Skill 全量检索

IDE 插件256,360implement-specSkillsMP@mattpocock实现 specification 代码.Implement a specification in code.#ide-plugins#framework-internalsmattpocock/skillsGit 克隆查看详情与安装步骤 → 框架内核253,169python-patternsSkillsMP@affaan-mPythonic 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。#framework-internalsaffaan-m/eccGit 克隆查看详情与安装步骤 → 框架内核253,169pytorch-patternsSkillsMP@affaan-mPyTorch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。#framework-internalsaffaan-m/eccGit 克隆查看详情与安装步骤 → 框架内核253,169regex-vs-llm-structured-textSkillsMP@affaan-m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。#framework-internalsaffaan-m/eccGit 克隆查看详情与安装步骤 → 框架内核253,169pytorch-patternsSkillsMP@affaan-mPyTorch 深度学习模式最佳实践构建健壮, 高效, reproducible 训练流水线, 模型 architectures, 数据加载. 使用编写评审 PyTorch 训练循环, 模型 architectures, 数据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#framework-internalsaffaan-m/eccGit 克隆查看详情与安装步骤 → 框架内核243,171accelerateSkillsMP@NousResearch运行 PyTorch 训练跨 GPUs minimal 变更.Run PyTorch training across GPUs with minimal changes.#framework-internalsnousresearch/hermes-agentGit 克隆查看详情与安装步骤 → 框架内核243,171peftSkillsMP@NousResearch精细-tune large LLMs LoRA limited GPU 记忆.Fine-tune large LLMs with LoRA on limited GPU memory.#framework-internalsnousresearch/hermes-agentGit 克隆查看详情与安装步骤 → 框架内核243,171unslothSkillsMP@NousResearchUnsloth: 2-5x 更快 LoRA/QLoRA 精细-tuning, less VRAM.Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.#framework-internalsnousresearch/hermes-agentGit 克隆查看详情与安装步骤 → 框架内核243,171darwinian-evolverSkillsMP@NousResearchEvolve prompts/regex/SQL/代码 Imbue's evolution 循环.Evolve prompts/regex/SQL/code with Imbue's evolution loop.#framework-internalsnousresearch/hermes-agentGit 克隆查看详情与安装步骤 → 框架内核243,171godmodeSkillsMP@NousResearchJailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.#framework-internalsnousresearch/hermes-agentGit 克隆查看详情与安装步骤 → 框架内核142,171flagsSkillsMP@vercel如何添加修改 Next. js experimental 功能 flags 端到端. 使用 editing config-shared. ts, config-schema. ts, define-env-plugin. ts, next-server. ts, 导出/worker. ts, module. compiled. js. 覆盖 type declaration, zod 结构, buiHow 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, bui#framework-internalsvercel/next.jsGit 克隆查看详情与安装步骤 → 框架内核138,570wpf-to-winui3-migrationSkillsMP@microsoft指南迁移 PowerToys 模块 WPF WinUI 3 (Windows 应用 SDK). 使用要求迁移 WPF 代码, 转换 WPF XAML WinUI, replace 系统. Windows namespaces Microsoft. UI. Xaml, 更新 Dispatcher DispatcherQueue, replGuide 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, repl#framework-internalsmicrosoft/powertoysGit 克隆查看详情与安装步骤 → 框架内核104,201cavemanSkillsMP@JuliusBrusseeUltra-compressed communication 模式 cuts 输出词元 keeping technical accuracy. Levels: lite, 完整, ultra wenyan variants. 使用 /caveman, "caveman 模式", "talk 例如 caveman", " 简要" "less 词元".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".#framework-internalsjuliusbrussee/cavemanGit 克隆查看详情与安装步骤 → 框架内核104,201cavemanSkillsMP@JuliusBrusseeUltra-compressed communication 模式 cuts 输出词元 keeping technical accuracy. Levels: lite, 完整, ultra wenyan variants. 使用 /caveman, "caveman 模式", "talk 例如 caveman", " 简要" "less 词元".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".#framework-internalsjuliusbrussee/cavemanGit 克隆查看详情与安装步骤 → 框架内核102,818add-uint-supportSkillsMP@pytorch添加 unsigned 整数 (uint) type 支持 PyTorch operators 更新 AT_DISPATCH macros. 使用新增支持 uint16, uint32, uint64 types operators, kernels, 用户提及 enabling unsigned types, barebones unsignedAdd 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 #framework-internalspytorch/pytorchGit 克隆查看详情与安装步骤 → 框架内核102,818at-dispatch-v2SkillsMP@pytorch转换 PyTorch AT_DISPATCH macros AT_DISPATCH_V2 格式化 ATen C++ 代码. 使用 porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, 其他 dispatch macros 新建 v2 API. ATen kernel 文件, CUDA kernels, natConvert 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 nat#framework-internalspytorch/pytorchGit 克隆查看详情与安装步骤 → 框架内核102,818cuda-index-widthSkillsMP@pytorch选择 32-bit vs 64-bit 索引 math PyTorch CUDA kernels. 使用修复 large-tensor indexing overflows, deciding 是否使用 int64_t, canUse32BitIndexMath, CUDA_KERNEL_LOOP_TYPE, AT_DISPATCH_INDEX_TYPES, considering binaChoose 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 bina#framework-internalspytorch/pytorchGit 克隆查看详情与安装步骤 → 框架内核102,818metal-kernelSkillsMP@pytorch编写 Metal/MPS kernels PyTorch operators. 使用新增 MPS 设备支持 operators, 实现 Metal shaders, porting CUDA kernels Apple Silicon. 覆盖 native_functions. yaml dispatch, 主机-端 operators, Metal kernWrite 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 kern#framework-internalspytorch/pytorchGit 克隆查看详情与安装步骤 → 框架内核102,818pt2-bug-basherSkillsMP@pytorch调试 PyTorch 2 编译器 stack 失败包括 Dynamo 图谱 breaks, Inductor codegen 错误, AOTAutograd 崩溃, accuracy mismatches. 使用 encountering torch. 编译错误, BackendCompilerFailed 异常, recompilation 工单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#framework-internalspytorch/pytorchGit 克隆查看详情与安装步骤 → 框架内核93,077plan-changeSkillsMP@ruvnet转换功能请求 minimal, 文件-级别实现计划在…之前代码.Turn a feature request into a minimal, file-level implementation plan before any code.