Agent skill

Generate World

Drive geniesimworld to produce a photorealistic, explorable 3D world from a single equirectangular panorama — uses the geniesimworld create CLI (Click subcommand), pairs SHARP + DA360 to fuse…

MPL-2.0Auto-check passedMedia & Creative

Install Generate World

skills CLI

$ npx skills add AgibotTech/genie_sim --skill generate-world -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install AgibotTech/genie_sim generate-world --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/AgibotTech/genie_sim.git skills-src && mkdir -p .claude/skills && cp -r skills-src/source/geniesim_world/skills/generate-world .claude/skills/generate-world && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "generate-world" agent skill from https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world/skills/generate-world into .claude/skills/generate-world/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-world", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world/skills/generate-world

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add AgibotTech/genie_sim --skill generate-world -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install AgibotTech/genie_sim generate-world --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AgibotTech/genie_sim.git skills-src && mkdir -p .agents/skills && cp -r skills-src/source/geniesim_world/skills/generate-world .agents/skills/generate-world && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "generate-world" agent skill from https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world/skills/generate-world into .agents/skills/generate-world/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-world", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AgibotTech/genie_sim --skill generate-world -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install AgibotTech/genie_sim generate-world --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AgibotTech/genie_sim.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/source/geniesim_world/skills/generate-world .cursor/skills/generate-world && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "generate-world" agent skill from https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world/skills/generate-world into .cursor/skills/generate-world/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-world", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/AgibotTech/genie_sim.git --path source/geniesim_world/skills/generate-world

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add AgibotTech/genie_sim --skill generate-world -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install AgibotTech/genie_sim generate-world --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AgibotTech/genie_sim.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/source/geniesim_world/skills/generate-world .gemini/skills/generate-world && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "generate-world" agent skill from https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world/skills/generate-world into .gemini/skills/generate-world/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-world", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install AgibotTech/genie_sim generate-world

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add AgibotTech/genie_sim --skill generate-world -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/AgibotTech/genie_sim.git skills-src && mkdir -p .github/skills && cp -r skills-src/source/geniesim_world/skills/generate-world .github/skills/generate-world && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "generate-world" agent skill from https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world/skills/generate-world into .github/skills/generate-world/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-world", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AgibotTech/genie_sim --skill generate-world -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install AgibotTech/genie_sim generate-world --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AgibotTech/genie_sim.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/source/geniesim_world/skills/generate-world .opencode/skills/generate-world && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "generate-world" agent skill from https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world/skills/generate-world into .opencode/skills/generate-world/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-world", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: generate-world
GitHub stars: 1.4k
Token cost: ~1.9k tokens
SKILL.md length: 511 words
Files: 1
Skills in repo: 26
Repo updated: Sep 7, 2026
First seen: Oct 7, 2026
Licence: MPL-2.0

At a glance

Drive geniesimworld to produce a photorealistic, explorable 3D world from a single equirectangular panorama — uses the geniesimworld create CLI (Click subcommand), pairs SHARP + DA360 to fuse…

Works in 5 steps: Verify the layout → Create a clean env and install → Generate a world from a panorama → …
Asks to generate a world
SKILL.md covers When to Use, Critical Patterns, Workflow and Commands (copy-paste summary…, plus 2 more sections
Calls pip and conda; reaches download.pytorch.org and github.com

What it does

Generate World is an agent skill from AgibotTech/genie_sim. Drive geniesimworld to produce a photorealistic, explorable 3D world from a single equirectangular panorama — uses the geniesimworld create CLI (Click subcommand), pairs SHARP + DA360 to fuse panorama RGB with metric depth, and optionally upscales with Real-ESRGAN. Trigger: When the user asks to "generate a world", "生成 3D 世界", "pano to 3D", "PanoRecon", "make a scene from a photo", "create a world from a panorama", or references geniesimworld / a .png panorama input.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Image editing. The repository describes itself as: Simulation Platform from AgiBot. The licence is MPL-2.0.

When your agent uses it

Asks to generate a world
Make a scene from a photo
Create a world from a panorama
References geniesimworld / a .png panorama input

Example prompts

“generate a world”
“生成 3D 世界”
“pano to 3D”
“/generate-world”

Requirements

Python 3

Workflow steps

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

Verify the layout
Create a clean env and install
Generate a world from a panorama
Inspect the work-dir
(🚧 W.I.P.) Feed into a Genie Sim scene

What it can do on your machine

Read from SKILL.md and the folder at commit 6ca11c7. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- pip
- conda
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:
- download.pytorch.org
- github.com
Also links to:
- arxiv.org
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

Generate World loads about 1.9k tokens when it runs. Until then it costs about 124 tokens; SKILL.md has 511 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~124
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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

The full file from AgibotTech/genie_sim at commit 6ca11c7, republished under its MPL-2.0 licence (© AgibotTech). 511 words, ~1,851 tokens.

Download SKILL.mdSave it as .claude/skills/generate-world/SKILL.md (or your agent's skills folder).

name: generate-world
description: Drive `geniesim_world` to produce a photorealistic, explorable 3D world from a single equirectangular panorama — uses the `geniesim_world create` CLI (Click subcommand), pairs SHARP + DA360 to fuse panorama RGB with metric depth, and optionally upscales with Real-ESRGAN. Trigger: When the user asks to "generate a world", "生成 3D 世界", "pano to 3D", "PanoRecon", "make a scene from a photo", "create a world from a panorama", or references `geniesim_world` / a `.png` panorama input.
license: MPL-2.0
metadata.author: genie-sim
metadata.version: 1.0

When to Use

User has an equirectangular panorama (2:1 aspect, e.g. 4096×2048) and wants a 3D world (Gaussian splat / depth map / fused cubes) out of it.
User wants to seed a Genie Sim scene with a generated environment rather than a hand-authored USD.
Researcher reproducing the PanoRecon paper (arXiv 2604.07105).

Do not use for:

USD scene authoring without a panorama input → that's the generate-scene skill in geniesim_generator.
Asset / object library search → search-assets in geniesim_generator.
Importing an existing USD scene into the RT Engine → just point the scene yaml's scene_usda at the existing USD (see add-robot / launch-scene). This skill is not the path for that — geniesim_world produces .ply / .gsp Gaussians today, and loading them into a scene_*.yaml is 🚧 W.I.P.

Critical Patterns

Out-of-band install. geniesim_world is not pulled in by geniesim bootstrap — it lives behind heavy CUDA deps (PyTorch + ml-sharp + DA360 + optional Real-ESRGAN). Install in its own conda env, separate from the rest of the stack.
Three external dependencies, not on pip. Need external/ml-sharp/, external/DA360/ (with checkpoint), and optionally external/realesrgan-ncnn-vulkan-…/. The external/ tree sits next to geniesim_world/ under source/.
DA360 checkpoint is mandatory. Either drop it at external/DA360/DA360_large.pth, pass --da360-checkpoint, or set GENIESIM_DA360_CHECKPOINT. Without it, depth prediction fails immediately.
Tested on RTX 5090 / CUDA 12.8. Other GPUs work but need a matching requirements-cu<XX>.txt. Don't paste the cu128 line verbatim onto a cu118 box.
Real-ESRGAN is optional. It improves visual fidelity but introduces synthetic texture — disable for tasks where ground-truth pixel statistics matter.

Workflow

Step 1 — Verify the layout

source/
├── geniesim_world/                              # this project
└── external/
    ├── ml-sharp/                                # git clone https://github.com/apple/ml-sharp.git
    ├── DA360/                                   # git clone https://github.com/DepthAnything/DA360.git
    │   └── DA360_large.pth                      # checkpoint (download separately)
    └── realesrgan-ncnn-vulkan-20220424-ubuntu/  # optional, super-sample binary
        └── realesrgan-ncnn-vulkan

If any external is missing, run the clone / download from the geniesim_world/README.md § "Prepare Dependencies".

Step 2 — Create a clean env and install

bash

conda create -n geniesim_world python=3.11 -y
conda activate geniesim_world
pip install --upgrade "pip==24.0" "setuptools==69.5.1" "wheel==0.43.0"

cd source/geniesim_world
pip install --extra-index-url https://download.pytorch.org/whl/cu128 -r requirements-cu128.txt
pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e .

Verify:

bash

geniesim_world --help                            # Click group
geniesim_world create --help                     # subcommand surface

Step 3 — Generate a world from a panorama

bash

geniesim_world create \
  --panorama path/to/scene_pano.png \
  --work-dir runs/$(date +%Y%m%d_%H%M%S) \
  --device cuda:0

Optional knobs:

Flag	Effect
`--da360-checkpoint <path>`	Override checkpoint path
`--da360-root <dir>`	Override DA360 repo root
`--checkpoint-path <path>`	SHARP checkpoint override
`--depth-max <float>`	Clip predicted depth at N metres
`--no-depth-gt-init`	Stock SHARP (ignore depth_gt override)
`--super-sample`	Run Real-ESRGAN before fusing (needs the optional binary)

