agentsclimarketplace

Scene to layout

Skill wjlgatech/design-anything/skills/scene-to-layout

Any design intent in (text, picture) → execution-ready 3D blueprint out — construction- and 3D-print-verified. Game design · simulation · architecture (3DCP+AI) · interior · landscape.

Install
npx -y skills add wjlgatech/design-anything --skill scene-to-layout

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 18 days oldThe repository was created 18 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Turn a room photo, scan, or point cloud into a structured layout — walls, openings, furniture as typed objects with dimensions — using SpatialLM-class models, ready for blueprint-validate and re-design. Trigger: "here's a photo of my room", "measure this space", "redesign from this picture".

The file declares its own license as CC-BY-4.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.8 KB, as published. Nobody here has run it

scene-to-layout

When to use

The input is a picture (the repo's second input modality) rather than text — an existing room/site that must become structured data before redesign.

What it does

  1. Route by input: photo → monocular layout estimation; scan/point-cloud → SpatialLM (https://github.com/manycore-research/SpatialLM); floor-plan image → wall/opening extraction.
  2. Emit a structured layout JSON: walls (start/end/height/thickness), openings (type/position/size), furniture (class/bbox/orientation), declared units.
  3. State per-element confidence; dimensions estimated from a single photo are marked ESTIMATED and need one user-confirmed reference measurement.
  4. Hand off to blueprint-validate (audit) or brief-to-blueprint (redesign).

Example

"Photo of a 4x5m living room + 'the door is 80cm' reference" → layout JSON with scaled dimensions → "now add a reading corner with daylight" → redesign loop.

Verification (eval-with-teeth)

Output JSON must round-trip: rendered back to a 2D plan, wall topology is closed (rooms are bounded polygons) and openings lie on walls. An unclosed room polygon is a failed extraction — report it, don't patch it silently.

Safety

Never claim measured accuracy from an unreferenced photo; renovation decisions need a tape measure.

Cross-runtime

Model access varies by runtime; degrade to "ask user for measurements" when no vision/SpatialLM backend is available (skip-not-fail).

Gives 0 of the 12 instructions most ui components skills give

Counted across 343 of the 344 authors here whose files we hold, read 2026-08-06

  • Make touch targets at least 44x44 pixelsin 48 of 343, across 17 files
  • Use SVG icons instead of emojisin 39 of 343, across 12 files
  • Ensure minimum color contrast of 4.5:1in 36 of 343, across 9 files
  • provide visible focus rings on interactive elementsin 26 of 343, across 10 files
  • Use semantic color tokens instead of raw hex codesin 26 of 343, across 10 files
  • Generate a design system before codingin 23 of 343, across 6 files
  • Respect prefers-reduced-motion user settingsin 22 of 343, across 6 files
  • use semantic html elementsin 21 of 343, across 14 files
  • use semantic tailwind colorsin 19 of 343, across 6 files
  • Match style to product type and industryin 18 of 343, across 2 files
  • use consistent design tokensin 18 of 343, across 6 files
  • build complex interfaces from composable primitivesin 18 of 343, across 6 files

Said here and by no other author read

  • route input by type to the correct extractor
  • emit a structured layout JSON
  • include walls, openings, and furniture in the JSON
  • state per-element confidence in the output
  • mark dimensions estimated from a photo as ESTIMATED
  • require one user-confirmed reference measurement

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.