For results closest to the showcase, I recommend starting with Codex. I use Codex to create and test my showcase examples for this project.

You can also install the Skill in Claude Code, Cursor, Antigravity, or other agents with file and terminal access. However, differences in models, tool configuration, and execution can lead to different results.

Send the following to your AI assistant:

Install this Skill for me:
https://github.com/kaomei/stickman-video-director

Once installed, read the installed SKILL.md right away.
Explain what each mode produces, the tools it needs, and the workflow
in plain language, with examples I can copy.
Based on what I want to make, tell me what is missing and exactly what to do next.

<a id="director-start"></a>

A · Director Mode: scene-by-scene video prompts

After installation, send this to your AI assistant and replace the placeholder with your topic:

Use Director Mode / mode A to turn the following topic, copy, or brief
into a stickman video:
[Enter a topic, paste your copy, or describe what you need]

Requirements: landscape 16:9, A3 "Prehistoric Cave" style, starting with 30 seconds.
Give me the director's treatment first. After I approve it, provide scene-by-scene video prompts.

Workflow: share your topic and brief → develop the story script → optionally approve front, side, and back character views → generate detailed storyboard prompts → manually generate clips and edit the final video

The treatment covers the story structure, scene-by-scene narration, actions, camera direction, and sound design. Copy each prompt into Google Flow or another video generator, then add captions and finish the edit in CapCut or your preferred editor.

For your first video, follow the visual production walkthrough on X (Thread with step-by-step video demos).

<a id="autopilot-start"></a>

B · Autopilot Mode: from a brief to a long-form video

After installing in Codex, Claude Code, or another environment with file access and command execution, try:

Use Autopilot Mode / mode B to turn the following topic, article, post, news item, or brief
into a compelling YouTube video:
[Paste content or a link, or describe what you want to promote]

Requirements: 5–10 minutes, landscape 16:9, B1 "Minimal Line Art" style, with voiceover, captions, and sound effects.

Check the image generation, voiceover, and video-rendering setup first. Then give me a script and a 20-second preview with sound.
After I approve it, build the full video with visuals timed to the narration. Deliver a complete video file; I do not want to assemble scenes myself.

Workflow: share a topic, content, or brief → approve the script → approve a 20-second preview with sound → automatically produce the full video → receive the finished video file

The AI assistant plans the scenes, generates the visuals and narration, adds captions and sound effects, and renders a complete video to the voiceover's timing. You approve the script and preview; you do not have to generate and assemble every scene yourself.

On first use, it checks the required setup and walks you through anything missing. If a visual or voiceover section needs work, revise just that section and keep what you have already approved.

Optional finishing for either mode: once you confirm the final video, continue with the Thumbnail & Publishing Kit for a matching cover and upload copy—or finish here. No new mode or installation is needed.

<a id="style-gallery"></a>

<a id="a-styles"></a>