Show full SKILL.md (186 more words)Show less

Step 4 — Inspect the work-dir

Typical artifacts under runs/<stamp>/:

runs/<stamp>/
├── pano_input.png             # the panorama (copied for provenance)
├── depth/                     # per-cube depth maps (EXR or PNG)
├── cubes/                     # cubemap faces fused from pano + depth
└── world.gsp / world.ply / …  # exported world (format depends on flags)

Step 5 — (🚧 W.I.P.) Feed into a Genie Sim scene

Loading the generated world into the RT Engine via a scene_*.yaml is not yet supported. The current contract is that geniesim_world produces .ply / .gsp Gaussians (plus per-face EXR depth + cubemap RGB); downstream consumption is via the package's own debug tooling (geniesim_world debug) and external viewers, not the RT Engine launcher. The RT-Engine load path is planned — track the Roadmap & Updates section in the root README.

Commands (copy-paste summary for the user)

bash

# Once-off setup
conda create -n geniesim_world python=3.11 -y && conda activate geniesim_world
cd source/geniesim_world
pip install --extra-index-url https://download.pytorch.org/whl/cu128 \
  -r requirements-cu128.txt
pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e .

# Generate
geniesim_world create \
  --panorama path/to/scene_pano.png \
  --work-dir runs/demo \
  --device cuda:0

Notes

The CLI is a Click group: geniesim_world exposes subcommands, with create being the primary one. Run geniesim_world --help for the full list.
"Generate from text" and "Generate from sparse images" are flagged COMING SOON in geniesim_world/README.md — don't promise them in the workflow.
The env is intentionally isolated from the rest of the stack so pip install here can't break a working geniesim_ros shell.
For sim-to-real research, the generated world's depth statistics are more reliable without --super-sample (Real-ESRGAN introduces hallucinated texture).

Resources

CLI source: source/geniesim_world/src/geniesim_world/cli_pano.py
README: source/geniesim_world/README.md
AGENTS.md: source/geniesim_world/AGENTS.md
Paper: https://arxiv.org/abs/2604.07105
External deps: apple/ml-sharp, DepthAnything/DA360, optional xinntao/Real-ESRGAN

Files

Just SKILL.md in source/geniesim_world/skills/generate-world of AgibotTech/genie_sim.

Open the folder on GitHubat commit 6ca11c7

Compare with similar skills

Generate World next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Generate World compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Generate World this skillAgibotTech/genie_sim	1.4k	—	~1.9k	Automated safety check: Pass	MPL-2.0	1 mo ago
HyperFrames Media Useheygen-com/hyperframes	58k	2 repos	~2.1k	Automated safety check: Pass	Apache-2.0	today
AI Image Generation and Editingzhayujie/CowAgent	47k	—	~1.3k	Automated safety check: Pass	MIT	2 days ago
Generate Imageynulihao/AgentSkillOS	617	10 repos	~1.7k	Automated safety check: Notes	None	7 mo ago
GPT Image Generation CLIwuyoscar/GPT-Image2-Skill	5.6k	—	~2.5k	Automated safety check: Notes	MIT	7 days ago
NanobananaReScienceLab/opc-skills	1.8k	1 repos	~1.3k	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

HyperFrames Media Use
heygen-com/hyperframes
Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.
58k GitHub starsUsed in 2 repos~2.1k tokens
Media & CreativeAuto-check passed
AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
47k GitHub stars~1.3k tokensUpdated 2 days ago
Media & CreativeAuto-check passed
Generate Image
ynulihao/AgentSkillOS
Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.
617 GitHub starsUsed in 10 repos~1.7k tokens
Media & CreativeAuto-check: notes
GPT Image Generation CLI
wuyoscar/GPT-Image2-Skill
Generates and edits images with GPT Image 2 or 2.5 through a packaged CLI and a prompt gallery, after settling which model fits the request.
5.6k GitHub stars~2.5k tokensUpdated 7 days ago
Media & CreativeAuto-check: notes
Nanobanana
ReScienceLab/opc-skills
Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro).
1.8k GitHub starsUsed in 1 repo~1.3k tokens
Media & CreativeAuto-check passed
Native Transparent Imagegen
ZSeven-W/craft-skills
Generate new raster assets that must contain native pixel transparency, then verify the untouched PNG or WebP before delivery.
223 GitHub starsUsed in 2 repos~1.1k tokens
Media & CreativeAuto-check passed

