Converts the official documentation for NVIDIA PTX ISA 9.1, CUDA 13.1 (Runtime/Driver), Math API 13.x, cuBLAS 13.2, and NCCL into searchable Markdown, and provides a supporting AI IDE skill library (compatible with Claude Code, Trae, and others), designed to enhance knowledge-driven automation for low-level GPU development and large language model (LLM) inference.
This repository also configures its own agents. See what cuda-code-skill tells them →
ForceInjection/cuda-code-skill
Skill Claude CodeCodex
Generates optimized CUDA kernel code based on performance analysis reports or algorithm type. Reads NCU analysis reports (e.g. analysis.md) and optionally existing kernel code, then produces high-quality compilable .cu files with applied optimizations. Use when the user provides an NCU analysis report or requests CUDA…
ForceInjection/cuda-code-skill
Skill Claude CodeCodex
Debugs CUDA kernel errors using compute-sanitizer (memcheck, racecheck, initcheck, synccheck), cuda-gdb (non-interactive batch backtrace), and cuobjdump (PTX/SASS/register analysis). Use when a CUDA kernel crashes (segfault, illegal memory access), produces wrong results, hangs, or when the user asks to debug or…
ForceInjection/cuda-code-skill
Skill Claude CodeCodex
CUDA kernel development, debugging, performance optimization, linear algebra, and multi-GPU communication for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, parallel algorithms, or CUDA library calls. Covers cuBLAS/cuBLASLt GEMM operations, CUDA Math API (half, bfloat16, FP8, FP6…
ForceInjection/cuda-code-skill
Skill Claude CodeCodex
Orchestrates a full profiling-driven CUDA kernel optimization loop (write → validate → profile → analyze → optimize) until performance converges or no further gains are possible. Capabilities include generating reference implementations, writing initial kernels via cuda-code-generator, running correctness validation…
ForceInjection/cuda-code-skill
Skill Claude CodeCodex
Curated index of NVIDIA official CUDA Samples with code patterns, GitHub permalinks, and key snippets. Use when looking for working CUDA code examples, GPU kernel patterns (reduction, scan, GEMM, transpose, histogram), Tensor Core WMMA usage, CUDA Graphs API, cuBLAS/cuFFT/cuSPARSE library integration, stream/event…
ForceInjection/cuda-code-skill
Skill Claude CodeCodex
Compiles, validates, and benchmarks a CUDA kernel (.cu file) against a Python reference (ref.py). Auto-detects GPU arch and infers dimension args from the extern "C" void solve(...) signature. Runs benchmark.py to: compile with nvcc, optionally validate outputs (exits on failure), benchmark both kernel and reference…
ForceInjection/cuda-code-skill
Skill Claude CodeCodex
Profiles a CUDA kernel with NCU and analyzes the resulting .ncu-rep report to diagnose performance bottlenecks and generate optimization recommendations. Use when the user provides a .cu file or a .ncu-rep file and asks for performance analysis, NCU profiling, or bottleneck diagnosis. If given a .cu file, runs NCU via…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: