Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →bluelovers/generate2dmap
Generate and revise production-oriented 2D game maps with built-in image generation as the default visual asset source, choosing a visual model, runtime object model, collision model, art direction, and engine/export target.
Passed 14 of 19 test cases with the skill, and 4 of 19 without it.
and 14 more in the full report
11 fixed5 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to generate 16 simple environmental items (small rocks, grass tufts, tiny flowers, small pebbles) in a single image generation call. Which prop generation mode should be used?
| Checked | Without skill | With skill |
|---|---|---|
| Selects prop_pack_4x4 for batching 16 simple small props. | Missed | Passed |
The instructions your model reads when the skill loads.
Build the smallest map bundle that satisfies the game. Decide the map as a pipeline, not as a single strategy label:
visual_model: baked_raster | layered_raster | tilemap | layered_tilemap | parallax_layersruntime_object_model: none | separate_props | y_sorted_props | interactive_entities | foreground_occluderscollision_model: none | coarse_shapes | precise_shapes | tile_collision | polygon_walkmesh | trigger_zonesengine_target: raw_canvas | Phaser | Tiled_JSON | LDtk | Godot_TileMap | Unity_Tilemap | project-nativeUse user-specified parameters when present. When the user does not specify them, infer the lightest pipeline from the existing game, camera, collision needs, map scale, and editing needs.
Read references/map-strategies.md when the pipeline choice is not obvious. Read references/layered-map-contract.md before implementing a layered raster map. Read references/prop-pack-contract.md before batching generated props into a sheet.
This skill is image-generation-first for visual assets. Use built-in image_gen as the default creative art source for base maps, dressed references, prop sheets, prop sprites, tileset art, parallax layers, battle backgrounds, and other visible map assets.
The agent must write the creative image prompts itself. Do not use scripts to generate creative prompts or to procedurally draw final visual art. Scripts may assemble, slice, chroma-key, crop, validate, compose previews, emit JSON metadata, and wire image-generated assets into engine-native files such as Godot .tscn scenes.
Only use procedural drawing or scripted placeholder art when the user explicitly asks for placeholders, test fixtures, debug maps, or engine scaffolding without final art. If using an engine target such as Godot_TileMap, generate or reuse the visual tileset art first, then use scripts/code only to build tile layers, collision, zones, and scene wiring.
User-facing parameters may be stated in natural language:
map_kind: overworld | town | dungeon | shrine | arena | battle_bg | side_scroller | tacticalvisual_model: baked raster | layered raster | tilemap | layered tilemap | parallaxsize: pixel dimensions, tile dimensions, or camera-relative sizeperspective: top-down | 3/4 top-down | side-view | isometric-likeart_style: clean_hd | pixel_inspired | retro_pixel | hand_painted | project-nativevisual_asset_source: image_gen | existing_assets | procedural_placeholdercollision_precision: none | coarse | precise | tile | walkmeshprop_generation: none | one_by_one | prop_pack_2x2 | prop_pack_3x3 | prop_pack_4x4output_format: PNG only | layered preview | manifest JSON | engine-native map dataWhen unspecified:
image_gen as the visual asset source.test cases passed, vs 4 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.