#framework-internalsruvnet/ruviewGit 克隆查看详情与安装步骤 → 框架内核91,546triton-kernel-writingSkillsMP@vllm-project编写评审 Triton kernels vLLM, practical 指引生成-代码 inspection, 上线 grids, indexing, specialization, tuning, representative performance 校验.Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation.#framework-internalsvllm-project/vllmGit 克隆查看详情与安装步骤 → 框架内核68,803programmingSkillsMP@code-yeongyu应用 strict, 现代语言 practice (typed 错误, exhaustive 匹配, TDD) Python, Rust, TypeScript, Go. 使用工作. py,. rs,. ts,. go 文件.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.#framework-internalscode-yeongyu/oh-my-openagentGit 克隆查看详情与安装步骤 → 框架内核64,865dedupe-issue-localSkillsMP@warpdotdev仓库-特定 dedupe 指引 warp. 分类 declared overridable 核心 dedupe-工单技能 specialized here.Repo-specific dedupe guidance for warp. Only the categories declared overridable by the core dedupe-issue skill may be specialized here.#framework-internalswarpdotdev/warpGit 克隆查看详情与安装步骤 → 框架内核56,383hyperframes-registrySkillsMP@calesthio安装 wire 注册中心 blocks 组件 HyperFrames compositions. 使用 running hyperframes 添加, installing block 组件, wiring 已安装条目 index. html, 处理 hyperframes. json. 覆盖添加 comInstall 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 com#framework-internalscalesthio/openmontageGit 克隆查看详情与安装步骤 → 框架内核53,400analysis-api-mark-internal-apisSkillsMP@JetBrains云端硬盘按-模块内部-API 代码库测试, refine suggested 注解 down `internal` ( up `@KaImplementationDetail`) 基于 actual 外部用法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#framework-internalsjetbrains/kotlinGit 克隆查看详情与安装步骤 → 框架内核49,222decompress-binarySkillsMP@ClickHouse提取 inner ELF ClickHouse self-extracting `clickhouse` binary, 包括架构 differs 主机 (e. g. 加载 aarch64 CI 核心 dump x86 workstation). 使用 gdb/lldb 需要真实 symbols dowExtract 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 dow#framework-internalsclickhouse/clickhouseGit 克隆查看详情与安装步骤 → 框架内核49,211fe-modularizationSkillsMP@metabaseDeciding 前端代码 lives — tier 模型, move mechanics, 扩展 points, 端 effects, naming, traps. 使用 moving 代码模块, carving 新建模块, 修复边界 violations, 新增 barrel 接口, oDeciding 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, o#framework-internalsmetabase/metabaseGit 克隆查看详情与安装步骤 → 框架内核48,873stage-tamagotchi-godot-csharpSkillsMP@moeru-ai应用引擎-本地 C# 开发方法代码风格处理 `engines/stage-tamagotchi-godot`, 包括 `. cs` 文件, `. csproj`, 引擎-本地 `. editorconfig`, Godot-特定 C# 结构决策. 使用 TypApply 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 Typ#framework-internalsmoeru-ai/airiGit 克隆查看详情与安装步骤 → 框架内核47,792discourse-upcoming-changes-authoringSkillsMP@discourse使用修改, 调试, extending upcoming 变更框架代码系统 itself.Use when modifying, debugging, or extending the upcoming changes framework code and system itself.#framework-internalsdiscourse/discourseGit 克隆查看详情与安装步骤 → 框架内核43,904opentrons-integrationSkillsMP@K-Dense-AI作者, 评审, 迁移, simulate, 排查官方 Opentrons Python 协议 API v2 协议 Flex OT-2 robots. 使用机器人-特定 liquid handling, 演示文稿 labware 初始化设置, pipettes, 模块, 运行时 parameters, liquidAuthor, 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 #framework-internalsk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 框架内核43,904pennylaneSkillsMP@K-Dense-AI硬件-agnostic quantum ML 框架自动 differentiation. 使用训练 quantum circuits 通过 gradients, 构建混合 quantum-classical 模型, needing 设备 portability 跨 IBM/Google/Rigetti/IonQ. Best variatHardware-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 variat#framework-internalsk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 框架内核43,904pymooSkillsMP@K-Dense-AI多-objective 优化框架. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, 基准测试 (ZDT, DTLZ), 工程设计优化问题.Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.#framework-internalsk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 框架内核43,904pytorch-lightningSkillsMP@K-Dense-AI深度学习框架 (PyTorch Lightning / lightning 软件包). Organize PyTorch 代码 LightningModules, 配置 Trainers 多-GPU/TPU, 实现数据流水线, callbacks, 日志记录 (W&B, TensorBoard, MLflow), 分布式 traininDeep 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 trainin#framework-internalsk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 框架内核43,904torchdrugSkillsMP@K-Dense-AI构建排查 TorchDrug 0.2.1 工作流程 molecular 图谱, 房产预测, self-supervised pretraining, molecule generation, retrosynthesis, protein representation 学习, 知识图谱推理. 使用代码 impoBuild 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 impo#framework-internalsk-dense-ai/scientific-agent-skillsGit 克隆查看详情与安装步骤 → 框架内核41,408claude-mdSkillsMP@luongnv89Tạo hoặc cập nhật các 文件 CLAUDE. md theo các thực hành tốt nhất để 新手引导 tác nhân AI tố ưuTạo hoặc cập nhật các file CLAUDE.md theo các thực hành tốt nhất để onboarding tác nhân AI tối ưu#framework-internalsluongnv89/claude-howtoGit 克隆查看详情与安装步骤 → 框架内核40,632chakra-ui-migrateSkillsMP@chakra-ui迁移 Chakra UI 项目 v2 v3, 覆盖软件包变更, codemods, 提供方初始化设置, color 模式, prop renaming, compound 组件, theming, 食谱, Next. js 更新. 使用技能用户升级 Chakra UI versiMigrate 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 versi#framework-internalschakra-ui/chakra-uiGit 克隆查看详情与安装步骤 → 框架内核39,485spark-environment-setupSkillsMP@wshobson集合 up 处理 ML training/inference 环境 NVIDIA DGX Spark (GB10, aarch64, CUDA 13). 使用 installing PyTorch/Unsloth/TRL/vLLM DGX Spark, hitting libcudart wheel-ABI 错误 aarch64, 选择 NGC 容器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#framework-internalswshobson/agentsGit 克隆查看详情与安装步骤 → 框架内核39,485python-error-handlingSkillsMP@wshobsonPython 错误处理模式包括输入校验, 异常 hierarchies, partial 失败 handling. 