Diagnose and fix 3DGS training-time failures: NaN losses, OOM crashes, divergent optimization, floater artifacts, densification failures, hyperparameter sensitivity. Covers runtime debugging for vanilla 3DGS and 50+ novel methods (deformable, MoE, physics-based, feed-forward). Detects 50+ runtime failure patterns. Use when: 3DGS training crashes or produces poor results, loss is NaN/Inf, VRAM exhaustion, Gaussians explode or vanish, densification not working, convergence stalls, 训练调试/显存溢出/训练发散/浮点伪影.
$npx -y skills add jaccen/awesome-gaussian-skills --skill 3dgs-training-debuggerInstalls into the current project.
Run `npx skills use "https://github.com/jaccen/awesome-gaussian-skills" --skill "jaccen/awesome-gaussian-skills/3dgs-training-debugger"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/jaccen/awesome-gaussian-skills" that are relevant to the current task. Run `npx skills add "https://github.com/jaccen/awesome-gaussian-skills"` and select the relevant skills, then follow their instructions.