Skip to main content
skillsmp

Menu

Internals Framework

Parcourez les skills pour le développement de frameworks, optimisation de compilateurs et composants bas niveau

Les catégories, les étoiles GitHub et la date de dernière mise à jour à la source servent à structurer et ordonner le catalogue. Ces signaux ne constituent ni une recommandation, ni une certification de qualité, ni un contrôle de sécurité, ni une garantie d’adéquation. Consultez la page du skill et sa source avant utilisation.

22 284 résultats

implement-spec
256.4k
mattpocockmattpocock/skills
Implement a specification in code.

Langue du contenu du Skill : anglais

python-patterns
253.2k
affaan-maffaan-m/ECC
Pythonic イディオム、PEP 8標準、型ヒント、堅牢で効率的かつ保守可能なPythonアプリケーションを構築するためのベストプラクティス。

Langue du contenu du Skill : japonais

pytorch-patterns
253.2k
affaan-maffaan-m/ECC
PyTorch深度学习模式与最佳实践，用于构建稳健、高效且可复现的训练流程、模型架构和数据加载。

Langue du contenu du Skill : chinois

regex-vs-llm-structured-text
253.2k
affaan-maffaan-m/ECC
选择在解析结构化文本时使用正则表达式还是大型语言模型的决策框架——从正则表达式开始，仅在低置信度的边缘情况下添加大型语言模型。

Langue du contenu du Skill : chinois

pytorch-patterns
253.2k
affaan-maffaan-m/ECC
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. Use when writing or reviewing PyTorch training loops, model architectures, or data loading, or when a run will not reproduce.

Langue du contenu du Skill : anglais

accelerate
243.2k
NousResearchNousResearch/hermes-agent
Run PyTorch training across GPUs with minimal changes.

Langue du contenu du Skill : anglais

peft
243.2k
NousResearchNousResearch/hermes-agent
Fine-tune large LLMs with LoRA on limited GPU memory.

Langue du contenu du Skill : anglais

unsloth
243.2k
NousResearchNousResearch/hermes-agent
Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

Langue du contenu du Skill : anglais

darwinian-evolver
243.2k
NousResearchNousResearch/hermes-agent
Evolve prompts/regex/SQL/code with Imbue's evolution loop.

Langue du contenu du Skill : anglais

godmode
243.2k
NousResearchNousResearch/hermes-agent
Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

Langue du contenu du Skill : anglais

flags
142.2k
vercelvercel/next.js
How to add or modify Next.js experimental feature flags end-to-end. Use when editing config-shared.ts, config-schema.ts, define-env-plugin.ts, next-server.ts, export/worker.ts, or module.compiled.js. Covers type declaration, zod schema, build-time injection, runtime env plumbing, and the decision between runtime env-var branching vs separate bundle variants.

Langue du contenu du Skill : anglais

wpf-to-winui3-migration
138.6k
microsoftmicrosoft/PowerToys
Guide for migrating PowerToys modules from WPF to WinUI 3 (Windows App SDK). Use when asked to migrate WPF code, convert WPF XAML to WinUI, replace System.Windows namespaces with Microsoft.UI.Xaml, update Dispatcher to DispatcherQueue, replace DynamicResource with ThemeResource, migrate imaging APIs from System.Windows.Media.Imaging to Windows.Graphics.Imaging, convert WPF Window to WinUI Window, migrate .resx to .resw resources, migrate custom Observable/RelayCommand to CommunityToolkit.Mvvm source generators, handle WPF-UI (Lepo) to WinUI native control migration, or fix installer/build pipeline issues after migration. Keywords: WPF, WinUI, WinUI3, migration, porting, convert, namespace, XAML, Dispatcher, DispatcherQueue, imaging, BitmapImage, Window, ContentDialog, ThemeResource, DynamicResource, ResourceLoader, resw, resx, CommunityToolkit, ObservableProperty, WPF-UI, SizeToContent, AppWindow, SoftwareBitmap.

Langue du contenu du Skill : anglais

caveman
104.2k
JuliusBrusseeJuliusBrussee/caveman
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

Langue du contenu du Skill : anglais

caveman
104.2k
JuliusBrusseeJuliusBrussee/caveman
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

Langue du contenu du Skill : anglais

add-uint-support
102.8k
pytorchpytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.

