Create AI avatar videos with full control over avatars, voices, scripts, and backgrounds using POST /v3/videos. Two creation modes via discriminated union on type:
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionavatar-videoExecute the skills CLI command in your project's root directory to begin installation:
Fetches avatar-video from heygen-com/skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate avatar-video. Access via /avatar-video in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
103
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
103
stars
Create AI avatar videos with full control over avatars, voices, scripts, and backgrounds using POST /v3/videos. Two creation modes via discriminated union on type:
"type": "avatar" + avatar_id — use a HeyGen avatar from the library"type": "image" + image (AssetInput) — animate any photo via Avatar IVAll requests require the X-Api-Key header. Set the HEYGEN_API_KEY environment variable.
curl -X GET "https://api.heygen.com/v3/avatars" \
-H "X-Api-Key: $HEYGEN_API_KEY"
If HeyGen MCP tools are available (mcp__heygen__*), prefer them over direct HTTP API calls — they handle authentication and request formatting automatically.
| Task | MCP Tool | Fallback (Direct API) |
|---|---|---|
| Check video status / get URL | mcp__heygen__get_video |
GET /v3/videos/{video_id} |
| List account videos | mcp__heygen__list_videos |
GET /v3/videos |
| Delete a video | mcp__heygen__delete_video |
DELETE /v3/videos/{video_id} |
Video generation (POST /v3/videos) and avatar/voice listing are done via direct API calls — see reference files below.
GET /v3/avatars/looks → pick a look, note its id (this is the avatar_id) and default_voice_id. See avatars.mdGET /v3/voices → pick a voice matching the avatar's gender/language. See voices.mdPOST /v3/videos with avatar_id, voice_id, script, and optional background per scene. See video-generation.mdGET /v3/videos/{video_id} until status is completed. See video-status.mdThis skill = precise control (specific avatar, exact script, custom background). create-video = prompt-based ("make me a video about X", AI handles the rest).
Read these as needed — they contain endpoint details, request/response schemas, and code examples (curl, TypeScript, Python).
Core workflow:
POST /v3/videos request fields, avatar input modes, voice settings, backgroundsGET /v3/avatars (groups) and GET /v3/avatars/looks (looks → avatar_id)GET /v3/voices with filtering by language, gender, engineGET /v3/videos/{id} polling patterns and downloadCustomization:
Advanced:
type: "image" (Avatar IV), AI-generated avatarsGET /v3/avatars/looks and download preview_image_url so the user can see the avatar before committingdefault_voice_id pre-matched for natural resultstest: true to avoid consuming credits (output will be watermarked)Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
heygen-com/skills
affaan-m/everything-claude-code
remotion-dev/skills
supercent-io/skills-template
davila7/claude-code-templates
zrong/skills
We added avatar-video from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Useful defaults in avatar-video — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
avatar-video reduced setup friction for our internal harness; good balance of opinion and flexibility.
Solid pick for teams standardizing on skills: avatar-video is focused, and the summary matches what you get after install.
Registry listing for avatar-video matched our evaluation — installs cleanly and behaves as described in the markdown.
Keeps context tight: avatar-video is the kind of skill you can hand to a new teammate without a long onboarding doc.
Registry listing for avatar-video matched our evaluation — installs cleanly and behaves as described in the markdown.
avatar-video has been reliable in day-to-day use. Documentation quality is above average for community skills.
I recommend avatar-video for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Useful defaults in avatar-video — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
showing 1-10 of 53