使用实现校验逻辑, 设计异常策略, handling 批量处理失败, 构建健壮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 A#framework-internalswshobson/agentsGit 克隆查看详情与安装步骤 → 框架内核38,754create-implementation-planSkillsMP@github创建新建实现计划文件新建功能, 重构现有代码升级软件包, 设计, 架构基础设施.Create a new implementation plan file for new features, refactoring existing code or upgrading packages, design, architecture or infrastructure.#framework-internalsgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 框架内核38,754csharp-asyncSkillsMP@github获取最佳实践 C# 异步 programmingGet best practices for C# async programming#framework-internalsgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 框架内核38,754dotnet-upgradeSkillsMP@github就绪-to-使用提示词全面. NET 框架升级分析执行Ready-to-use prompts for comprehensive .NET framework upgrade analysis and execution#framework-internalsgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 框架内核38,754ef-coreSkillsMP@github获取最佳实践实体框架核心Get best practices for Entity Framework Core#framework-internalsgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 框架内核38,754multi-stage-dockerfileSkillsMP@github创建已优化多-阶段 Dockerfiles 语言框架Create optimized multi-stage Dockerfiles for any language or framework#framework-internalsgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 框架内核38,754mvvm-toolkitSkillsMP@githubCommunityToolkit. Mvvm ( MVVM 工具集) 核心: 来源生成器 ([ObservableProperty], [RelayCommand], [NotifyPropertyChangedFor], [NotifyCanExecuteChangedFor], [NotifyDataErrorInfo]), 基础类 (ObservableObject / ObservableValidator /CommunityToolkit.Mvvm (the MVVM Toolkit) core: source generators ([ObservableProperty], [RelayCommand], [NotifyPropertyChangedFor], [NotifyCanExecuteChangedFor], [NotifyDataErrorInfo]), base classes (ObservableObject / ObservableValidator /#framework-internalsgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 框架内核38,754refactor-method-complexity-reduceSkillsMP@github重构给定方法 `${input: methodName}` reduce cognitive complexity `${input: complexityThreshold}` below, extracting 辅助工具方法.Refactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by extracting helper methods.#framework-internalsgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 框架内核38,754semantic-kernelSkillsMP@github创建, 更新, 重构, explain, 评审语义 Kernel 解决方案使用共享指引以及语言-特定参考. NET Python.Create, update, refactor, explain, or review Semantic Kernel solutions using shared guidance plus language-specific references for .NET and Python.#framework-internalsgithub/awesome-copilotGit 克隆查看详情与安装步骤 → 框架内核35,842add-sgl-kernelSkillsMP@sgl-project分步教程新增 heavyweight AOT CUDA/C++ kernel sgl-kernel (包括测试 & 基准测试)Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)#framework-internalssgl-project/sglangGit 克隆查看详情与安装步骤 → 框架内核35,034competition-kernel-container-escapeSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程 kernel attack 暴露面, namespace cgroup 边界, 容器隔离 assumptions, syscall 路径, escape primitive 核验. 使用用户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 as#framework-internalszhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 框架内核35,034competition-malware-configSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程恶意软件配置 recovery, staged 载荷边界, beacon parameter extraction, IOC decoding. 使用用户要求 recover 恶意软件配置, dInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for malware configuration recovery, staged payload boundaries, beacon parameter extraction, and IOC decoding. Use when the user asks to recover a malware config, d#framework-internalszhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 框架内核35,034competition-reverse-pwnSkillsMP@zhaoxuya520内部下游技能 ctf-沙箱-orchestrator. CTF-沙箱工作流程 reverse 工程, 恶意软件, DFIR, 固件, pwnable, 原生漏洞利用 challenges. 使用用户要求 reverse binary, unpack 样例, 检查Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for reverse engineering, malware, DFIR, firmware, pwnable, and native exploit challenges. Use when the user asks to reverse a binary, unpack a sample, inspect a me#framework-internalszhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 框架内核35,034dotnet-reverseSkillsMP@zhaoxuya520. NET / C# 二进制逆向。当目标是. NET assembly（PE 头含 CLR、. exe/. dll 托管程序）、C# 编译产物（含 NativeAOT）、红队 Sharp* 工具（Rubeus / SharpHound / SharpHound 等）、. NET 混淆程序（ConfuserEx / SmartAssembly / Babel / Eazfuscator）、. NET loader / info-stealer / 套壳恶意软件时使用。优先用 d.NET / C# 二进制逆向。当目标是 .NET assembly（PE 头含 CLR、.exe/.dll 托管程序）、C# 编译产物（含 NativeAOT）、红队 Sharp* 工具（Rubeus / SharpHound / SharpHound 等）、.NET 混淆程序（ConfuserEx / SmartAssembly / Babel / Eazfuscator）、.NET loader / info-stealer / 套壳 malware 时使用。优先用 d#framework-internalszhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 框架内核35,034ghidra-reverseSkillsMP@zhaoxuya520使用 free/open reverse 工程 Ghidra (headless GUI), 包括 decompile, cross-refs, 可选 Ghidra MCP 工作流程 IDA unavailable.Use for free/open reverse engineering with Ghidra (headless or GUI), including decompile, cross-refs, and optional Ghidra MCP workflows when IDA is unavailable.#framework-internalszhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 框架内核35,034protocol-reverseSkillsMP@zhaoxuya520使用经授权 reverse 工程自定义 binary 协议, Protobuf/gRPC, WebSocket frames, PCAP-driven 协议 recovery.Use for authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery.