When you need to put accurate text on AI-generated video, this is the tool. LTX-2 and SadTalker can't render readable text reliably, so the pattern is: generate the visual, then overlay names, prices, or captions with moviepy in Python. It's built for sub-30s spots, lower thirds on talking heads, and anything where the text has to be pixel-perfect for legal or editorial reasons. The skill includes two runnable examples that produce real mp4s immediately, and it ships a PIL-based text renderer that sidesteps moviepy's tight-bbox bug. Use this over Remotion when you want a single build.py file and zero React overhead.
npx -y skills add digitalsamba/claude-code-video-toolkit --skill moviepy --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills