachlabs-video-edit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-edit -a cursor2Manually: put the files in place
.cursor/skills/eachlabs-video-edit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills eachlabs-video-edit2Manually: put the files in place
.github/skills/eachlabs-video-edit/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-edit -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/eachlabs-video-editManually: put the files in place
.devin/skills/eachlabs-video-edit/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-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 eachlabs-video-edit
How to install eachlabs-video-edit in Claude Code?
Run npx skills add eachlabs/skills --skill eachlabs-video-edit -a claude-code. Alternatively, place the specification file into ~/.claude/skills/eachlabs-video-edit/SKILL.md.
What credentials does eachlabs-video-edit require?
You must obtain an API key from eachlabs.ai and export it as EACHLABS_API_KEY. The agent uses it to populate the X-API-Key header on every request.
How does eachlabs-video-edit process video jobs?
The assistant inspects the model schema first, posts inputs to https://api.eachlabs.ai/v1/prediction, and repeatedly polls the task endpoint until the output URL is ready.