#framework-internalszhaoxuya520/reverse-skillGit 克隆查看详情与安装步骤 → 框架内核32,390analyzing-golang-malware-with-ghidraSkillsMP@mukul975Reverse engineer Go-编译恶意软件 Ghidra 解析 Go buildinfo pclntab structures, recovering stripped/obfuscated 函数名称 (e. g. 通过 GoResolver), extracting 嵌入式 module/dependency 字符串 types Go binariesReverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries#framework-internalsmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 框架内核32,390implementing-memory-protection-with-dep-aslrSkillsMP@mukul975实现记忆防护 mechanisms 包括 DEP (数据执行 Prevention), ASLR (Address Space 布局 Randomization), CFG (控制流程守卫), 其他漏洞利用 mitigations 防止记忆 corruption attacks. 使用 hardening eImplements memory protection mechanisms including DEP (Data Execution Prevention), ASLR (Address Space Layout Randomization), CFG (Control Flow Guard), and other exploit mitigations to prevent memory corruption attacks. Use when hardening e#framework-internalsmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 框架内核32,390reverse-engineering-ios-app-with-fridaSkillsMP@mukul975Reverse engineers iOS 应用使用 Frida 动态 instrumentation understand 内部逻辑, 提取加密关键点, bypass 安全控件, 发现隐藏 functionality 无需源码访问. 使用 performing 作者Reverse engineers iOS applications using Frida dynamic instrumentation to understand internal logic, extract encryption keys, bypass security controls, and discover hidden functionality without source code access. Use when performing author#framework-internalsmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 框架内核32,390reverse-engineering-malware-with-ghidraSkillsMP@mukul975Reverse engineers 恶意软件 binaries 使用 NSA's Ghidra disassembler decompiler 研究内部逻辑, cryptographic routines, C2 协议, evasion techniques assembly pseudo-C 级别. 使用静态动态分析Reverse engineers malware binaries using NSA's Ghidra disassembler and decompiler to study internal logic, cryptographic routines, C2 protocols, and evasion techniques at the assembly and pseudo-C level. Use when static or dynamic analysis #framework-internalsmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 框架内核32,390reverse-engineering-rust-malwareSkillsMP@mukul975Reverse engineers Rust-编译恶意软件使用 IDA Pro Ghidra, 覆盖 techniques non-null-terminated fat-pointer 字符串, monomorphized/duplicated 泛型代码, Result/Option unwrap chains, crate 依赖 extraction, Rust-speReverse engineers Rust-compiled malware using IDA Pro and Ghidra, covering techniques for non-null-terminated fat-pointer strings, monomorphized/duplicated generic code, Result/Option unwrap chains, crate dependency extraction, and Rust-spe#framework-internalsmukul975/anthropic-cybersecurity-skillsGit 克隆查看详情与安装步骤 → 框架内核30,563huggingface-accelerateSkillsMP@davila7极简分布式训练 API. 4 lines 添加分布式支持 PyTorch 脚本. Unified API DeepSpeed/FSDP/Megatron/DDP. 自动设备 placement, mixed precision (FP16/BF16/FP8). 可交互配置, 单个上线命令Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563pytorch-lightningSkillsMP@davila7High-级别 PyTorch 框架 Trainer 类, 自动分布式训练 (DDP/FSDP/DeepSpeed), callbacks 系统, minimal 脚手架. Scales laptop supercomputer same 代码. 使用需要整洁训练循环High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563llama-cppSkillsMP@davila7运行 LLM 推理计算 CPU, Apple Silicon, 消费方 GPUs 无需 NVIDIA 硬件. 使用 edge 部署, M1/M2/M3 Macs, AMD/Intel GPUs, CUDA unavailable. 支持 GGUF quantization (1.5-8 bit) reduced 记忆 4-10× spRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× sp#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563tensorrt-llmSkillsMP@davila7优化 LLM 推理计算 NVIDIA TensorRT maximum 吞吐量 lowest 延迟. 使用生产环境部署 NVIDIA GPUs (A100/H100), need 10-100x 更快推理计算 PyTorch, serving 模型 quantization (Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563nnsight-remote-interpretabilitySkillsMP@davila7提供指引 interpreting manipulating neural 网络 internals 使用 nnsight 可选 NDIF 远程执行. 使用 needing 运行 interpretability 实验 massive 模型 (70B+) 无需本地 GPU 资源, whProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or wh#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563pyvene-interventionsSkillsMP@davila7提供指引 performing causal interventions PyTorch 模型使用 pyvene's 声明式 intervention 框架. 使用 conducting causal 链路追踪, activation patching, interchange intervention 训练, testing causal hypotheProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypothe#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563ml-engineerSkillsMP@davila7构建生产环境 ML 系统 PyTorch 2. x, TensorFlow, 现代 ML 框架. 实现模型 serving, 功能工程, A/B testing, 监控.Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563distributed-llm-pretraining-torchtitanSkillsMP@davila7提供 PyTorch-原生分布式 LLM pretraining 使用 torchtitan 4D parallelism (FSDP2, TP, PP, CP). 使用 pretraining Llama 3.1, DeepSeek V3, 自定义模型 scale 8 512+ GPUs Float8, torch. 编译, distribProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distrib#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563optimizing-attention-flashSkillsMP@davila7优化 transformer attention Flash Attention 2-4x speedup 10-20x 记忆 reduction. 使用 training/running transformers long sequences (>512 词元), encountering GPU 记忆工单 attention, need 更快 inferOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster infer#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563torchforge-rl-trainingSkillsMP@davila7提供指引 PyTorch-原生 agentic RL 使用 torchforge, Meta's 函数库 separating infra 算法. 使用需要整洁 RL abstractions, 简单算法 experimentation, 可扩展训练 Monarch TorchTitan.Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563outlinesSkillsMP@davila7保证有效 JSON/XML/代码结构在…期间 generation, 使用 Pydantic 模型 type-安全输出, 支持本地模型 (Transformers, vLLM), maximize 推理计算提速 Outlines - dottxt. ai's 结构化 generation 函数库Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563salesforce-developmentSkillsMP@davila7专家模式 Salesforce 平台开发包括 Lightning 网页组件 (LWC), Apex 触发类, REST/Bulk APIs, Connected 应用, Salesforce DX scratch orgs 2nd generation 软件包 (2GP). 使用: salesfExpert patterns for Salesforce platform development including Lightning Web Components (LWC), Apex triggers and classes, REST/Bulk APIs, Connected Apps, and Salesforce DX with scratch orgs and 2nd generation packages (2GP). Use when: salesf#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563pennylaneSkillsMP@davila7跨平台 Python 函数库 quantum computing, quantum 机器学习, quantum chemistry. 启用构建训练 quantum circuits 自动 differentiation, 无缝集成 PyTorch/JAX/TensorFlow, devicCross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry. Enables building and training quantum circuits with automatic differentiation, seamless integration with PyTorch/JAX/TensorFlow, and devic#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563pymooSkillsMP@davila7多-objective 优化框架. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, 基准测试 (ZDT, DTLZ), 工程设计优化问题.Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核30,563pytorch-lightningSkillsMP@davila7深度学习框架 (PyTorch Lightning). Organize PyTorch 代码 LightningModules, 配置 Trainers 多-GPU/TPU, 实现数据流水线, callbacks, 日志记录 (W&B, TensorBoard), 分布式训练 (DDP, FSDP, DeepSpeed), foDeep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), fo#framework-internalsdavila7/claude-code-templatesGit 克隆查看详情与安装步骤 → 框架内核27,791react-best-practicesSkillsMP@mastra-aiReact 性能优化规范指南 Mastra 工程. 技能用于编写, 评审, 重构 React 代码确保 optimal performance 模式. 触发任务 involving React 组件, 数据获取React performance optimization guidelines from Mastra Engineering. This skill should be used when writing, reviewing, or refactoring React code to ensure optimal performance patterns. Triggers on tasks involving React components, data fetch#framework-internalsmastra-ai/mastraGit 克隆查看详情与安装步骤 → 框架内核25,685compliance-osSkillsMP@alirezarezvani合规 OS — meta-orchestrator lets 合规 teams CONFIGURE 框架应用, COMPUTE cross-框架控制 overlap, SIMULATE 内部审计, CONSOLIDATE 证据跨 多个框架. Four 决策: (1) 给定Compliance OS — meta-orchestrator that lets compliance teams CONFIGURE which frameworks apply, COMPUTE cross-framework control overlap, SIMULATE internal audits, and CONSOLIDATE evidence across multiple frameworks. Four decisions: (1) Given#framework-internalsalirezarezvani/claude-skillsGit 克隆查看详情与安装步骤 → 框架内核25,685kubernetes-operatorSkillsMP@alirezarezvani使用构建 Kubernetes 运维者 — 自定义控制器 reconcile CRD 状态. 触发 "构建运维者", "CRD 设计", "reconcile 循环", "控制器-运行时", "kubebuilder", "运维者-SDK", "metacontroller", "KOPF", "运维者Use when building a Kubernetes Operator — custom controllers that reconcile CRD state. Triggers on "build an operator", "CRD design", "reconcile loop", "controller-runtime", "kubebuilder", "operator-sdk", "metacontroller", "KOPF", "operator#framework-internalsalirezarezvani/claude-skillsGit 克隆查看详情与安装步骤 → 框架内核25,240header-cycle-breakerSkillsMP@v8指南 breaking cyclic 依赖 V8 请求头解决 cascade IWYU 失败.Guide for breaking cyclic dependencies in V8 headers and resolving cascade IWYU failures.#framework-internalsv8/v8Git 克隆查看详情与安装步骤 → 框架内核25,240torqueSkillsMP@v8提供专家指引 navigating, 实现, verifying V8 Torque (. tq) builtins. 使用修改调试 Torque 文件. 使用 C++ macro builtins.Provides expert guidance for navigating, implementing, and verifying V8 Torque (.tq) builtins. Use when modifying or debugging Torque files. Do not use for C++ macro builtins.#framework-internalsv8/v8Git 克隆查看详情与安装步骤 → 框架内核24,190async-io-modelSkillsMP@tursodatabaseExplanations 通用异步模式用于 tursodb. Involves IOResult, 状态 machines, re-entrancy pitfalls, CompletionGroup. 始终使用模式 `core` 进行中 anything IOExplanations of common asynchronous patterns used in tursodb. Involves IOResult, state machines, re-entrancy pitfalls, CompletionGroup. Always use these patterns in `core` when doing anything IO#framework-internalstursodatabase/tursoGit 克隆查看详情与安装步骤 → 框架内核24,077paddle-cross-ecosystem-custom-opSkillsMP@PaddlePaddle将原生 PyTorch 自定义算子库、Torch 扩展、生态库（TorchCodec/FlashInfer/DeepEP 等）以及 Kernel DSL 生态（Triton/TileLang/TVM FFI 等）以最小修改方式接入 PaddlePaddle。遇到以下场景务必使用：迁移外部算子库到 Paddle；分析 PFCCLab fork 与上游的兼容差异；处理 paddle. enable_compat、paddle. utils. cpp_extension、T将原生 PyTorch 自定义算子库、Torch extension、生态库（TorchCodec/FlashInfer/DeepEP 等）以及 Kernel DSL 生态（Triton/TileLang/TVM FFI 等）以最小修改方式接入 PaddlePaddle。遇到以下场景务必使用：迁移外部算子库到 Paddle；分析 PFCCLab fork 与上游的兼容差异；处理 paddle.enable_compat、paddle.utils.cpp_extension、T#framework-internalspaddlepaddle/paddleGit 克隆查看详情与安装步骤 → 框架内核24,077paddle-design-compilerSkillsMP@PaddlePaddle使用处理 Paddle 3.0 编译器完整流水线: SOT (Symbolic Opcode Translator) bytecode-级别 dy2st 图谱采集, PIR (Paddle IR) SSA-基于中级 representation, CINN fused CUDA kernel generation, 运维者 decUse when working with Paddle 3.0 compiler full pipeline: SOT (Symbolic Opcode Translator) for bytecode-level dy2st graph capture, PIR (Paddle IR) for SSA-based intermediate representation, CINN for fused CUDA kernel generation, operator dec#framework-internalspaddlepaddle/paddleGit 克隆查看详情与安装步骤 → 框架内核24,077paddle-phi-kernelSkillsMP@PaddlePaddle使用处理 Paddle's PHI kernel 系统: registering 新建 kernels, 调试 kernel selection/dispatch, understanding 代码自动-generation YAML, 实现运维者 decomposition 通过 combination mechanism.Use when working with Paddle's PHI kernel system: registering new kernels, debugging kernel selection/dispatch, understanding code auto-generation from YAML, or implementing operator decomposition via the combination mechanism.#framework-internalspaddlepaddle/paddleGit 克隆查看详情与安装步骤 → 框架内核24,077paddle-op-devSkillsMP@PaddlePaddlePaddlePaddle (飞桨) C++ 算子开发指南。提供从 YAML 配置、InferMeta 函数、Kernel 实现、Python API 封装、单元测试到编译验证的完整算子开发流程指导。在以下场景使用此技能：(1) 为 Paddle 框架新增 C++ 算子 (2) 修改或调试已有 Paddle 算子 (3) 编写算子的 YAML 配置、InferMeta、Kernel、Python API 或单元测试 (4) 理解 Paddle 算子开发架构和流程 (5)PaddlePaddle (飞桨) C++ 算子开发指南。提供从 YAML 配置、InferMeta 函数、Kernel 实现、Python API 封装、单元测试到编译验证的完整算子开发流程指导。在以下场景使用此 skill：(1) 为 Paddle 框架新增 C++ 算子 (2) 修改或调试已有 Paddle 算子 (3) 编写算子的 YAML 配置、InferMeta、Kernel、Python API 或单元测试 (4) 理解 Paddle 算子开发架构和流程 (5)#framework-internalspaddlepaddle/paddleGit 克隆查看详情与安装步骤 → 框架内核23,908zoom-meeting-sdk-unrealSkillsMP@anthropicsZoom Meeting SDK Unreal 引擎封装 integrations. 使用构建 Unreal 项目 embed Zoom meetings C++ 蓝图封装, 包括封装-to-SDK 映射 concerns.Zoom Meeting SDK for Unreal Engine wrapper integrations. Use when building Unreal projects that embed Zoom meetings with C++ and Blueprint wrappers, including wrapper-to-SDK mapping concerns.#framework-internalsanthropics/knowledge-work-pluginsGit 克隆查看详情与安装步骤 → 框架内核23,880token-efficiencySkillsMP@SuperClaude-OrgActivate ultra-compressed 输出模式 maximum 词元效率. 使用上下文 running low, 用户请求 brevity, dealing large-scale 运维.Activate ultra-compressed output mode for maximum token efficiency. Use when context is running low, user requests brevity, or dealing with large-scale operations.#framework-internalssuperclaude-org/superclaude_frameworkGit 克隆查看详情与安装步骤 → 框架内核23,395upgrade-depsSkillsMP@verl-project升级, downgrade, re-pin Python 依赖 (vllm, sglang, torch, transformers, flash-attn,.) verl's universal uv. 锁流程.Upgrade, downgrade, or re-pin a Python dependency (vllm, sglang, torch, transformers, flash-attn, etc.) in verl's universal uv.lock flow.#framework-internalsverl-project/verlGit 克隆查看详情与安装步骤 → 框架内核21,835python-sdkSkillsMP@comet-mlPython SDK 模式 Opik. 使用处理 sdks/python, SDK APIs, integrations, 消息处理.Python SDK patterns for Opik. Use when working in sdks/python, on SDK APIs, integrations, or message processing.#framework-internalscomet-ml/opikGit 克隆查看详情与安装步骤 → 框架内核21,778cuda-attention-kernel-patternsSkillsMP@microsoft模式 pitfalls ONNX 域名 Attention 运维者 (opset 23/24) CUDA 实现. 使用修改 dispatch cascade core/providers/cuda/llm/attention. cc, 编写 mask/bias CUDA kernels, 调试 attention 测试 routinPatterns and pitfalls for the ONNX domain Attention operator (opset 23/24) CUDA implementation. Use when modifying the dispatch cascade in core/providers/cuda/llm/attention.cc, writing mask/bias CUDA kernels, debugging attention test routin#framework-internalsmicrosoft/onnxruntimeGit 克隆查看详情与安装步骤 → 框架内核21,778cuda-cutlass-fmha-incremental-rebuildSkillsMP@microsoft使用 rebuilding ONNX 运行时 CUDA 在…之后 editing CUTLASS fused-MHA 请求头 (onnxruntime/contrib_ops/cuda/bert/cutlass_fmha/*. h kernel_forward. h fmha_launch_template. h), 页眉编辑 "passed" incremental 构建 tUse when rebuilding ONNX Runtime CUDA after editing CUTLASS fused-MHA headers (onnxruntime/contrib_ops/cuda/bert/cutlass_fmha/*.h such as kernel_forward.h or fmha_launch_template.h), or when a header edit "passed" an incremental build but t#framework-internalsmicrosoft/onnxruntimeGit 克隆查看详情与安装步骤 → 框架内核21,778onnx-opset-bump-checklistSkillsMP@microsoft分步检查清单 bumping pinned ONNX 依赖 / opset ONNX 运行时 (e. g. ONNX 1.21 / opset 26 → 1.22 / opset 27). 使用 integrating 新建 ONNX 发布版本发布版本-candidate, 更新 cmake/deps. txt onnx pin cStep-by-step checklist for bumping the pinned ONNX dependency / opset in ONNX Runtime (e.g. ONNX 1.21 / opset 26 → 1.22 / opset 27). Use when integrating a new ONNX release or release-candidate, updating the cmake/deps.txt onnx pin or the c#framework-internalsmicrosoft/onnxruntimeGit 克隆查看详情与安装步骤 → 框架内核21,778ort-transformers-gpu-pytestSkillsMP@microsoft运行 ONNX 运行时 transformers Python 测试 (onnxruntime/test/python/transformers) 对照 GPU wheel, confirm 真实 cuDNN/flash SDPA dispatch. 使用 transformers pytest fails ModuleNotFoundError onnxruntime. capi, torcRun the ONNX Runtime transformers Python tests (onnxruntime/test/python/transformers) against a GPU wheel, and confirm real cuDNN/flash SDPA dispatch. Use when a transformers pytest fails with ModuleNotFoundError onnxruntime.capi, when torc#framework-internalsmicrosoft/onnxruntimeGit 克隆查看详情与安装步骤 → 框架内核21,474add-function-bodySkillsMP@onnx添加函数 body definition ONNX 运维者, defining decomposes 更简单 ops. 