PlanningVideoMotion GraphicsTTSEditingDesign

Blender 3D Long-form Automation Skillbot

Blocky Science Long-form: Start Here

A map for 8-9 minute What-if science videos in a blocky 3D world: skills per step, requirements and folder layout.

Works with Claude, GPT and GeminiInstall any one of them in VS Code →ClaudeClaude CodeGPTCodexGeminiAntigravity

How to use

  1. 1

    Download the ZIP

    Get the skill file with the button below. No sign-up.

  2. 2

    Unzip and open

    Unzip it into a folder and open that folder in VS Code.

  3. 3

    Just ask

    Tell your AI agent ‘Run the automation pipeline in this folder’.

When to use it

Try saying

“블록 과학 영상 처음 만드는데 뭐부터 해?”I want to make a blocky science video, where do I start?
“만약 시리즈 롱폼 제작 순서 알려줘”Show me the What-if long-form production order

What you get

  1. 01A 7-step map with requirements
  2. 02Episode folder layout

Tips

Skills in this set

Get it free now

No sign-up, just one ZIP. Edit it freely for personal or commercial use.

Download ZIP (2KB)

Installation

Claude.ai / Desktop app (ZIP upload)

  1. Download the ZIP below.
  2. Upload it under Settings → Capabilities → Skills.
  3. Turn the skill on and start a chat with one of the "Try saying" lines.

Claude Code (copy the folder)

  1. Unzip it. You'll get a folder named after the skill.
  2. Put that folder inside ~/.claude/skills/ (or .claude/skills/ for a single project).
  3. Restart Claude Code.

Menu names may differ slightly depending on your environment. If you can't see the menu, check that skills are enabled on your plan.

Files and preview

Included files

SKILL.md
README.txt

Preview of SKILL.md

---
name: blocky-science-start-here
description: Map for 8-9 minute What-if science videos in a blocky 3D world (Blender, free TTS, Remotion): which skill at each step, setup and folder layout. Start here. 블록 과학 롱폼 시작 안내.
---

# Blocky Science Long-form: Start Here

This skill is the map. It tells the user which skill to use next and checks that they have what each step needs.

The format: a 16:9 long-form video, 8-9 minutes, that asks "What if...?" (What if mosquitoes disappeared? What if the Earth's magnetic field vanished?) and answers with real science, shown in a cute blocky 3D world. The contrast between cute visuals and serious content is the point.

## The path
| Step | What you want | Skill | Needs |
|---|---|---|---|
| 1 | Pick a topic and write a fact-checked script | `what-if-topic-script` | Web search |
| 2 | Make the narration and sentence timings | `free-tts-narration` | Python, edge-tts, ffmpeg |
| 3 | Design the 3D scenes for each idea | `science-scene-design` | Blender 4.2+ |
| 4 | Place cuts and cameras on the narration | `narration-synced-cuts` | Blender, ffmpeg |
| 5 | Add captions and cards | `text-overlay-remotion` | Node.js, Remotion |
| 6 | Make the thumbnail | `blocky-thumbnail` | an image tool, Python |
| 7 | Cut a 60-90 s vertical highlight | `vertical-highlight-reshoot` | Blender, ffmpeg |

Nothing in this set needs a paid service. Blender and Remotion renders are free to repeat.

## Folder layout per episode
```
episodes/<NN - title>/
  script.md        narration by block, shot table, fact-check table, TTS replacement table
  01_blend/        one script per section
  02_render/       <section>/####.jpg, _stills/
  03_audio/        narration wav, timings
  04_final/        preview without text, final with text
output/            finished videos only
```

## Rules for the whole set
- **Facts first**: every number and quote is checked against a source before narration. Unsourced claims are cut.
- **Blocky style, original assets**: follow the look, never use a game's official characters, textures, logos or UI.
- **One shared timeline**: frame = narration second x fps + 1. Every section script and every text card uses it.
- **Stills before renders**, **one full render at a time**, frames as **JPG 95**.

You may also like

This skill is a set of instructions Claude loads on its own. You are responsible for how you use the results. The instructions inside the ZIP are written in Korean. Terms of Use