Realistic Ugc Video

This orchestrates Nano Banana and Kling AI to generate talking head videos that don't scream "AI generated." The workflow is thorough: generate a base image with intentional imperfections like pores and mixed lighting, chunk your script into 55-60 syllable segments for natural pacing, then generate 10-second video clips with choreographed micro-movements. The documentation is refreshingly honest about the hands problem (AI models can't do realistic hand movement, so crop them out or keep them static). It's a multi-step process that requires post-production, but if you need UGC-style spokesperson videos and care about them looking real, this gives you the specific prompting strategies and pacing math to pull it off.

skills.sh installs: 310
GitHub stars: 9
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add dennisonbertram/claude-media-skills --skill realistic-ugc-video --agent claude-code

Installs into .claude/skills of the current project.

Files

Realistic UGC Video Production

Create long-form AI videos that look and sound authentically human. This skill orchestrates a multi-step workflow using Nano Banana for realistic base images and Kling AI for video generation, with specific techniques to avoid the "AI look".

Why Videos Look AI (And How to Fix It)

Problem	Solution
Too perfect/clean skin	Add imperfections: micro-pores, natural oils, fine lines
Studio lighting	Use available/natural light, mixed color temps
Character too still	Add micro-movements, head tilts, natural sway
Inconsistent pacing	Use 55-60 syllables per clip
Robotic voice	Process through Adobe Podcast or Resemble AI
Obvious jump cuts	Cover with B-roll or animations
Weird AI hands	Crop hands out of frame or keep completely static

Known Limitation: Hands

AI video models (Kling, Veo, etc.) struggle with realistic hand movement. Fingers morph, gestures look unnatural, and hands are often the biggest tell.

Best practice: Keep hands OUT of frame or completely static.

SKILL.md on GitHub