使用要求制作 op decomposable, 添加 FunctionBody, 实现 SetContextDependentFunctionBodyBuilder, express op terms oAdd a function body definition to an ONNX operator, defining how it decomposes into simpler ops. Use when asked to make an op decomposable, add a FunctionBody, implement SetContextDependentFunctionBodyBuilder, or express an op in terms of o#framework-internalsonnx/onnxGit 克隆查看详情与安装步骤 → 框架内核21,474add-opSkillsMP@onnx添加新建 ONNX 运维者更新现有运维者新建 opset 版本. 使用要求 define 运维者结构, register op, 添加 inputs/outputs/attributes op, move op old. cc, 版本升级 op's opset 版本.Add a new ONNX operator or update an existing operator to a new opset version. Use when asked to define an operator schema, register an op, add inputs/outputs/attributes to an op, move an op to old.cc, or bump an op's opset version.#framework-internalsonnx/onnxGit 克隆查看详情与安装步骤 → 框架内核21,394viteSkillsMP@debpalash专家指引 Vite 开发现代构建 tooling, HMR, 框架 integrations, 性能优化Expert guidance for Vite development with modern build tooling, HMR, framework integrations, and performance optimization#framework-internalsdebpalash/voicestudioGit 克隆查看详情与安装步骤 → 框架内核20,475cpp-header-inclusionSkillsMP@googleEnforce strict topological 页眉 inclusion layering reordering 规则 Filament. 使用技能新增修改 `#include` directives C++ 来源页眉文件.Enforce the strict topological header inclusion layering and reordering rules in Filament. Use this skill when adding or modifying `#include` directives in C++ source or header files.#framework-internalsgoogle/filamentGit 克隆查看详情与安装步骤 → 框架内核20,475filament-mathSkillsMP@googleEnforce correct mathematical primitives naming 约定 Filament 代码. 使用技能 performing coordinate transformations, vector math, projection setups.Enforce correct mathematical primitives and naming conventions in Filament code. Use this skill when performing coordinate transformations, vector math, or projection setups.#framework-internalsgoogle/filamentGit 克隆查看详情与安装步骤 → 框架内核20,445pseudo-kmpSkillsMP@JetBrains创建修改 IntelliJ pseudo-KMP 模块使用 expect/actual emulation.Create or modify IntelliJ pseudo-KMP modules using expect/actual emulation.#framework-internalsjetbrains/intellij-communityGit 克隆查看详情与安装步骤 → 框架内核20,445pseudo-kmpSkillsMP@JetBrains创建修改 IntelliJ pseudo-KMP 模块使用 expect/actual emulation.Create or modify IntelliJ pseudo-KMP modules using expect/actual emulation.#framework-internalsjetbrains/intellij-communityGit 克隆查看详情与安装步骤 → 框架内核18,268extensions-reviewSkillsMP@dotnet指引编写修改 Microsoft. 扩展.* 系统. IO. Compression 代码 dotnet/runtime. 覆盖 DI lifetime 管理, 配置 binding, 选项校验, 日志记录提供方模式, 缓存语义, compressionGuidance for writing and modifying Microsoft.Extensions.* and System.IO.Compression code in dotnet/runtime. Covers DI lifetime management, configuration binding, options validation, logging provider patterns, caching semantics, compression #framework-internalsdotnet/runtimeGit 克隆查看详情与安装步骤 → 框架内核18,166golang-expertSkillsMP@RightNow-AIGo programming 专家 goroutines, 通道, 接口定义, 模块, concurrency 模式Go programming expert for goroutines, channels, interfaces, modules, and concurrency patterns#framework-internalsrightnow-ai/openfangGit 克隆查看详情与安装步骤 → 框架内核17,759mcore-bump-base-imageSkillsMP@NVIDIA版本升级 NVIDIA PyTorch 基础图片 (`nvcr. io/nvidia/pytorch: YY. MM-py3`) 用于 Megatron-LM CI. 覆盖 two pin sites (GitHub CI `docker/. ngc_version. dev` GitLab CI `. gitlab/stages/01. build. yml`), 帖子-版本升级 CI 循环 (re-运行Bump the NVIDIA PyTorch base image (`nvcr.io/nvidia/pytorch:YY.MM-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker/.ngc_version.dev` and GitLab CI in `.gitlab/stages/01.build.yml`), the post-bump CI loop (re-run #framework-internalsnvidia/megatron-lmGit 克隆查看详情与安装步骤 → 框架内核17,038frontend-forge-fi-operationsSkillsMP@kubesphereOperate FrontendIntegration 资源前端-forge 扩展. 使用 Codex 需要创建 FrontendIntegration FrontendIntegration YAML, 更新补丁 FI 生命周期状态, 检查排查 FI 构建输出, creaOperate FrontendIntegration resources and the frontend-forge extension. Use when Codex needs to create a FrontendIntegration from FrontendIntegration YAML, update or patch FI lifecycle state, inspect or troubleshoot FI build output, or crea#framework-internalskubesphere/kubesphereGit 克隆查看详情与安装步骤 → 框架内核16,317inference-format-optimizerSkillsMP@a2ui-projectIterative benchmarking, evaluation, algorithmic 优化 alternative A2UI 推理计算格式 ( Express, Atom, Elemental). 触发要求: (1) 运行优化 passes 循环推理计算格式化, (2) EvaluateIterative benchmarking, evaluation, and algorithmic optimization of alternative A2UI inference formats (such as Express, Atom, and Elemental). Trigger when asked to: (1) Run optimization passes or loops on an inference format, (2) Evaluate #framework-internalsa2ui-project/a2uiGit 克隆查看详情与安装步骤 → 框架内核16,039cpu-kernelSkillsMP@alibabaMNN CPU 后端 kernel 开发分支（`skills/cpu/` 下，另一分支是 `cpu/optimize` 性能归因）。覆盖标量 oracle → C++ SIMD → intrinsic → 汇编的四级实现阶梯、pack/kernel ABI 契约（tile、cell stride、后处理参数）、CoreFunctions 派发表注册与二级表安全构造、跨 ISA × 精度的正确性门禁，以及 AArch64 / x86_64 / RISC-V 三份实现参考。为 C#framework-internalsalibaba/mnnGit 克隆查看详情与安装步骤 → 框架内核16,039cpuSkillsMP@alibabaMNN CPU 后端（ARM / x86_64 / RISC-V 三侧）的总入口，只做分流不承载技术内容。下分 `optimize/`（为什么慢、该改哪一层）与 `kernel/`（这条 kernel 怎么写对、怎么被选中）两个分支，`shared/` 放两者共用的构建测试跑分命令、env 开关注册表与 RISC-V 开发板远端验证纪律。做 CPU 侧的工作但还不确定该进哪个分支，或需要三侧结构差异对照（第二张函数表按什么分、二级表怎么构造、`Precision_Low` 语#framework-internalsalibaba/mnnGit 克隆查看详情与安装步骤 → 框架内核16,039metal-optimizeSkillsMP@alibabaMNN Metal 后端 op/kernel 开发与优化入口。