---
title: "How to Make Any AI Video — tool for AI video: research & trends"
description: "A video request becomes the right skill with its install line and options, or the ten-step route for a whole video made from scratch. Install in Claude Code, Codex and Grok with one command."
url: https://varg.ai/how-to/skills/how-to-make-ai-video
updated: 2026-11-12
---

# How to Make Any AI Video — tool skill for research & trends

> **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/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://varg.ai/how-to/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. From a terminal: `curl -fsSL https://varg.ai/install | sh` installs the vargai CLI (https://varg.ai/how-to/cli.md): `vargai search` and `vargai install <slug>` with no key, every varg model after `vargai login`.

A video request becomes the right skill with its install line and options, or the ten-step route for a whole video made from scratch.

- **Type:** [Tool](https://varg.ai/how-to/models.md) · [Research & trends](https://varg.ai/how-to/browse/skills/research.md)
- **Slug:** `how-to-make-ai-video`
- **Status:** live
- **Publisher:** varg (varg, verified)
- **License:** MIT
- **Source:** https://github.com/vargHQ/skills/tree/main/how-to-make-ai-video
- **Works in:** Claude Code, Codex, Cursor, Gemini CLI
- **Requires:** curl and network access to varg.ai
- **Cost:** 0 credits — Free: the skill only searches and routes; generation is quoted in credits

## What it does

One search over varg how to turns a request ("a UGC ad for my serum", "a music video for my song", "TikTok captions") into the best-matching how-to page, the options to show the person with example links, and the top skills with exact install commands for Claude Code, Codex, Cursor, OpenClaw and Gemini CLI. No key, about 0.1 to 0.5 s, any language.

For a whole piece made from scratch it carries the ten-step route (references, moodboard, script, sound, characters, previz in code, takes, edit, review, GitHub), with the one line a person pastes, the rules, and the guide and skill for each step: https://varg.ai/how-to/make-a-video-in-ten-steps

It also explains the keyless MCP server (`search_how_to`, `get_how_to`), the signed-in search, and how to list a skill you built.

## Use when

- How do I make a ... video
- Which skill should I use for this video
- Make a whole film or launch video from scratch
- Find a skill for captions, voiceover or an edit
- List a video skill I built

## Not for

- Running a generation itself (use varg-ai)
- Non-media coding tasks

## Install

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg`
- Codex: `npx skills add vargHQ/skills --skill how-to-make-ai-video -a codex -y`
- Cursor: `npx skills add vargHQ/skills --skill how-to-make-ai-video -a cursor -y`
- Gemini CLI: `npx skills add vargHQ/skills --skill how-to-make-ai-video -a gemini-cli -y`
- Any agent, with the vargai CLI: `vargai install how-to-make-ai-video`

## More research & trends skills

- [Video Skills Finder](https://varg.ai/how-to/skills/video-skills.md): Finds the right skill for any AI video, image, voice or music job here and shows you the visual options.
- [Apify MCP](https://varg.ai/how-to/skills/apify-mcp.md): Thousands of ready scrapers behind one MCP: TikTok, Instagram, YouTube, hashtags, sounds.
- [TwelveLabs Video Understanding](https://varg.ai/how-to/skills/twelvelabs.md): Semantic search and analysis across your video library from Claude Code.
- [Civitai MCP](https://varg.ai/how-to/skills/civitai-mcp.md): Top AI images and videos with prompts and base models, plus model search.
- [Hugging Face MCP](https://varg.ai/how-to/skills/huggingface-mcp.md): Trending models, Spaces and papers from Hugging Face inside your agent.
- [Exa Search MCP](https://varg.ai/how-to/skills/exa-mcp.md): Neural web search and crawling for research agents.