HeyGen Skills
Three HeyGen skills: an avatar from a photo, a video with that avatar on screen from a brief, and translation of finished videos with dubbing and lip-sync
- 525 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent creates videos in the HeyGen cloud by API key or OAuth, spending the API plan or plan credits
- Photos and texts from your tasks go to HeyGen to create the avatar and videos, and clips are shared by link
- The heygen CLI installs from a ready script off the internet, and the API key lives in the environment or ~/.heygen/credentials
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/heygen-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent creates videos in the HeyGen cloud by API key or OAuth, spending the API plan or plan credits
- Photos and texts from your tasks go to HeyGen to create the avatar and videos, and clips are shared by link
- The heygen CLI installs from a ready script off the internet, and the API key lives in the environment or ~/.heygen/credentials
This is third-party code. Review the repository files before installing.
What it does
HeyGen Skills are official HeyGen skills that let an agent make avatar videos. The authors' idea is that the agent gets a face and a voice and can send video like a message. The three skills work on their own or chained. heygen-avatar creates a persistent digital twin with a voice from a photo and saves it to an AVATAR-NAME.md file for later videos. heygen-video turns an idea into a script and a finished video: the agent picks the avatar, voice and style, corrects the frame aspect ratio and returns a video link plus a HeyGen session URL for tweaks. The README mentions 20 curated styles, for example A24-like, editorial and clean tech. heygen-translate translates a finished video with voice cloning and lip-sync into 175-plus languages. The skills run through the heygen CLI with an API key or through HeyGen's remote MCP server over OAuth. If HEYGEN_API_KEY is set, the CLI wins; without a key the skills look for MCP tools.
Who it is for. For marketers, founders and teams who want video messages, explainers and localized videos without studio shooting, and for agent builders.
Good fit when
- You need a video message to a client or investor in an avatar's voice: the agent drafts a script, you approve it, it generates the clip
- An article or PDF should become a one-minute video explainer with a presenter
- You have a finished video to translate and dub into another language with lip-sync
- The team wants a regular video update: the agent first asks what shipped this week, then builds the clip
- You want a digital twin from your own photo to reuse in every video
Not a fit when
- You need cinematic footage or b-roll without a presenter: heygen-video is built for a talking person on screen
- You only want text-to-speech with no video: voice-service skills fit better
- You need a live streaming avatar: heygen-video explicitly excludes it
- You have no HeyGen account: without an API key or OAuth sign-in the skills do not work
Example request
Use heygen-avatar and heygen-video: create my avatar from this photo and a 30-second video where I introduce our product. Ask me what you need before you startLimitations
You need a HeyGen account. In CLI mode with HEYGEN_API_KEY, usage is billed on the API plan separately; in MCP mode over OAuth it consumes your plan credits. Priority is the API key, then MCP, then a heygen auth login session.
The heygen CLI installs with a script from static.heygen.ai and targets macOS and Linux. The photo for the avatar goes to HeyGen. The only script in the set, update-check.sh, compares versions and runs only when you start it.
How to disable. Delete the heygen-avatar, heygen-video and heygen-translate folders from the agent's skills directory, for example ~/.claude/skills/heygen-skills. For MCP, remove the heygen server from the agent settings, take HEYGEN_API_KEY out of your shell profile and revoke it at app.heygen.com/api.
FAQ
How do I install the HeyGen skills in Claude Code?
The easiest way is to ask the agent to read INSTALL_FOR_AGENTS.md from the repository: it clones the skills, asks for a key and runs a check. By hand: gh skill install heygen-com/skills heygen-avatar (then heygen-video and heygen-translate), which needs GitHub CLI 2.90 or newer. Or git clone into ~/.claude/skills/heygen-skills.
Do I need an API key to use the HeyGen skills?
No. With HEYGEN_API_KEY the heygen CLI is used and usage is billed on the API plan. Without a key the skills use HeyGen's remote MCP over OAuth and spend your plan credits. Connect it with claude mcp add --transport http heygen https://mcp.heygen.com/mcp/v1/.
