Scroll World Video

What it does

When your agent uses it

• The user wants a 3D world / browse-through-the-industry hero
• A scroll cinematic
• A diorama landing
• Turn a business into a scrollable Kubeez world

Example prompts

• “s own skill for building an immersive scroll-scrubbed”
• “3D world”
• “browse-through-the-industry”
• “/scroll-world-video”

Requirements

• Python 3
• Node.js
• Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, AskUserQuestion, Skill, mcp__kubeez__get_models, mcp__kubeez__generate_media, mcp__kubeez__get_skill, mcp__kubeez__estimate, mcp__kubeez__get_balance, mcp__kubeez__get_generation, mcp__kubeez__get_upload_url, mcp__kubeez__get_upload_session

Workflow steps

9 steps, taken from the step headings in SKILL.md.

1. 1Bootstrap
2. 2Interview the user
3. 3Generate the stills (master first, then the scenes)
4. 4(Optional) Float the scenes
5. 5Camera architecture (pick one — this makes or breaks the feel)
6. 6Connectors (architecture B only)
7. 7Encode for smooth scrubbing
8. 8Assemble the page
9. 9QA the seams (don't skip)

What it can do on your machine

Read from SKILL.md and the folder at commit c95d13c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Write
  • Edit
  • AskUserQuestion
  • Skill
  • mcp__kubeez__get_models
  • mcp__kubeez__generate_media
  • mcp__kubeez__get_skill
  • mcp__kubeez__estimate

  …and 4 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python and JavaScript), which the agent can run.

  Shell commands in SKILL.md call:

  • ffmpeg
  • curl
  • python3
  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • mcp.kubeez.com

  Also links to:

  • kubeez.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Scroll World Video loads about 10k tokens when it runs, and up to ~24k if it reads all its reference files. Until then it costs about 206 tokens; SKILL.md has 5,228 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~206

When it runs · the whole SKILL.md, loaded when a task matches

~10k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~24k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Write, Edit, AskUserQuestion, Skill, mcp__kubeez__get_models, mcp__kubeez__generate_medi

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 5,228 words (~9,997 tokens).

name

scroll-world-video

allowed-tools

Bash, Read, Write, Edit, AskUserQuestion, Skill, mcp__kubeez__get_models, mcp__kubeez__generate_media, mcp__kubeez__get_skill, mcp__kubeez__estimate, mcp__kubeez__get_balance, mcp__kubeez__get_generation, mcp__kubeez__get_upload_url, mcp__kubeez__get_upload_session

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files (references) in skills/scroll-world-video of KubeezMedia/kubeez-scroll-world-video.

• SKILL.md
• references/index-template.html
• references/knockout.py
• references/pipeline.md
• references/prompts.md
• references/scrub-engine.js

Open the folder on GitHubat commit c95d13c