
Liveavatar Integrate
If you're wiring up HeyGen's LiveAvatar API, this skill figures out what you already have (your LLM, your TTS pipeline, static site, whatever) and picks the integration path for you. No menu of options. It scans your codebase for signals like OpenAI imports or ElevenLabs SDKs, asks only what's missing, then routes you to Embed, FULL Mode, or LITE Mode with specific implementation steps. The LITE Mode guidance is especially practical: it tells you to hook into your existing turn cycle instead of rebuilding everything. Treats backend/frontend separation and API key handling as non-negotiable, which is correct. Built by HeyGen, so the pathway logic and gotchas come from people who actually support these integrations.
- skills.sh installs
- 1.2K
- GitHub stars
- 16
- last updated
- Aug 21, 2026
Install
$ npx -y skills add heygen-com/liveavatar-agent-skills --skill liveavatar-integrate --agent claude-codeInstalls into .claude/skills of the current project.
Files
LiveAvatar Integration
LiveAvatar gives your product a human face — real-time, lip-synced video avatars that speak, react, and maintain eye contact. This skill assesses what you have, recommends the best integration path, and walks you through building it.
Step 1: Discover What the User Has
Before recommending a path, gather context. Check the codebase and conversation for signals. Do not ask questions the codebase already answers.
Signals to look for in the codebase
Scan for these automatically — do not ask the user if you can detect them:
Sponsors
Details
- Repository
- github.com/heygen-com/liveavatar-agent-skills
- Categories
- DevOps & CI/CD, AI & Agent Building, Automation & Workflows, Sales & Marketing, Generative Media
- First seen
- Jun 3, 2026