agentleFS
worldlabsaiworldlabsai/skills/skills/worldlabs/SKILL.md

worldlabs

Skill9 starsChanged 30 days agoApache-2.0View on GitHub

Generate and edit scene images, estimate cameras and depth, reconstruct Gaussian splats, or extract meshes with World Labs, through its connected tools or its CLI.

  • Reads credentials
  • Sends data out

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. OpusGameLabs/game-creator★ 360same name
    2. sandraschi/worldlabs-mcp★ 24same name
    3. JustinPerea/nebula-nodes★ 23same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If World Labs tools are connected (list_projects, import_image, create_image_upload, estimate_camera_depth, get_operation, get_asset), use …

    line 11
  2. Very specific:

    Before estimating, name the project and say the task uses its World Labs Developer API credits.

    line 14
  3. Distinctive:

    Read the documentation before submitting work.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

World Labs

Choose a path

  • If World Labs tools are connected (list_projects, import_image, create_image_upload, estimate_camera_depth, get_operation, get_asset), use them to estimate a camera and depth from one image. The connected tools cover only this task.
    • Pick a project from list_projects whose available_tools include estimate_camera_depth; ask when several fit.
    • Get the image into that project. For a file attached in the chat, call import_image. For a local file, call create_image_upload with its type and exact size, upload the bytes to upload_url with an HTTP PUT that sends exactly the returned headers (for example curl -X PUT -H 'content-type: image/jpeg' --upload-file photo.jpg '<upload_url>'), and use the returned asset_id. Never put image bytes in a tool argument.
    • Before estimating, name the project and say the task uses its World Labs Developer API credits. Reuse the same idempotency_key when retrying, and poll get_operation until done.
  • With a local shell, use the CLI below for tasks the connected tools do not cover, or for every task when they are not connected.
  • With neither, say which task the user wants is unavailable here, and that connecting World Labs or installing the CLI makes it available.

Use the CLI

Use worldlabs for the Developer API. Requires Node 22+ and @worldlabsai/cli. If worldlabs is missing, locate the user-provided CLI executable or install @worldlabsai/cli@0.3.0 with npm. Use the resolved executable consistently; do not assume plugin installation installs the CLI. Run worldlabs --help for command syntax and worldlabs tasks list for task names; account access can differ.

Read the documentation before submitting work. It is maintained with the API; where it differs from this skill, follow the documentation.

  • CLI: uploading assets, submitting request JSON, retrying with idempotency keys, waiting, and downloading results.
  • How to use Atlas: which task fits, scene data, cameras and depth, and chaining tasks. Follow its links for each task's fields.
  • Generate a video or camera path: read before any video or flythrough.
  • Splat best practices: read before posedImages2Splats.

A posedImages2Splats run usually takes about 20 minutes. Submit it without --wait, keep the operation ID, and check on it with worldlabs operations wait <operation-id> --json until it is done. Don't resubmit while it runs.

Authentication

Check worldlabs auth status. If login is needed, have the user run worldlabs auth login in their own terminal and enter the key privately. Never request keys in chat or put them in command arguments. Automation can supply WLT_API_KEY. The key selects the API project and billing; a successful status check verifies asset access, not every task permission.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.