3dgs-code-reviewer
This skill analyzes CUDA implementations of 3D Gaussian Splatting techniques, identifying correctness issues and performance bottlenecks in GPU kernels. It draws on comprehensive knowledge of 3DGS methods to provide targeted feedback on memory access patterns, synchronization, and computational efficiency. Perfect for researchers and engineers optimizing rendering pipelines.
3dgs-code-reviewer analyzes CUDA implementations of 3D Gaussian Splatting techniques, identifying correctness issues and performance bottlenecks in GPU kernels. It draws on comprehensive knowledge of 3DGS methods to provide targeted feedback on memory access patterns, synchronization, and computational efficiency, making it ideal for researchers and engineers optimizing rendering pipelines.
AI-generated summary based on this skill's SKILL.md
Install
jaccen/Awesome-Gaussian-Skills/3dgs-code-reviewer · repository language: TypeScript
git clone https://github.com/jaccen/Awesome-Gaussian-Skills
cp -r Awesome-Gaussian-Skills/skills/3dgs-code-reviewer ~/.claude/skills/3dgs-code-reviewerFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does 3dgs-code-reviewer do?
3dgs-code-reviewer analyzes CUDA implementations of 3D Gaussian Splatting techniques, identifying correctness issues and performance bottlenecks in GPU kernels. It draws on comprehensive knowledge of 3DGS methods to provide targeted feedback on memory access patterns, synchronization, and computational efficiency, making it ideal for researchers and engineers optimizing rendering pipelines.
Can 3dgs-code-reviewer review CUDA kernels for 3DGS?
Yes. 3dgs-code-reviewer specializes in reviewing CUDA kernels for 3D Gaussian Splatting implementations. It examines code for correctness and performance bugs, validates memory access patterns, and checks warp-level performance patterns to ensure your GPU kernels meet both functional and efficiency standards.
How does 3dgs-code-reviewer detect rendering artifacts?
3dgs-code-reviewer debugs rendering artifacts by analyzing your 3DGS implementation code in detail. It traces through the rendering pipeline—including alpha compositing, tile-based rasterization, and covariance projection—to pinpoint the source of visual defects and suggest corrections.
What bug patterns does 3dgs-code-reviewer recognize?
3dgs-code-reviewer detects 108+ known 3DGS bug patterns in code submissions. These patterns cover common implementation mistakes across CUDA kernels, loss functions, training pipelines, and rendering stages, enabling rapid identification of issues that would otherwise require manual inspection.
Can 3dgs-code-reviewer optimize my training pipeline?
Yes. 3dgs-code-reviewer optimizes 3DGS training pipelines and validates loss function implementations. It reviews computational efficiency, memory usage, and algorithmic correctness to help you accelerate training while maintaining convergence quality.
What license does 3dgs-code-reviewer use?
3dgs-code-reviewer is released under the Apache-2.0 license, permitting free use, modification, and distribution for both commercial and non-commercial projects.
SKILL.md
rendered from the published skill — quoted content, verbatim
3DGS Code Reviewer
You are a senior graphics engineer and 3DGS implementation expert. Review code for correctness, performance, and adherence
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 2 files
skills/3dgs-code-reviewer/SKILL.md
skills/3dgs-code-reviewer/references/bug-patterns.md