# Video Producer — workflow skill for Shorts & Reels

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page.

Topic in, narrated short MP4 out: shot plan, AI stills, per-scene voiceover, Remotion render

- **Type:** [Workflow](https://skills.varg.ai/workflows.md) · [Shorts & Reels](https://skills.varg.ai/browse/skills/shorts.md)
- **Slug:** `video-producer`
- **Status:** beta
- **Publisher:** a1024708231 (community)
- **License:** unknown
- **Source:** https://clawhub.ai/a1024708231/skills/video-producer
- **Works in:** OpenClaw
- **Requires:** Node.js, Remotion, video-director skill, an image generation and TTS backend (not named)
- **Cost:** Depends on the image and TTS services you configure; the SKILL.md does not name them
- **Adoption:** 94 installs, 2 ClawHub stars (ClawHub, 2026-10-27)

## What it does

Coordinates a short-video pipeline: it calls a separate video-director skill to write a storyboard table (scenes, timing, narration, asset prompts and file names), then generates AI images for each asset, records TTS voiceover per scene, writes Remotion code that animates the stills, emoji and titles, and renders and muxes a final MP4. It ships a keyword-to-visual mapping table (e.g. 'layoffs' becomes an empty office) and is run with `node produce.js "topic" '[scenes JSON]'`. The SKILL.md does not say which image model or TTS service is used, and it depends on the video-director skill being installed.

## Use when

- You want a complete short video with voiceover generated from a topic and a few talking points
- You want a storyboard you can edit by hand before the video is rendered
- You need text-and-emoji explainer shorts built from AI stills

## Not for

- Live-action footage or AI video-model clips; the motion comes from animated stills in Remotion

## Install

- OpenClaw: `npx clawhub@latest install video-producer`

## More Shorts & Reels skills

- [AI Social Media Content](https://skills.varg.ai/skills/inference-sh-ai-social-media-content.md): Produce reels, shorts, images and thumbnails for TikTok, Instagram, YouTube and X with one toolkit.
- [Krea Faceless Video](https://skills.varg.ai/skills/krea-faceless-video.md): Make narrated faceless explainers, documentaries and kids' stories as finished multi-scene films on Krea.
- [Short Video Script](https://skills.varg.ai/skills/short-video-script.md): Short-video scripts, titles and cover ideas for Douyin, Kuaishou, Bilibili and WeChat Channels

## Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Grok and any agent that reads SKILL.md: `npx skills add vargHQ/skills --skill varg-ai`, or point it at the skill's SKILL.md
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt