i18n-translate
Use when translating changed keys from `_locales/en-US.ts` into one or more sibling locale files while preserving structure, placeholders, tags, and product terms.
1.23k repo starsObserved in 2 repos
Development
Development skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
cache-dit-model-integration
High-level guide for integrating a new DiT model into cache-dit: Cache (BlockAdapter/ForwardPattern), Context Parallelism, Tensor Parallelism, Text Encoder Parallelism (TE-P), VAE Parallelism (VAE-P), generate CLI, installation, testing workflow, and detailed references. Use when adding support for a new diffusion transformer model in cache-dit.
1.23k repo starsObserved in 1 repos
Development
cuda-cpp-kernel
Use when writing, debugging, porting, reviewing, or optimizing CUDA C++ or PTX kernels; investigating CUDA Runtime or Driver API behavior; profiling kernels with Nsight Systems or Nsight Compute; or reasoning about Tensor Core instructions, shared memory, bank conflicts, occupancy, async copy, TMA, WGMMA, and architecture-specific behavior on Ampere, Hopper, or Blackwell.
1.23k repo starsObserved in 1 repos
Development
cute-dsl-kernel
Use when writing, modifying, porting, or optimizing CuTe DSL GPU kernels in Python; reading CuTe DSL API reference material; integrating a CuTe DSL kernel into a project; or rewriting an existing CUDA or C++ operator into CuTe DSL while preserving correctness and performance expectations.
1.23k repo starsObserved in 1 repos
Development
cutlass-cpp-kernel
Use when writing, debugging, porting, reviewing, or optimizing CUTLASS or CuTe C++ kernels and templates; navigating CUTLASS examples, collectives, epilogues, pipelines, GEMM schedules, or CuTe headers; or analyzing template configuration, tiling, memory movement, and kernel structure for Hopper or Blackwell GPUs.
1.23k repo starsObserved in 1 repos
Development
operator-migration
Use when doing operator migration or kernel migration for CUDA, Triton, or custom ops in cache-dit; porting kernels from nunchaku, deepcompressor, or other repos; designing operator registration and public wrappers; wiring build and packaging for optional extensions; or reviewing an operator migration plan. Guides survey, minimal-closure migration, API design, extension loading, packaging, and layered validation. Do not use for blind copy-paste ports.
1.23k repo starsObserved in 1 repos
Development
ptq-workflow-integration
Use when integrating a new PTQ workflow into cache-dit; designing quantize/load API shape, backend-specific config validation, save/load manifests, benchmark and regression tests, or reviewing a PTQ integration plan. Uses the SVDQ PTQ integration only as a style and coverage reference. Do not copy the SVDQ implementation mechanically.
1.23k repo starsObserved in 1 repos
Development
triton-kernel
Write optimized Triton GPU kernels for deep learning operations. Covers the full spectrum from basic vector ops to Flash Attention, persistent matmul, fused normalization, quantized GEMM, and memory-efficient patterns.
1.23k repo starsObserved in 1 repos
Development
implement-comet-expression
Use when implementing a new Spark expression in DataFusion Comet. Walks through cloning latest Spark master to study the canonical implementation, checking the upstream datafusion-spark crate before writing native code, building the Comet serde and Rust wire-up from the contributor guide, then running audit-comet-expression to drive a test-coverage iteration loop.
1.23k repo starsObserved in 1 repos
Development
wire-datafusion-function
Use when wiring an existing DataFusion or datafusion-spark function into Comet for a Spark expression. Identifies the right wiring pattern (one-line passthrough, datafusion-spark UDF registration, or custom serde with input massaging / restrictions), applies the Scala serde, registers the UDF in jni_api when needed, and adds SQL file tests. Assumes the function already exists upstream — if not, switch to `implement-comet-expression`.
1.23k repo starsObserved in 1 repos
Development