Claude Skills by RemakeBench

Model what a 3D object is, not merely its outline, and prove quality with geometry-only close-up renders plus a manifest. Use before building, generating, importing, cleaning, reviewing, or signing off on meshes, props, buildings, terrain, environments, levels, dioramas, and set dressing in Blender, game engines, glTF workflows, or image-to-3D tools. Requires functional parts, bevelled light-catching edges, real thickness, and the same standard for every asset.

The build→judge→rebuild loop for MULTI-asset 3D work — whenever a scene, environment, village, level, diorama or any batch of more than ~3 assets is being built (in Blender, via MCP, procedurally, or by generation), and especially when builder subagents are doing the work. The parent orchestrates; builders never self-certify; every "done" claim triggers a FRESH independent judge subagent that sees only renders, manifest and references, and the loop repeats until the judge passes or the operat...

Run OpenAI Codex CLI as an external subagent from Claude Code, either once or as a parallel fanout, through hardened codex-sub and codex-fanout wrappers. Use for independent review, cross-model judging, structured second opinions, image analysis, or isolated passes over files and subsystems, especially when the user says "ask Codex", "ask GPT", "cross-check this", or requests parallel independent workers. Load before invoking the codex binary directly so prompts, timeouts, schemas, images, an...

Plan and route a game or playable 3D demo through art direction, sandbox, environment, character, assembly, atmosphere, gameplay, and shipping. Use at the start of any game-shaped project or when replanning one mid-flight. Coordinates reference-pack-authority, asset-judge-loop, 3d-asset-quality, and verify-by-playing, with a playable placeholder sandbox required before production assets.

Run xAI Grok as a second-model subagent from Claude Code for independent review, cross-checking, structured output, or parallel fanout. Use when the user asks to consult Grok or xAI, when Claude and Codex need a third vote, or when multiple files or candidates benefit from independent passes. Includes safe wrappers, schemas, run artifacts, timeout handling, and an optional MCP shim.

Generate or segment modular video-game asset reference plates for image-to-3D services such as Tripo or Meshy. Use when the user asks for a modular kit, kitbash pieces, character outfit parts, building parts, environment modules, or front/left/right/back multiview references intended for image-to-3D reconstruction; do not use for ordinary cinematic thumbnails or single concept-art images.

How to structure, audit and use a GENERATED reference/concept-art pack before building a 3D world from it — the art-direction stage's exit gate. Load this whenever generating target images (Claude with an image tool, Meshy, or any image model), whenever receiving a reference pack for an environment/level/world build, and BEFORE the first geometry is authored against images. Covers the two-tier authority split (technical plates govern geometry, cinematics govern fidelity), the congruence pass ...

The gameplay acceptance gate — prove interactive software works by PLAYING it with real input, not by green gates, passing tests, code inspection or screenshots of stills. Load this whenever a gameplay change is claimed done, before shipping or demoing any playable build, after integrating a character, controls, camera, level geometry, combat or any input path, and whenever a test suite or validator is green on interactive software. Also load it when writing acceptance checks for a game, so t...