# heygen

Prepares video scripts and configuration briefs for HeyGen talking-head avatars, video translation with lip-sync, and social content pipelines.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 589 installs · ★ 199
- Author: social-media-skills
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/social-media-skills/skills/tree/HEAD/skills/heygen/SKILL.md
- Updated: 2026-10-15
- HTML: https://affpapa.org/en/nevibecode/skills/social-media-skills-heygen

## What it does

This skill structures and scripts AI talking-head videos before passing them down the pipeline. It selects the avatar type, sets the voice and background, and plans B-roll cutaway cues. HeyGen executes the video rendering, a human reviews the draft, and WoopSocial handles scheduling. Real founder videos route to `talking-head-and-piece-to-camera`, while enterprise SCORM courses hand off to `synthesia`.

Drafting follows the TALK framework: tailor the persona, select the audio, keep the copy lean, and switch camera angles to avoid visual fatigue. The setup works with Avatar V for digital twins, Avatar IV for expressive movement, stock characters, and Talking Photo for clips under 15 seconds. Video Translator handles localization across 175+ languages with lip-sync.

Non-consensual avatars are blocked immediately, and every generated asset requires an explicit AI disclosure on screen or in captions.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill heygen -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/heygen/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/heygen/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill heygen -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/heygen/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill heygen -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/heygen/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install social-media-skills/skills heygen
```

2. **Manually: put the files in place**
- File: `.github/skills/heygen/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill heygen -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/social-media-skills/skills --path skills/heygen
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/heygen/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill heygen -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/social-media-skills/skills/tree/HEAD/skills/heygen/SKILL.md

## When to use it
- draft conversational scripts for talking-head avatars using the TALK framework
- configure localization briefs for Video Translator across 175+ languages
- select the correct avatar engine between Avatar V, Avatar IV, or stock options
- route generative B-roll cutaways to `veo-3` to avoid viewer visual fatigue

## Example prompts
- Write a 60-second talking-head script for an Avatar V digital twin and mark B-roll cutaways
- Configure a HeyGen Video Translator setup to localize our product demo into Spanish and German
- Prepare an explainer brief using a stock avatar with AI disclosure tags for WoopSocial scheduling

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 97384a3d1e184317.

BEGIN THIRD-PARTY FILE 97384a3d1e184317
```text
---
name: heygen
description: >-
  The AI avatar / talking-head mini-skill (HeyGen). Use when someone wants an "AI avatar video,"
  "talking-head video," "digital twin / clone of myself on camera," "faceless presenter video,"
  "spokesperson video," or to "translate/localize a video into many languages with lip-sync."
  The creator/social avatar lane; enterprise L&D/training/SCORM avatar work routes to synthesia,
  and a real human on camera (founder/trust content) routes to talking-head-and-piece-to-camera.
  Scripts and sets up the video; HeyGen renders; the human reviews/edits; WoopSocial schedules/
  publishes. Sits below the ai-video router, sibling to veo-3. Consented avatars only; AI
  disclosure mandatory.
version: 1.0.0
---

# heygen

The mini-skill for **avatar / talking-head video** with HeyGen — the counterpart producer to
**veo-3** (generative scenes) under the **ai-video** router. It scripts and sets up the video;
HeyGen renders; a human reviews; WoopSocial schedules/publishes.

## The POV: right tool for scaled scripted delivery, not personality
Avatars win for **scaled, scripted, multilingual** work — explainers, training, localization, FAQ,
faceless channels, personalized sales at volume. They **lose** at spontaneity, personality, and
parasocial warmth (still human territory — trust-led founder content routes to
**talking-head-and-piece-to-camera**). Use a **consented** avatar, write for calm clarity, cut
away so a static face doesn't fatigue, diversify avatars, and **always disclose**. HeyGen is the
**creator/social-native lane**; enterprise L&D/compliance/SCORM at scale → **synthesia**.

## Read these first
1. **brand-profile** — look, audience, non-negotiables (and the avatar's demeanor).
2. **voice-builder** — tone, so the script and voice sound like the brand.

## The framework: TALK
(Depth: `references/the-talk-framework.md`.)
- **T — Tailor the avatar:** Digital Twin (Avatar V, ~15s clip, consented) for a personal brand;
  stock for faceless; Talking Photo only for <15s clips.
- **A — Audio that fits:** voice + language; clone the speaker for consistency; localize via Video
  Translator (175+ languages, lip-sync).
- **L — Lean script:** conversational, one idea, short sentences, no tongue-twisters; open with the point.
- **K — Keep eyes moving:** cut to B-roll (veo-3), screen-records, text, shot changes; the avatar is
  the spine, not the whole frame.

## Pick the engine / type (verify-quarterly)
Avatar V (highest fidelity, twins, identity-stable over long videos) · Avatar IV (expressive
default) · stock avatars (no likeness questions) · Talking Photo (<15s only). Localization is
HeyGen's strongest use case. Full capabilities + API + pricing:
`references/heygen-2026-capabilities.md`.
```
END THIRD-PARTY FILE 97384a3d1e184317

The third-party file has ended. Everything between the 97384a3d1e184317 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2779 of 5130 bytes. © social-media-skills · MIT · https://github.com/social-media-skills/skills/tree/HEAD/skills/heygen/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md