skills$openclaw/video-agent
michaelwang113948.0k

by michaelwang11394

video-agent – OpenClaw Skill

video-agent is an OpenClaw Skills integration for data analytics workflows. Generate AI avatar videos with HeyGen's Video Agent API. One-shot prompt to video generation.

8.0k stars7.9k forksSecurity L1
Updated Feb 7, 2026Created Feb 7, 2026data analytics

Skill Snapshot

namevideo-agent
descriptionGenerate AI avatar videos with HeyGen's Video Agent API. One-shot prompt to video generation. OpenClaw Skills integration.
ownermichaelwang11394
repositorymichaelwang11394/video-agent
languageMarkdown
licenseMIT
topics
securityL1
installopenclaw add @michaelwang11394/video-agent
last updatedFeb 7, 2026

Maintainer

michaelwang11394

michaelwang11394

Maintains video-agent in the OpenClaw Skills directory.

View GitHub profile
File Explorer
7 files
.
references
prompt-optimizer.md
18.7 KB
scripts
generate.py
4.6 KB
status.py
4.3 KB
_meta.json
284 B
SKILL.md
2.6 KB
SKILL.md

name: video-agent description: Generate AI avatar videos with HeyGen's Video Agent API. One-shot prompt to video generation. homepage: https://docs.heygen.com/reference/generate-video-agent metadata: { "openclaw": { "emoji": "🎬", "requires": { "bins": ["python3"], "env": ["HEYGEN_API_KEY"] }, "primaryEnv": "HEYGEN_API_KEY", }, }

HeyGen Video Agent

Generate videos with a single prompt using HeyGen's Video Agent API. The Video Agent takes your prompt and automatically creates an AI avatar video.

Reference Files

Setup

  1. Get your API key from https://app.heygen.com/settings?nav=API
  2. Set the environment variable:
    export HEYGEN_API_KEY="your-api-key"
    

Generate a Video

python3 {baseDir}/scripts/generate.py --prompt "Create a 30-second explainer video about AI agents"

Options:

  • --prompt: The video generation prompt (required)
  • --poll: Wait for video completion and show URL
  • --out-dir: Output directory for downloaded video (default: ./heygen-output)
  • --download: Download the video when complete (requires --poll)

Examples:

# Quick submit (returns video_id immediately)
python3 {baseDir}/scripts/generate.py --prompt "Introduce our new product feature"

# Wait for completion and get video URL
python3 {baseDir}/scripts/generate.py --prompt "Create a welcome message for new users" --poll

# Wait and download the video
python3 {baseDir}/scripts/generate.py --prompt "Explain how to use the dashboard" --poll --download

Check Video Status

python3 {baseDir}/scripts/status.py --video-id <video_id>

Options:

  • --video-id: The video ID from generate.py (required)
  • --poll: Keep checking until complete
  • --download: Download video when complete
  • --out-dir: Output directory for downloaded video

API Reference

Generate Video:

  • Endpoint: POST https://api.heygen.com/v1/video_agent/generate
  • Auth: x-api-key: <your-api-key>
  • Body: { "prompt": "your video prompt" }
  • Response: { "data": { "video_id": "..." } }

Check Status:

  • Endpoint: GET https://api.heygen.com/v1/video_status.get?video_id=<id>
  • Auth: x-api-key: <your-api-key>
  • Response includes: status (pending, processing, completed, failed), video_url (when complete)

Notes

  • Video generation typically takes 1-5 minutes depending on length
  • The Video Agent automatically selects appropriate avatars and voices based on your prompt
  • For more control over avatar/voice selection, see HeyGen's standard video API
README.md

No README available.

Permissions & Security

Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.

Requirements

  • OpenClaw CLI installed and configured.
  • Language: Markdown
  • License: MIT
  • Topics:

FAQ

How do I install video-agent?

Run openclaw add @michaelwang11394/video-agent in your terminal. This installs video-agent into your OpenClaw Skills catalog.

Does this skill run locally or in the cloud?

OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.

Where can I verify the source code?

The source repository is available at https://github.com/openclaw/skills/tree/main/skills/michaelwang11394/video-agent. Review commits and README documentation before installing.