perf-analyzer
Analyzes performance benchmarks from CUDA, CPU, memory tests. Parses output, identifies bottlenecks, tracks metrics over time, generates optimization insights.
Discover tools framework internals skills, compare source repositories and read the instructions for each workflow.
Analyzes performance benchmarks from CUDA, CPU, memory tests. Parses output, identifies bottlenecks, tracks metrics over time, generates optimization insights.
Guides performance analysis and optimization for any application. Use when diagnosing slowness, optimizing code, improving load times, or when asked about performance.
Build the C++ backend using CMake. Use when user asks to compile, build, rebuild, or mentions CMake, compilation errors, or linking issues.
Identify and execute independent operations in parallel for 3-5x speedup. Auto-analyzes task dependencies, groups into batches, launches parallel Task() calls. Applies to /optimize (5 checks), /ship pre-flight...
Generate optimized SQLite extensions in C, Rust, or Mojo
Advanced memory management techniques for the OpenCode memory system
Reviews memory optimization patches using a 5-persona peer review system. Requires unanimous approval backed by benchmarks. Bugs discovered during review are valuable - invoke /validate-correctness to validate...
Measure, compare, and improve eo-processor performance safely. Use when adding/changing Rust compute kernels, refactoring hot paths, or making performance claims. Provides a repeatable benchmark protocol with c...
Implement or modify a Rust function exposed to Python via PyO3 in eo-processor. Use when adding new compute kernels, fixing numerical/shape bugs in the Rust core, or wiring Rust functions into the Python module...
Astral社製ツール(uv, Ruff, ty)でPython開発環境を構築。プロジェクト作成、依存関係管理、コード品質改善、CI/CD設定時に使用。
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use for ML training, analyt...
Feature development using DPPM framework (Discover, Plan, Prototype, Monitor). Use for feature planning and multi-agent orchestration.
Feature development using DPPM framework (Discover, Plan, Prototype, Monitor). Use for feature planning and multi-agent orchestration.
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use for ML training, analyt...
Audit and remove unnecessary abstractions from the codebase. Use when user wants to simplify, reduce dependencies, or eliminate complexity that slows down AI agents.
Add two integers and respond in a fixed format.
Backend Compiler Expert
Takes the dual of a linear program (LP). Use when the user provides an LP in LaTeX or markdown and wants its dual, or asks about LP duality transformations.
Your approach to handling ffi memory management. Use this skill when working on files where ffi memory management comes into play.
Your approach to handling ffi bindings. Use this skill when working on files where ffi bindings comes into play.
Add tensor shape validation and documentation to PyTorch code. This skill should be used when working with PyTorch models to ensure tensor shapes are correct and well-documented with inline comments.
Add comprehensive type hints to Python functions and methods, including PyTorch tensor types. This skill should be used when improving code quality through static type checking or when preparing code for mypy v...
Handle complex-valued tensors in PyTorch for astronomical imaging applications. This skill should be used when working with Fourier transforms, phase/amplitude representations, and complex arithmetic in PRISM.
Convert Python loops to vectorized PyTorch tensor operations for performance. This skill should be used when optimizing computational bottlenecks in PyTorch code during Phase 4 performance optimization.
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.