lilo-labs-plugins

Drive a live Blender session from Claude Code. Model procedurally with Blender Python, generate organic meshes through a pluggable backend (your own GPU or a paid API), and gate every result on real geometry - non-manifold edges, topology, UVs, scale, polycount - before it can be exported.

1 skill · 5 commands · 1 MCP server · hooks

Search and deliver from a local game-asset library. Indexes packs and individual assets by concept taxonomy, licence and the work each needs before it is usable.

1 skill · 5 commands · 1 MCP server

Review a pull request as a conversation instead of a diff. Publishes the request as a page you can talk to Claude inside, then writes the discussion back to the PR and merges on your approval.

1 skill · 2 commands · hooks

Paint a 3D model for multi-filament printing from a single command. Finds each feature by looking from many angles and lightings, lets the mesh's own geometry draw every boundary, iterates with you to confirm what they are, offers colour plans, and writes an Orca/Bambu-ready 3MF with the geometry preserved byte-for-byte.

1 skill · 1 command · hooks

Capture thoughts as a checklist during conversations and surface them to Claude at the right time

1 skill · 1 command · hooks

Turn one character image into a finished, engine-ready sprite sheet. Vision rigs the character into parts and joints, a deterministic skeletal animator draws fifteen animations and 8-direction movement from those parts, and the build measures its own output: a clip that comes apart has the responsible swing damped and reported, a transform is not allowed to break what the artist drew in one piece, and a walk keeps its feet on the floor. Exports to Unity, Godot, Phaser, GameMaker, RPG Maker and Unreal with every output frame provably built from the source's own palette.

1 skill · 1 command

Interactive visual architecture diagrams that stay in sync as Claude works. Auto-layout, live SSE updates, comment-driven interrupts.

1 skill · hooks

Convert a folder of mixed-format documents (PDF, DOCX, XLSX, CSV, PPTX, EML, VSDX) into clean, polished, chunkable markdown — with embedded image descriptions, deterministic noise cleanup, LLM-driven semantic polish, and verification against snapshots to prove no content was lost.

1 skill · 1 command