Agent skill · creative production · digitalsamba
video_toolkit
Create professional videos autonomously using claude-code-video-toolkit — AI voiceovers, image generation, music, talking heads, and Remotion rendering.
Why this skill is useful
Adds specific command usage patterns and progress reporting techniques for video generation that the AI wouldn't reliably generate on its own.
What it needs
Requires ffmpeg, node, npm, python3 installed locally. About 10k tokens when loaded. Last updated 2026-07-06. 1,901 stars on the source repository.
What this skill does
Video Toolkit Create professional explainer videos from a text brief. The toolkit uses open-source AI models on cloud GPUs (Modal or RunPod) for voiceover, image generation, music, and talking head animation. Remotion (React) handles composition and rendering. CRITICAL: Toolkit Path The toolkit lives at a fixed path. ALWAYS cd here before running any tool command. NEVER run tool commands from inside a project directory. Tools resolve paths relative to the toolkit root. CRITICAL: Progress Reporting ALWAYS add --progress json to every cloud GPU tool command. This gives you structured JSON Lines on stderr so you can monitor job status, detect stuck jobs, and report progress to the user in real-time. Tools that support --progress json: musicgen.py, qwen3tts.py, flux2.py, upscale.py, sadtalker.py, imageedit.py, dewatermark.py, ltx2.py, chainvideo.py. See the Progress Reporting section below for output format and stage definitions. CRITICAL: Long-Running Tasks — Use yieldMs, Not background:true Any tool command that takes more than 30 seconds MUST use exec with yieldMs so you can report progress to the user live. This includes: batch FLUX generation, chainvideo, SadTalker, music generation, and any multi-scene pipeline. The polling loop: 1. exec with yieldMs:10000 starts the command and returns control to you every 10 seconds 2. Read the --progress json output — look for "stage":"item" (scene complete) or "stage":"complete" (all done) 3. Report progress to the user ("Scene 05/30 complete, 17%") 4. Poll again: process action:poll sessionId:<id> 5. Repeat until "stage":"complete" Why: Your agent run ends when you finish responding. If you use bash background:true, you lose the ability to report progress — the user sees silence until they nudge you. With yieldMs, you stay in the loop. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills digitalsamba/openclaw-video-toolkit