skills.rest
TheMattBerman
TheMattBermanCOMMUNITY
Explore all skills by this author →
Website𝕏@themattbermanGitHub

scrollclaw-animate

Generate talking-head MP4 clips from approved frames and script-tagged dialogue segments.

68|15|Updated Mar 24, 2026
Search Tags:#fal.ai#image-to-video#talking head#lip sync#ugc video#sora 2#kling 3
One-click install
npx skills add https://github.com/TheMattBerman/scrollclaw --skill scrollclaw-animate
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrollclaw-animate
Source: https://github.com/TheMattBerman/scrollclaw/tree/main/animate
Command: npx skills add https://github.com/TheMattBerman/scrollclaw --skill scrollclaw-animate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill converts approved first frames and tagged A-roll script segments into scroll-stopping talking-head video clips with synced lip movement and dialogue audio, reducing the anti-polish effort needed to make AI video feel human.

Core Features & Use Cases

  • A-roll clip generation (image-to-video with dialogue): Produces one talking-head MP4 clip per [A-ROLL] script segment using Sora 2 as the primary provider.
  • Provider fallback chain for reliability: Automatically falls back from Sora 2 (fal.ai) to Kling 3, and then to Replicate Kling 3 if needed; you can force Kling by using --provider kling.
  • Structured motion prompting: Uses a labeled prompt schema (Camera/Subject/Dialogue/Audio/Environment & light/Style & mood) to keep the result realistic (iPhone/selfie feel) and reduce content-filter failures.
  • Generation logging and brand memory integration: Reads the canonical frame1.png, the [A-ROLL] script, and creator references; writes MP4 outputs and append-only output-log.md entries.

Quick Start

Run the animate workflow for A-roll by generating a portrait clip from your approved frame1.png using motion-prompt.txt and an A-roll script that includes [A-ROLL] segments.

Frequently Asked Questions about scrollclaw-animate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a talking head video from an image with lip sync?▼

You can animate a still image into a talking head clip by providing an approved first frame and an A-roll script tagged with dialogue segments. The Skill uses structured motion prompting to ensure lip sync and dialogue audio match the script.

How do I use Sora 2 for image-to-video generation with fal.ai?▼

You can use Sora 2 for image-to-video generation via fal.ai as the default provider for animating talking head clips. The Skill handles provider routing and polling automatically, falling back to Kling 3 if Sora 2 fails.

Can I force Kling 3 for UGC video generation instead of Sora 2?▼

Yes, you can force Kling 3 for UGC video generation by using the --provider kling flag. This bypasses the default Sora 2 provider and executes the image-to-video animation using Kling only.

What is structured motion prompting for AI video?▼

Structured motion prompting for AI video uses a labeled prompt schema covering Camera, Subject, Dialogue, Audio, Environment, and Style to keep results realistic. This reduces content-filter failures and maintains an authentic iPhone or selfie feel for UGC clips.

Do I need a specific script format to create A-roll talking head clips?▼

Yes, you need a script format that includes explicitly tagged [A-ROLL] dialogue segments to create talking head clips. The Skill processes each [A-ROLL] segment individually to generate one synchronized MP4 output per segment.

Why does image-to-video generation fail content filters for UGC clips?▼

Image-to-video generation often fails content filters for UGC clips due to unstructured prompting. This Skill mitigates filter failures by using a structured motion-prompting schema that enforces realistic camera, subject, and environment parameters.

Related Skills

Explore More Design & Creative Skills→
TheMattBermanTheMattBerman
68

scrollclaw-broll

Generate environment-matched B-roll clips aligned to scripted voice beats.

Community
Intermediate
1370998960-del1370998960-del
207

seedance-audio

Automate audio post-production for dialogue, lip-sync, and sound layers in Seedance 2.0.

Community
Intermediate
GroundMountCompanyGroundMountCompany

ai-product-video

Convert approved product images into cinematic video variations with multiple AI models.

Community
Basic
mattwoodcomattwoodco
3

ai-video-gen

Generate videos from text prompts or images via Replicate and fal.ai.

Community
Advanced