type-hints-for-ml-code
Apply appropriate type hints for ML/PyTorch code. Use when adding type annotations to ML code or addressing mypy errors.
发现 tools framework internals 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Apply appropriate type hints for ML/PyTorch code. Use when adding type annotations to ML code or addressing mypy errors.
Optimize training performance for Kaggle competitions. Use PROACTIVELY when training is slow, GPU memory issues occur, or user asks about performance tuning. Keywords: 遅い, 最適化, OOM, CUDA, batch_size, num_w...
Set up GPU sandboxes for interpretability research. Use when writing setup.py scripts with Sandbox, SandboxConfig, ModelConfig, or create_notebook_session. Provides the exact API for Modal GPU environments - MU...
AI-assisted development workflow with TDD, context management, and incremental implementation. Use when developing features with AI assistance, managing code context for AI tools, implementing features step-by-...
Expert knowledge for building event-driven systems with Composable Rust framework. Use when implementing reducers, designing state machines, working with effects, creating environment traits for dependency inje...
Rust development patterns for video processing, trait abstractions, error handling, and Linux device interaction
Structured performance profiling and optimization skill for identifying and eliminating bottlenecks. Auto-triggers on slowness keywords.
Avoid non-null assertion operator (!) and use type-safe alternatives instead
Deep code and system analysis using the Quantum Cognitive OS. Use when analyzing code, architectures, or complex systems that benefit from multi-dimensional reasoning.
Use Syntax::Keyword::Assert for zero-cost assertions in Perl
Store and export type constraints for Type::Tiny, Moose, Data::Checks, and more
Pure Data reference documentation for audio patch development. Use when writing .pd patches, working with OSC/audio/sampling, or implementing Pure Data code.
Guide for using the Neural DSP Quad Cortex device library in MMD files. Use when the user mentions Quad Cortex, QC, Neural DSP guitar processor, or needs help with preset loading, scene switching, expression co...
Comprehensive F* proof-oriented programming for formal verification including dependent types, refinement types, effect system, SMT solver integration, tactic-based interactive theorem proving, and verified cod...
Use Result::Simple for tuple-based error handling in Perl
Guides performance optimization: atomic clock service, performance monitoring, memory optimization, battery optimization. Use when optimizing performance, monitoring metrics, or improving app efficiency.
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 of...
Iteration 2 of Multiplicity Cascade - Amplifies jank recursively through iterations
Implement features and tasks defined in openspec proposals.
Implements concise, streamlined Python code matching exact architect specifications. Use when writing Python code, creating modules, or when the user asks to implement features in Python.
Add a new base field to an aggregate with clear rules for:
Optimize code for speed and efficiency. Use this skill when profiling, identifying bottlenecks, or improving performance. Covers profiling tools, common patterns, and optimization strategies.
avoids unnecessary computation
Define module boundaries, shared kernel, and anti-corruption layers.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。