Discover tools framework internals skills, compare source repositories and read the instructions for each workflow.
Provides performance optimization guidelines for profiling, caching, memory management, and concurrency. Use when optimizing slow code, fixing memory leaks, improving throughput, or conducting performance revie...
Provides performance optimization guidelines for profiling, caching, memory management, and concurrency. Use when optimizing slow code, fixing memory leaks, improving throughput, or conducting performance revie...
Extract invariants from specification, encode in types/structure, enable single-pass construction.
Use when optimizing Swift code performance, reducing memory usage, improving runtime efficiency, dealing with COW, ARC overhead, generics specialization, or collection optimization
Use when writing Zig code. Contains Zig 0.15 API changes and patterns.
Hardware chip semantic versioning scheme for IC modules. Defines MAJOR.MINOR.PATCH conventions for RTL design and verification changes.
Use this skill when receiving any task that might benefit from parallel execution. Auto-detects parallelizable work patterns based on task description and suggests optimal execution strategy (Claude sub-agents,...
Simulate whole-brain emulation core processes.
Guide for adding new opence native skills to the workflow
Эксперт Python разработки. Используй для Python best practices, async, typing и ecosystem.
Helps write FTC robot code using the FTCLib library. Use for command-based programming, subsystems, GamepadEx input handling, Pure Pursuit path following, or vision pipelines.
Transform natural language requests into complete GPU CLI workflows. The ultimate skill for Mac users who want to run NVIDIA GPU workloads without configuration complexity. Describe what you want, get a working...
Compound Engineering workflow for AI-assisted development. Use when planning features, executing work, reviewing code, or codifying learnings. Follows the Plan -> Work -> Review -> Compound loop where each unit...
Explain how code implementations work
Test skill to validate skill loading mechanism
Provide architecture-specific GPU optimization advice for NVIDIA GPUs (Ampere, Hopper, Ada). Use when discussing GPU architecture features, compute capability, or hardware-specific optimizations.
Optimize CUDA kernels and GPU code for performance. Use when reviewing CUDA code, analyzing performance, or suggesting GPU optimizations.
Design new unit modules for dimtensor. Use when creating astronomy, chemistry, engineering, or other domain-specific units.
Refactor PyTorch code to improve maintainability, readability, and adherence to best practices. Identifies and fixes DRY violations, long functions, deep nesting, SRP violations, and opportunities for modular c...
Debug PyTorch issues systematically. Use when encountering tensor errors, CUDA out of memory errors, gradient problems like NaN loss or exploding gradients, shape mismatches between layers, device conflicts bet...
Interface nil trap - typed nil is not nil
Apply performance optimization patterns for game loop, rendering, and state updates. Use when discussing frame rate, optimization, profiling, or when editing core game loop code. Auto-apply when user mentions "...
Optimizes outputs by interpreting underspecified prompts before execution. Analyzes user input, infers missing context and specifications, then executes an enhanced version. Produces better results directly rat...
Update a Raycast extension to the latest version
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.