Add it to a GitHub README or profile β the card updates as the ranking changes:
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
One desktop app for your coding agents, made for creative work. Early beta, Windows and macOS.
LUMEN, a generative shader studio. 9 WebGL2 art modes plus synth style blending, perfect-loop animation, gradient sets, share codes and PNG/WebM/GIF export. Zero dependencies.
A golden-hour Japanese temple built entirely in code with three.js. No models, no textures, no HDRIs. Rendered offline into a 70s 1080p60 film
A drone flight over the Na Pali coast, rendered entirely in code. No textures, images or models.
Design image-generation skills for coding agents: website comps, mobile app screens, brand kits, and image-to-code.
A 60 second cinematic alpine lake film rendered entirely from code. Procedural terrain, GPU erosion, forest, water, sky and a fully synthesized soundtrack in Python and GLSL.
Real-time procedural cherry blossom landscape in the browser. Volumetric sky, dynamic weather, endless wind-driven meadow, and a fully generated sakura tree. Zero art assets: every texture synthesised at runtime, every mesh built in code. three.js + WebGL2.