Langue du contenu du Skill : anglais

at-dispatch-v2
102.8k
pytorchpytorch/pytorch
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.

Langue du contenu du Skill : anglais

cuda-index-width
102.8k
pytorchpytorch/pytorch
Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64_t, canUse32BitIndexMath, CUDA_KERNEL_LOOP_TYPE, or AT_DISPATCH_INDEX_TYPES, and when considering binary-size or performance impact of index-type templating.

Langue du contenu du Skill : anglais

metal-kernel
102.8k
pytorchpytorch/pytorch
Write Metal/MPS kernels for PyTorch operators. Use when adding MPS device support to operators, implementing Metal shaders, or porting CUDA kernels to Apple Silicon. Covers native_functions.yaml dispatch, host-side operators, and Metal kernel implementation.

Langue du contenu du Skill : anglais

pt2-bug-basher
102.8k
pytorchpytorch/pytorch
Debug PyTorch 2 compiler stack failures including Dynamo graph breaks, Inductor codegen errors, AOTAutograd crashes, and accuracy mismatches. Use when encountering torch.compile errors, BackendCompilerFailed exceptions, recompilation issues, Triton kernel failures, FX graph problems, or when the user mentions debugging PT2, Dynamo, Inductor, or compiled model issues.

Langue du contenu du Skill : anglais

plan-change
93.1k
ruvnetruvnet/RuView
Turn a feature request into a minimal, file-level implementation plan before any code.

Langue du contenu du Skill : anglais

triton-kernel-writing
91.5k
vllm-projectvllm-project/vllm
Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation.

Langue du contenu du Skill : anglais

programming
68.8k
code-yeongyucode-yeongyu/oh-my-openagent
Applies strict, modern language practice (typed errors, exhaustive match, TDD) for Python, Rust, TypeScript, and Go. Use for work on .py, .rs, .ts, or .go files.

Langue du contenu du Skill : anglais

dedupe-issue-local
64.9k
warpdotdevwarpdotdev/warp
Repo-specific dedupe guidance for warp. Only the categories declared overridable by the core dedupe-issue skill may be specialized here.

Langue du contenu du Skill : anglais

hyperframes-registry
56.4k
calesthiocalesthio/OpenMontage
Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

Langue du contenu du Skill : anglais

analysis-api-mark-internal-apis
53.4k
JetBrainsJetBrains/kotlin
Drive the per-module internal-API codebase test, then refine the suggested annotations down to `internal` (or up to `@KaImplementationDetail`) based on actual external usage

Langue du contenu du Skill : anglais

decompress-binary
49.2k
ClickHouseClickHouse/ClickHouse
Extract the inner ELF from a ClickHouse self-extracting `clickhouse` binary, including when its architecture differs from the host (e.g. to load an aarch64 CI core dump on an x86 workstation). Use when gdb/lldb needs real symbols from a downloaded CI/release binary, or when self-extraction by running the binary is not possible because of an architecture mismatch.

Langue du contenu du Skill : anglais

fe-modularization
49.2k
metabasemetabase/metabase
Deciding where frontend code lives — tier model, move mechanics, extension points, side effects, naming, and the traps. Use when moving code between modules, carving new modules, fixing boundary violations, adding a barrel or an endpoint, or reviewing module-shape decisions.

Langue du contenu du Skill : anglais

stage-tamagotchi-godot-csharp
48.9k
moeru-aimoeru-ai/airi
Apply engine-local C# development method and code style only when working in `engines/stage-tamagotchi-godot`, including its `.cs` files, `.csproj`, engine-local `.editorconfig`, and Godot-specific C# structure decisions. Do not use for TypeScript, Electron, renderer code, shared workspace config, repo-wide C# conventions, or any file outside `engines/stage-tamagotchi-godot`.

Langue du contenu du Skill : anglais

discourse-upcoming-changes-authoring
47.8k
discoursediscourse/discourse
Use when modifying, debugging, or extending the upcoming changes framework code and system itself.

Langue du contenu du Skill : anglais

opentrons-integration
43.9k
K-Dense-AIK-Dense-AI/scientific-agent-skills
Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow must support multiple robot vendors.

