mcpField
L
layer-environments

layer-environments

github.com/layeraiOther70 installsUpdated today
Repository

About layer-environments

layer-environments is a Layer skill for planning game environment art, parallax backgrounds, skyboxes, and generated worlds. It guides game artists through structuring scenes for readable gameplay and exporting layered backgrounds for supported engines.

Key features

  1. 01Plan depth tiers and gameplay-safe backgrounds
  2. 02Split scenes into parallax layers
  3. 03Export parallax for Godot, Unity, or JSON
  4. 04Create equirectangular skyboxes
  5. 05Generate and complete world drafts

Use cases

  1. 01Design a readable platformer background
  2. 02Prepare a looping parallax scene for an engine
  3. 03Create a 360-degree sky panorama
  4. 04Iterate on a world draft before completion

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/layerai/skills --skill layer-environments

After installing, type/layer-environmentsin Claude Code to confirm it loaded.

Details

From the project README

Layer Environments

Overview

An environment is the art the player looks through, not at. It has to hold depth, sit behind gameplay without competing with it, and, for a parallax background, come apart into layers that move at different speeds and still line up.

Generation mechanics (model discovery, the estimate gate, uploads, polling) are in the layer skill; prompt craft is in layer-image. Characters and props are in layer-game-assets, isometric and hex tiles in layer-tilesets, and tiling surfaces in layer-textures.

If a sibling skill named here is missing from your available skills, ask the user to install it (npx skills add layerai/skills --skill <name>); unattended, proceed from tool schemas and flag the gap.

Quick reference

DeliverableHow
Environment concept arttext_to_image; name camera height and depth tiers
Parallax backgroundGenerate one scene, then execute_forge with parallax on an inpainting or erase_object model
Parallax for an engineexport_parallax on the split's output, engine GODOT, UNITY or JSON
360 skyboxuse_case: "create_skybox" with projection: "EQUIRECTANGULAR"
Worlduse_case: "text_to_world" or "image_to_world"; iterate with draft: true where the model offers it

Environment concept art

Name the camera height and the depth tiers, because these decide whether a background sits behind gameplay. Say which tier the art belongs to: foreground silhouette, midground playable band, far background. Keep contrast and saturation deliberately low where characters will stand. The most common note on generated game backgrounds is that they are too busy to read characters against.

Parallax: one scene, split by depth

Do not generate parallax layers one at a time. Separate runs never share a horizon, a light, or a vanishing point, and export_parallax refuses them: it takes only the output of a parallax split.

The split is one execute_forge run with the finished scene as init_image and parallax set, on a model found with list_base_models and filter.use_case: "inpainting" or "erase_object". That model fills in what each nearer layer hides. Given no prompt, an inpainting model is told to continue the scenery, which is usually what you want.

parallax takes three fields:

  • layers: 2 to 6, default 5.
  • cuts: where to slice, as ascending nearness values between 0 and 1, one fewer than layers. Omit it to cut at the gaps in the scene's own depth, which is the right default.
  • loop: every layer repeats left to right, each plate healed across its wrap.

The output is one layered PSD, farthest layer at the bottom, with each layer's scroll speed recorded. Pass its file_id to export_parallax with the engine: GODOT writes a Parallax2D scene for Godot 4.3 or later, UNITY writes sprites with their .meta and a parallax.json of scroll factors, and JSON writes the images and parallax.json for any engine. Every layer is written at the background's full size, so placed at one point they line up. The export spends no Creative Units.

A split bills one run of the model per layer except the nearest, and loop adds one heal per plate. Estimate it with exactly the inputs the run will get, parallax included, before deciding.

Compose the scene for splitting

The split can only separate what the scene already separates. Prompt the source for it:

  • Side-on camera, wide frame. A side-scroller background is landscape; filter for landscape_16_9 when choosing the model.
  • Distinct depth bands with air between them: sky, far range, midground, near foreground. A single tree that runs from the near edge into the far hills will be cut through.
  • A quiet gameplay band. Low contrast where characters stand, detail kept to the far layers and a sparse foreground silhouette.
  • For a loop, no unique landmark. A lone castle on one plate repeats every screen width.

Skyboxes

A skybox is a 2:1 equirectangular panorama whose left and right edges meet and whose poles settle. Find a model with filter.use_case: "create_skybox" and pass projection: "EQUIRECTANGULAR". Do not also set tileability; the projection already makes the wrap. Leave width and height unset to get the model's largest 2:1 preset, or use one of the presets get_base_model lists. Prompt the sky and the horizon, not a subject: anything framed as a focal point is stretched across the poles.

Worlds

A world is its own modality, found with filter.use_case: "text_to_world" or "image_to_world". Where get_base_model reports capabilities.draft, iterate on cheap drafts with draft: true, then complete only the one you keep: execute_forge with base_model_id set to the draft's draft.completion_base_model_id, batch_size: 1, and the draft's file_id as a guidance file of type draft_world, with no prompt. The completion keeps the draft's scene, has a flat price, and can happen once. Check draft.status first: an EXPIRED draft must be generated again.

Worked example

"A looping four-layer forest background for our Godot platformer."

  1. list_base_models with filter.use_case: "text_to_image" and filter.capabilities: {landscape_16_9: true} (an object of booleans). Take the first result.
  2. Prompt the source: "Side-on view of a misty pine forest for a 2D platformer background, wide landscape. Four distinct depth bands with clear space between them: pale sky, distant blue mountains, a midground of pine trunks, a sparse dark foreground of ferns along the bottom edge. Low contrast and muted greens in the middle band where characters run. No buildings, no single landmark." Estimate, execute with batch_size: 4, poll at poll_interval_seconds, pick one.
  3. list_base_models with filter.use_case: "inpainting". Take the first result.
  4. estimate_forge_price with that model, the chosen scene's file_id as init_image, batch_size: 1, no prompt, and parallax: {layers: 4, loop: true}. The estimate prices the per-layer runs and the loop heals together. Above 20 CUs, show the price and wait for an explicit yes.
  5. execute_forge with the same input; poll at poll_interval_seconds. Report any degraded reference set.
  6. export_parallax with the PSD's file_id, engine: "GODOT", and a name. Hand back the zip link and point the user at its README.

Common mistakes

  • Generating each parallax layer as a separate run. They will not line up, and export_parallax refuses them.
  • Running the split on a plain generation model instead of an inpainting or erase_object one.
  • A source scene with one object spanning several depth bands, which the split cuts in half.
  • Passing cuts with the wrong count: it is always one fewer than layers.
  • A busy, high-contrast gameplay band that characters cannot read against.
  • A unique landmark in a looping background.
  • Setting tileability on a skybox, or framing a focal subject that stretches across the poles.
  • Completing a world draft with a new prompt, or completing an expired one.

Comments

Markdown supported