What does heygen-translate do?
It translates and dubs a finished video with voice cloning and lip-sync. The README names more than 175 languages. The repository includes a locale guide and a description of the translation proofreading flow.
Where is the created avatar stored?
heygen-avatar creates the digital twin in HeyGen and writes an AVATAR-NAME.md file to the working folder. heygen-video reads it, so the avatar is picked up automatically in every later video.
What happened to the old HeyGen skills for TTS and face swap?
The first-generation skills live in a separate repository, heygen-com/skills-legacy. The current one keeps three skills built on the version 3 Video Agent pipeline.
Discussion
No questions or reviews yet.
Related
SkillsA skill that turns an idea, a link or a screen recording into finished video: HeyGen avatar, b-roll, captions and quality checks
Motion Video Skill
motion-video-skill
1080p beat-synced video: HyperFrames and GSAP, voice-over, karaoke captions, sound effects and music. Provider keys are kept in the CLI configuration
A skill for Cursor, Claude Code and Codex: from a product name or URL it builds a 4K promo with music, voice-over and checks
Two skills for generative video and images: video writes Seedance, Kling and Veo prompts by dramaturgy rules, image picks the model and its syntax
Skills and CLI from HeyGen: the agent writes HTML compositions and renders them into MP4 videos, captions, motion graphics and decks
A skill that writes prompts for video, image and music generation on 14 platforms and can submit them in the browser
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| HeyGen Skills (this entry) | yes | 525 | |
| HyperFrames | no | 75,530 | also from HeyGen: the agent writes video as HTML compositions rendered to MP4 |
| video-use | no | 30,108 | edits footage you already have: cuts pauses, adds subtitles and color grading |
| SpicyAPI Skill | yes | 3 | the official SpicyAPI skill |
README in short
The README goes from install to a first video: a paste-in request for the agent, manual routes (gh skill install, ClawHub, the OpenClaw plugin, git clone), getting an API key, installing the CLI and the remote MCP alternative. It then describes the three skills and how the avatar file links them, the auth modes with their priority and billing, example prompts, requirements and a security section.
README badge
Original SKILL.md
---
version: 3.2.0 # x-release-please-version
name: heygen-video
description: |
Generate HeyGen presenter videos via the v3 Video Agent pipeline — handles Frame Check
(aspect ratio correction), prompt engineering, avatar resolution, and voice selection.
Required for any HeyGen video generation. Replaces deprecated endpoints with v3.
Use when: (1) generating any HeyGen video (via API or otherwise),
(2) sending a personalized video message (outreach, update, announcement, pitch, knowledge),
(3) creating a HeyGen presenter-led explainer, tutorial, or product demo with a human face,
(4) "make a video of me saying...", "send a video to my leads", "record an update for my team",
"create a video pitch", "make a loom-style message", "I want to appear in this video",
"generate a HeyGen video", "make a talking head video".
Accepts avatar_id from heygen-avatar for identity-first HeyGen videos, or uses a stock presenter.
Returns video share URL + HeyGen session URL for iteration.
Chain signal: when the user wants to create/design an avatar AND make a video in the same request,
run heygen-avatar first, then return here. Conjunctions to watch: "and then", "and immediately",
"first...then", "X and make a video", "design [presenter] and record" = always CHAIN.
If the user provides a photo AND wants a video, route to heygen-avatar first.
NOT for: avatar creation or identity setup (use heygen-avatar first), cinematic footage
or b-roll without a presenter, translating videos, TTS-only, or streaming avatars.
argument-hint: "[topic_or_script] [--avatar avatar_id]"
homepage: https://developers.heygen.com/docs/quick-start
allowed-tools: Bash, WebFetch, Read, Write, mcp__heygen__*
metadata:
openclaw:
requires:
env:
- HEYGEN_API_KEY
primaryEnv: HEYGEN_API_KEY
---
## Preamble (run first)
No auto-run steps. Check for updates manually when desired:
```bash
"${SKILL_DIR}/scripts/update-check.sh"
```
This script is opt-in only. Do not execute it automatically on skill invocation.