More from AgibotTech/genie_sim

All 26 skills in this repo

Challenge Baseline Model
AgibotTech/genie_sim
Provision and launch the Simulation Challenge baseline inference model end to end: clone the inference code from a given git repo/branch, download the checkpoints from ModelScope into the repo's…
1.4k GitHub stars~2.4k tokensUpdated 1 mo ago
Auto-check passed
Challenge Download Datasets
AgibotTech/genie_sim
Download the Simulation Challenge LeRobot v2.1 training datasets from ModelScope using ./scripts/downloaddataset.sh.
1.4k GitHub stars~960 tokensUpdated 1 mo ago
Auto-check passed
Add Robot
AgibotTech/genie_sim
Bring a custom robot into the Genie Sim RT Engine — author / fix a xacro / URDF in geniesimrobotmodel, prep meshes with the offline tools (normalizeobjnames.py, diagnoseurdf.py, recomputeinertia.py…
1.4k GitHub stars~2.1k tokensUpdated 1 mo ago
Auto-check passed
Build Workspace
AgibotTech/genie_sim
Build the geniesimros colcon workspace inside the Genie Sim Docker container using the geniesim ros build CLI verb.
1.4k GitHub stars~1.2k tokensUpdated 1 mo ago
Auto-check passed
Challenge Inference Protocol
AgibotTech/genie_sim
Reference for the Simulation Challenge inference wire protocol — the exact obs (input) and action (output) message format exchanged between the gateway/genie-sim simulator and the contestant's…
1.4k GitHub stars~1.7k tokensUpdated 1 mo ago
Auto-check passed
Challenge Login
AgibotTech/genie_sim
A skill your agent uses when the contestant needs to obtain or refresh their Simulation Challenge JWT (CHALLENGETOKEN), or wants to inspect the current logged-in user.
1.4k GitHub stars~1.6k tokensUpdated 1 mo ago
Auto-check passed

Questions about Generate World

What does Generate World do?

Drive geniesimworld to produce a photorealistic, explorable 3D world from a single equirectangular panorama — uses the geniesimworld create CLI (Click subcommand), pairs SHARP + DA360 to fuse…. Generate World is an agent skill from AgibotTech/genie_sim. Drive geniesimworld to produce a photorealistic, explorable 3D world from a single equirectangular panorama — uses the geniesimworld create CLI (Click subcommand), pairs SHARP + DA360 to fuse panorama RGB with metric depth, and optionally upscales with Real-ESRGAN.

When should I use Generate World?

Generate World fits situations like: asks to generate a world; make a scene from a photo; create a world from a panorama; references geniesimworld / a .png panorama input.

How do I install Generate World in Claude Code?

Run `npx skills add AgibotTech/genie_sim --skill generate-world -a claude-code`. Or copy the skill folder (source/geniesim_world/skills/generate-world in AgibotTech/genie_sim) into .claude/skills/generate-world in your project. Claude Code loads it when a task matches its description.

How do I install Generate World in Codex?

Run `npx skills add AgibotTech/genie_sim --skill generate-world -a codex`. Or copy the skill folder (source/geniesim_world/skills/generate-world in AgibotTech/genie_sim) into .agents/skills/generate-world in your project. Codex loads it when a task matches its description.

Can I use Generate World in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AgibotTech/genie_sim --skill generate-world -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/generate-world, .gemini/skills/generate-world, .github/skills/generate-world and .opencode/skills/generate-world in your project.

What does Generate World need to run?

Going by SKILL.md and its folder, Generate World needs the command-line tools its instructions call (pip and conda). Our summary lists: Python 3.

Does Generate World access the network?

SKILL.md names 3 domains. In commands or code: download.pytorch.org and github.com; the agent is likely to contact these when it follows the instructions. As links in the text: arxiv.org. This is read from the text; nothing was executed.

Is Generate World safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Generate World use?

Generate World is published under the MPL-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Generate World use?

About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Generate World?

Skills that share tags, products or a category with Generate World: HyperFrames Media Use (heygen-com/hyperframes, 58k stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Generate Image (ynulihao/AgentSkillOS, 617 stars) and GPT Image Generation CLI (wuyoscar/GPT-Image2-Skill, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Generate World?

AgibotTech (a GitHub organization) maintains it in AgibotTech/genie_sim, which has 1,413 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on September 7, 2026.

Source: AgibotTech/genie_sim on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Generate World

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

When to Use

Critical Patterns

Workflow

Step 1 — Verify the layout

Step 2 — Create a clean env and install

Step 3 — Generate a world from a panorama

Step 4 — Inspect the work-dir

Step 5 — (🚧 W.I.P.) Feed into a Genie Sim scene

Commands (copy-paste summary for the user)

Notes

Resources

Files

Compare with similar skills

Similar skills

More from AgibotTech/genie_sim

Related

Questions about Generate World