Langue du contenu du Skill : anglais

pennylane
43.9k
K-Dense-AIK-Dense-AI/scientific-agent-skills
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch or JAX. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

Langue du contenu du Skill : anglais

pymoo
43.9k
K-Dense-AIK-Dense-AI/scientific-agent-skills
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

Langue du contenu du Skill : anglais

pytorch-lightning
43.9k
K-Dense-AIK-Dense-AI/scientific-agent-skills
Deep learning framework (PyTorch Lightning / lightning package). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.

Langue du contenu du Skill : anglais

torchdrug
43.9k
K-Dense-AIK-Dense-AI/scientific-agent-skills
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.

Langue du contenu du Skill : anglais

claude-md
41.4k
luongnv89luongnv89/claude-howto
Tạo hoặc cập nhật các file CLAUDE.md theo các thực hành tốt nhất để onboarding tác nhân AI tối ưu

Langue du contenu du Skill : vietnamien

chakra-ui-migrate
40.6k
chakra-uichakra-ui/chakra-ui
Migrate Chakra UI projects from v2 to v3, covering package changes, codemods, provider setup, color mode, prop renaming, compound components, theming, recipes, and Next.js updates. Use this skill whenever a user is upgrading Chakra UI versions, encountering breaking changes after an upgrade, converting old v2 patterns (ColorModeScript, useColorModeValue, styleConfig, extendTheme, isDisabled, colorScheme, @chakra-ui/icons, framer-motion dependency), fixing compound component patterns, or asking about differences between Chakra UI v2 and v3 — even if they don't say "migrate" or "upgrade" explicitly.

Langue du contenu du Skill : anglais

spark-environment-setup
39.5k
wshobsonwshobson/agents
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

Langue du contenu du Skill : anglais

python-error-handling
39.5k
wshobsonwshobson/agents
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.

Langue du contenu du Skill : anglais

create-implementation-plan
38.8k
githubgithub/awesome-copilot
Create a new implementation plan file for new features, refactoring existing code or upgrading packages, design, architecture or infrastructure.

Langue du contenu du Skill : anglais

csharp-async
38.8k
githubgithub/awesome-copilot
Get best practices for C# async programming

Langue du contenu du Skill : anglais

dotnet-upgrade
38.8k
githubgithub/awesome-copilot
Ready-to-use prompts for comprehensive .NET framework upgrade analysis and execution

Langue du contenu du Skill : anglais

ef-core
38.8k
githubgithub/awesome-copilot
Get best practices for Entity Framework Core

Langue du contenu du Skill : anglais

multi-stage-dockerfile
38.8k
githubgithub/awesome-copilot
Create optimized multi-stage Dockerfiles for any language or framework

Langue du contenu du Skill : anglais

mvvm-toolkit
38.8k
githubgithub/awesome-copilot
CommunityToolkit.Mvvm (the MVVM Toolkit) core: source generators ([ObservableProperty], [RelayCommand], [NotifyPropertyChangedFor], [NotifyCanExecuteChangedFor], [NotifyDataErrorInfo]), base classes (ObservableObject / ObservableValidator / ObservableRecipient), commands (RelayCommand / AsyncRelayCommand), and validation. Companion skills: mvvm-toolkit-messenger for pub/sub, mvvm-toolkit-di for Microsoft.Extensions.DependencyInjection wiring. Works across WPF, WinUI 3, MAUI, Uno, and Avalonia.

Langue du contenu du Skill : anglais

refactor-method-complexity-reduce
38.8k
githubgithub/awesome-copilot
Refactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by extracting helper methods.

Langue du contenu du Skill : anglais

semantic-kernel
38.8k
githubgithub/awesome-copilot
Create, update, refactor, explain, or review Semantic Kernel solutions using shared guidance plus language-specific references for .NET and Python.

Langue du contenu du Skill : anglais

add-sgl-kernel
35.8k
sgl-projectsgl-project/sglang
Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)

Langue du contenu du Skill : anglais

competition-kernel-container-escape
35.0k
zhaoxuya520zhaoxuya520/reverse-skill
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for kernel attack surface, namespace and cgroup boundaries, container isolation assumptions, syscall paths, and escape primitive verification. Use when the user asks to analyze container-to-host escape paths, kernel exploit prerequisites, namespace crossover, capability misuse, or prove whether an exploit primitive crosses the sandbox boundary. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Langue du contenu du Skill : anglais