framework-internals
0
sqlite-extension-generator
Generate optimized SQLite extensions in C, Rust, or Mojo
codetalcott
development
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
framework-internals
0
python-flynt-f-string-converter
Use flynt to convert old Python string formatting to f-strings. Activate when: (1) Converting %-formatting to f-strings, (2) Converting .format() calls to f-strings, (3) Modernizing string concatenation to f-strings, (4) Improving code readability through f-string adoption, or (5) Batch-converting legacy Python codebases.
FlexNetOS
development
framework-internals
0
torch-shape-validator
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.
omriwen
development
framework-internals
0
unsloth-kernel-optimization
Optimize and implement GPU kernels using CubeCL for memory-efficient LLM training
tzervas
development
framework-internals
0
path-tactics
Use ComputationalPaths path tactics to automate common RwEq goals (path_simp/path_auto/path_normalize), and structure calc-based proofs cleanly.
Arthur742Ramos
development
framework-internalsmarketplace
0
manage-memories
Memory layer operations for persistent session storage
cuioss
development
framework-internals
0
code-optimizer
Otimizador automático de código usando análise evolutiva GEPA para melhorar qualidade, performance e manutenibilidade
automacoescomerciaisintegradas
development
framework-internals
0
python-pro
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, analytics tools, performance profiling, or any Python heavy lifting.
ak-eyther
development
framework-internals
0
torch-compile
Optimize PyTorch with torch.compile (TorchDynamo/Inductor), focusing on compile overhead, graph breaks, and benchmark methodology. Use when speeding up PyTorch models or debugging compile behavior; triggers: torch.compile, torchdynamo, inductor, graph break, pytorch optimization.
cuba6112
development
framework-internals
0
loop-vectorizer
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.
omriwen
development
framework-internals
0
numpy-core
Fundamental NumPy operations including ndarray creation, dtypes, shape manipulation, and basic operations with a focus on memory alignment and data views. Triggers: numpy, ndarray, dtype, reshape, memory alignment, array-creation.
cuba6112
development
framework-internals
0
skill-with-scripts
A template for skills that include executable code for deterministic operations.
beshkenadze
development
framework-internals
0
autofix-type-conversion
Fixes type mismatch errors by adding appropriate casts or conversions.
hyz0906
development
framework-internals
0
ffi-bindings
Create FFI bindings between Lean 4 and C code. Use when working with foreign functions, native libraries, Metal, or system APIs.
nathanial
development
framework-internals
0
unsloth-qlora
Advanced 4-bit quantization techniques using Unsloth and BitsAndBytes for extreme VRAM efficiency (triggers: QLoRA, 4-bit, load_in_4bit, bnb-4bit, VRAM optimization, dynamic quantization).
cuba6112
development
framework-internals
0
discoverymarket-scan
Analyze the competitive and adjacent solution landscape to surface differentiation opportunities.
edwardmonteiro
development
framework-internals
0
embedded-thinking
提供嵌入式系统软硬件协同思考框架，涵盖硬件层、软件架构、资源约束、实时性、测试调试五大维度。当需要设计嵌入式应用、评审物联网系统、或需要全局视角审视 MCU/MPU 与软件配合时使用。支持裸机/RTOS 选型、功耗优化、内存预算、中断响应、OTA 升级等嵌入式特有场景决策。
tikazyq
development
framework-internals
0
gpu-parallel-scheduling
GPU-safe parallel processing patterns for KINTSUGI to prevent OOM crashes and ensure Jupyter-compatible progress output
smith6jt-cop
development
framework-internals
0
vm-interpreter
Exploiting custom interpreters and virtual machines
amattas
development
framework-internals
0
adding-features
Step-by-step guide for adding new feature modules to the renderer process using feature-based architecture
eretica
development
framework-internals
0
numpy-memory
Deep dive into memory layout, including strides, C vs Fortran order, and zero-copy view generation via stride tricks. Triggers: strides, C-order, Fortran-order, memory locality, stride_tricks.
cuba6112
development
framework-internals
0
lean-hit-development
Guides adding new Higher Inductive Types to the ComputationalPaths library. Use when creating new HITs, defining fundamental group (pi1) calculations, implementing encode-decode proofs, or adding new topological spaces.
Arthur742Ramos
development
framework-internals
0
ultra-performance-resilience-specialist
Experto en optimización de bajo nivel. Su misión es garantizar 60 FPS constantes, gestión de memoria eficiente mediante Isolates y disponibilidad offline total.
F4TB0Yz
development