Landmark Build-Up
Raise a city landmark in 3D stone by stone, then dismantle it to see inside: the Belém tower course by course, or the Statue of Liberty’s copper skin on its iron frame.
Bring a landmark and its structure: walls, openings, towers and roof. The Skill returns a downloadable Skill (recipe kit, meta prompt, lessons, verification), a runnable scene and a 40-second film.
How it works
Check the real building: storeys, openings, towers, turrets and roof.
Write its recipe.json with the masonry kit and its film.json, then review the build at each stage.
Verify headlessly, build one self-contained HTML file and record the film.
Frequently asked questions
Does it call any model or need a key?
No. The Skill gives your agent a prompt, lessons and a reference scene; the scene itself makes no network calls.
Why is the demo sandboxed?
The frame has an opaque origin and no network access, so the scene can’t read anything from this page or reach the internet.
Is it accurate?
No. It is an interpretive model with simplified proportions and ornament, not a survey.
Can I build another landmark?
Yes. Masonry forms use platforms, walls with openings, battlements, turrets, loggias and roofs; statues use a copper-plate figure, limbs, an iron pylon and armature. The Statue of Liberty example and a brick campanile run on the same code.
Does it work on mobile?
Phones get the low tier and a compact layout, and the scene honours reduced motion. It has been verified under touch emulation, not on real devices.
Why is there no online generation?
Building a new scene needs a model key inside the sandbox, which the backend doesn’t support yet. Run the Skill with your own agent for now.