add-rule
Add a new rule to the learned rules file
Discover tools framework internals skills, compare source repositories and read the instructions for each workflow.
Add a new rule to the learned rules file
O(n) instead of O(n log n)
avoid redundant computation
Generate CANN Ascend C operator code from Python reference
Optimize layers and use minimal base images.
Translate PyTorch implementations to Triton GPU kernels incrementally. Use when converting PyTorch code to Triton, optimizing GPU kernels, auditing/reviewing existing Triton code, or when user says "triton", "c...
Emit C output and a C header for embedding X07 in C/C++ via x07c --emit-c-header.
O(n) to O(1)
1M ops to 2K ops
Rust serialization/deserialization framework for JSON, YAML, TOML, and more.
enables hardware acceleration
Optimization standards for rebuilds and memory.
Expert performance analysis and optimization. Use when analyzing performance issues, optimizing slow code, reducing bundle size, or improving application speed.
Optimize mode for refactoring, performance improvement, and code cleanup. Use when user requests optimization or identifies slow code. Measures baseline, identifies bottlenecks, improves without changing behavi...
Optimize Sunset Pipeline Moonshot Integration for 32GB RAM + RTX 3060 GPU environment with practical scaling, resource-efficient implementations, and achievable milestones. Use when implementing AI development...
This document serves as some special instructions when working with Convex.
Implements visual shaders and shader code for 2D/3D effects including dissolve, outline, water, post-processing, and custom materials. Use when creating custom visual effects.
Implements optimization techniques for rendering, scripting, memory, and physics performance. Use when improving game performance for release.
Ottimizzazione Semantica e Fisica del Pensiero (SPAr).
Implements optimization techniques for rendering, scripting, memory, physics, and networking. Use when improving game performance, reducing lag, or preparing for mobile/low-end devices.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.