talking-head-video
Creates talking head videos from any source material (docs, changelogs, blog posts, notes, transcripts). Produces multi-scene videos with avatar narration over screenshots/images using HeyGen v2 API. Supports Quick Shot and Full Producer modes.
npx skills add gooseworks-ai/goose-skills --skill talking-head-video --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
A video production skill that takes source material (text, URLs, screenshots, images, or GitHub PRs) and produces talking head videos with an avatar narrating over screenshots/backgrounds. It supports Loom-style layouts and two production modes: Quick Shot for fast, short videos with minimal source material, and Full Producer for richer, longer videos with script and scene plan approval.
How it works
- Determine production mode from user intent: Quick Shot, Full Producer, or Interactive Session. Quick Shot uses lite discovery (2 questions) and generates 2-3 scenes with default avatar/voice; Full Producer uses full discovery (4 questions), analyzes material, presents script and scene plan for approval, and creates 4-8 scenes with style and avatar choices; Interactive Session handles when no source material is provided (extended discovery).
- Run discovery by reading the provided source material, then asking targeted questions to resolve intent, audience, tone, visuals, takeaway, and any inclusions/exclusions.
- Based on discovery, choose output parameters (orientation, duration, scene structure) and plan visuals (screenshots or assets) per mode.
- Avatar setup: check for AVATAR-CONFIG.md. If missing, present avatar setup options (stock avatar, photo avatar, digital twin, or generate from description) and proceed through avatar and voice selection, using HeyGen v2 endpoints as described.
- Save avatar configuration in AVATAR-CONFIG.md and proceed to video production flow with the selected avatar, voice, and style presets.
- Visual style presets guide background and tone; select appropriate style matching content type and audience.
When to use it
Use Quick Shot for short changelog updates or where source material is minimal. Use Full Producer for documentation walkthroughs, feature explainers, or customer-facing content with richer source material. Use Interactive Session when no source material is ready and you need to plan collaboratively.
What it can touch
The skill interacts with HeyGen v2 API through avatar and voice configuration steps, including endpoints for avatars and voices, and supports selecting or generating avatar visuals and voices as part of the AVATAR-CONFIG.md setup. It uses local files AVATAR-CONFIG.md and AVATAR-CONFIG.md for persistence across sessions.
Caveats
The workflow requires reading and interpreting the source material to guide discovery questions and production decisions. The skill specifies exact modes, questions, and API interactions but does not guarantee final video outcome or asset availability beyond described processes. AVATAR-CONFIG.md is created on first run and updated as needed; subsequent runs reuse existing avatar configurations.
# Talking Head Video Skill You are a video production skill that takes source material and produces a talking head video using HeyGen's v2 API. The video features an avatar narrating over screenshots and backgrounds, with support for Loom-style layouts (avatar in corner over content). --- ## Mode Detection Before starting, determine which production mode to use based on the user's request: ### Quick Shot **Trigger:** User wants something fast, simple, or says things like "just make a quick video", "nothing fancy", or provides minimal source material (a single paragraph, a short changelog entry). - Run discovery (lite — 2 questions) - Use default avatar, voice, and style - 2-3 scenes max - No approval gates — generate immediately - Best for: short changelog updates, quick FAQ answers, internal updates ### Full Producer **Trigger:** User provides rich source material, says "make it good", "this is for the website", or the content is longer than a few paragraphs. - Run discovery (full — 4 questions) - Analyze the source material thoroughly - Present the script and scene plan for approval before generating - 4-8 scenes - Offer style and avatar choices - Best for: documentation walkthro
- Mode Detection
- Quick Shot
- Full Producer
- Interactive Session
- Discovery
- How Discovery Works
- Discovery Questions (pick from this list based on what you DON'T already know)
- Discovery by Mode
- What to Do With Discovery Answers
- Avatar Setup
- Check for Existing Avatar Config
- First-Run Setup (No Config Exists)
- Voice Selection
- Save the Config
curl -X POST "https://upload.heygen.com/v1/asset" \ curl -s "https://api.heygen.com/v2/avatars" -H "X-Api-Key: <HEYGEN_API_KEY>" curl -s "https://api.heygen.com/v2/voices" -H "X-Api-Key: <HEYGEN_API_KEY>" curl -X POST "https://api.heygen.com/v3/voices" \
What does the talking-head-video skill do?
Creates talking head videos from any source material (docs, changelogs, blog posts, notes, transcripts). Produces multi-scene videos with avatar narration over screenshots/images using HeyGen v2 API. Supports Quick Shot and Full Producer modes.
How do I install it?
Run `npx skills add gooseworks-ai/goose-skills --skill talking-head-video --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From gooseworks-ai/goose-skills, a repository with 1,091 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.