eachlabs-video-generation — Claude Code skill: overview & setup
Creates new videos from text prompts, source images, or motion references via the EachLabs API. Useful when your agent needs to generate animations, speaking avatars, or scene transitions.
npx skills add eachlabs/skills --skill eachlabs-video-generation -a claude-codeWhat eachlabs-video-generation does
This skill lets your agent request video synthesis through the EachLabs Predictions API, which routes tasks across 165+ models. It handles text prompts, image animation, motion transfer, and talking head generation. Available model options include Sora 2, Kling v2.6, Wan v2.6, Pixverse v5.6, and Veo 3.1.
Every generation follows a structured sequence. The agent calls GET /v1/model?slug=<slug> to retrieve input parameters for the chosen model. Next, it sends a payload to POST /v1/prediction with version 0.0.1. The agent polls GET /v1/prediction/{id} until the run finishes, then returns the video link.
Without setting EACHLABS_API_KEY in your environment, calls to https://api.eachlabs.ai will fail immediately. This skill only generates new media; editing existing clips requires eachlabs-video-edit.
What it helps with
- Generate video clips from text descriptions using models like Pixverse or Sora 2
- Animate static images into 1080p video with Wan v2.6 Flash
- Produce talking-head video from an image and audio track via Creatify Aurora or Infinitalk
- Build morphing transitions between two reference frames using Pixverse Transition
Example prompts for the agent
- Generate a 5-second video of a dog running at sunset using
pixverse-v5-6-text-to-videoat 720p - Animate
https://example.com/photo.jpgwithwan-v2-6-image-to-video-flashso the subject turns and smiles - Create a transition between
start.jpgandend.jpgusingpixverse-v5-6-transition
How to install eachlabs-video-generation
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-generation -a claude-code2Manually: put the files in place
~/.claude/skills/eachlabs-video-generation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/eachlabs-video-generation/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-generation -a codex2Manually: put the files in place
.agents/skills/eachlabs-video-generation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-generation -a cursor2Manually: put the files in place
.cursor/skills/eachlabs-video-generation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills eachlabs-video-generation2Manually: put the files in place
.github/skills/eachlabs-video-generation/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-generation -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/eachlabs-video-generationManually: put the files in place
.devin/skills/eachlabs-video-generation/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-video-generation -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-generation
How do I install eachlabs-video-generation in Claude Code?
Run the command npx skills add eachlabs/skills --skill eachlabs-video-generation -a claude-code. The skill file is placed in ~/.claude/skills/eachlabs-video-generation/SKILL.md.
What credentials are required to use this skill?
You need an API key from eachlabs.ai. Export it as the EACHLABS_API_KEY environment variable or provide it in the X-API-Key header.
How does this skill differ from eachlabs-video-edit?
This skill creates new video footage from text, images, or motion references. Post-processing tasks such as video upscaling, lip-syncing existing clips, and subtitles are handled by eachlabs-video-edit.