索引四份 sub-文档：kernel 开发规范与优化知识库（命名/写法/GEMV/GEMM/attention）、算子融合全链路（导出图→转换器→Metal 单 dispatch）、运行时调度（fence/content-cache/H2D/replay）、构建测试基线、env 开关注册表。根据当前任务选择性阅读对应 sub-文档。MNN Metal 后端 op/kernel 开发与优化入口。索引四份 sub-doc：kernel 开发规范与优化知识库（命名/写法/GEMV/GEMM/attention）、算子融合全链路（导出图→converter→Metal 单 dispatch）、运行时调度（fence/content-cache/H2D/replay）、构建测试基线、env 开关注册表。根据当前任务选择性阅读对应 sub-doc。#framework-internalsalibaba/mnnGit 克隆查看详情与安装步骤 → 框架内核15,875writing-build-stepsSkillsMP@quarkusio模式创建修改 Quarkus @BuildStep 方法, 构建条目, recorders 扩展部署模块.Patterns for creating and modifying Quarkus @BuildStep methods, build items, and recorders in extension deployment modules.#framework-internalsquarkusio/quarkusGit 克隆查看详情与安装步骤 → 框架内核15,122create-mreSkillsMP@Nuitka创建 reduce Minimally Reproducible 示例 (MRE) Nuitka 缺陷 larger reproducer. 使用用户要求 isolate, minimize, shrink Python 代码 preserving 编译器, 优化, packaging 工单.Create or reduce a Minimally Reproducible Example (MRE) for a Nuitka bug from a larger reproducer. Use when the user asks to isolate, minimize, or shrink Python code while preserving a compiler, optimization, or packaging issue.#framework-internalsnuitka/nuitkaGit 克隆查看详情与安装步骤 → 框架内核15,122fix-module-not-found-errorSkillsMP@NuitkaDiagnose 修复 `ModuleNotFoundError` Nuitka standalone binaries caused 缺失 implicit 导入. 使用编译 program fails 运行时 imported 模块内含.Diagnose and fix `ModuleNotFoundError` in Nuitka standalone binaries caused by missing implicit imports. Use when a compiled program fails at runtime because an imported module was not included.#framework-internalsnuitka/nuitkaGit 克隆查看详情与安装步骤 → 框架内核14,788toolingSkillsMP@dotnet实现细节 EF 核心 dotnet-ef CLI tooling. 使用修改 dotnet-ef 命令, ef 封装, EFCore. 工具 (PMC), EFCore. 任务 MSBuild 集成.Implementation details for the EF Core dotnet-ef CLI and tooling. Use when changing dotnet-ef commands, the ef wrapper, EFCore.Tools (PMC), or EFCore.Tasks MSBuild integration.#framework-internalsdotnet/efcoreGit 克隆查看详情与安装步骤 → 框架内核14,764typescriptSkillsMP@prowler-cloudTypeScript strict 模式最佳实践. 触发: 实现重构 TypeScript. ts/. tsx (types, 接口定义, 泛型, const 映射, type 守卫, removing, tightening unknown).TypeScript strict patterns and best practices. Trigger: When implementing or refactoring TypeScript in .ts/.tsx (types, interfaces, generics, const maps, type guards, removing any, tightening unknown).#framework-internalsprowler-cloud/prowlerGit 克隆查看详情与安装步骤 → 框架内核14,570kernel-cute-writingSkillsMP@NVIDIA编写实现 GPU kernels 使用 NVIDIA CuTe DSL (CUTLASS 4. x Python API) — NOT Triton, CUDA C++, conceptual explanations. 触发用户需求编写实现 kernel, asking 问题 CuTe DSLWrite and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations. Trigger only when the user wants to write or implement a kernel, not when asking questions about CuTe DSL#framework-internalsnvidia/tensorrt-llmGit 克隆查看详情与安装步骤 → 框架内核14,570kernel-tileir-optimizationSkillsMP@NVIDIA优化现有 Triton kernels NVIDIA TileIR 后端 Blackwell GPUs (sm_100+). 添加 TileIR-特定 autotune configs: occupancy, num_ctas, TMA descriptors. 覆盖 kernel 分类 (dot-相关, norm-例如, elementwise, reductioOptimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors. Covers kernel classification (dot-related, norm-like, elementwise, reductio#framework-internalsnvidia/tensorrt-llmGit 克隆查看详情与安装步骤 → 框架内核14,570kernel-triton-writingSkillsMP@NVIDIAONLY OpenAI Triton (@triton. jit) kernel 开发. NEVER 使用 CUDA C++ kernels, TileIR, profiling 工具 (ncu, nsys). 用户's 请求 involve Triton 显式地. 覆盖 Triton-特定模式: fused elementwise, reductioONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductio#framework-internalsnvidia/tensorrt-llmGit 克隆查看详情与安装步骤 → 框架内核14,570perf-optimizationSkillsMP@NVIDIA性能优化 coordination 操作手册. 包含 specialist 路由表格, TileIR two-步骤流水线, kernel generation specialist 选择, prioritization criteria, 安全 modification 工作流程. 使用用户要求应用 opPerformance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and safe modification workflow. Use when the user asks to apply op#framework-internalsnvidia/tensorrt-llmGit 克隆查看详情与安装步骤 → 框架内核14,570perf-torch-cuda-graphsSkillsMP@NVIDIA应用 CUDA 图谱 PyTorch workloads — API 选择 (torch. 编译, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, 手册 torch. cuda. 图谱), 代码 compatibility, 采集工作流程,Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows,#framework-internalsnvidia/tensorrt-llmGit 克隆查看详情与安装步骤 → 框架内核14,570perf-workload-profilingSkillsMP@NVIDIA代码 instrumentation timing workloads. Two 场景: (1) 训练循环 — inject 手册 timing 报告按-迭代延迟, 吞吐量 (samples/sec), 数据加载时间. (2) Standalone kernel/op — 编写 CUDA 事件 timing 代码 wCode instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time. (2) Standalone kernel/op — write CUDA event timing code with w#framework-internalsnvidia/tensorrt-llmGit 克隆查看详情与安装步骤 → 框架内核14,409marko-best-practicesSkillsMP@marko-js应用 Marko 语法最佳实践 editing `. marko` 文件构建 Marko 组件.Apply Marko syntax and best practices when editing `.marko` files and building Marko components.#framework-internalsmarko-js/markoGit 克隆查看详情与安装步骤 → 框架内核14,348distributed-trainingSkillsMP@aiming-lab多-GPU 分布式训练模式 PyTorch DDP. 使用 scaling 训练跨 GPUs.Multi-GPU and distributed training patterns with PyTorch DDP. Use when scaling training across GPUs.#framework-internalsaiming-lab/autoresearchclawGit 克隆查看详情与安装步骤 → 框架内核14,348pytorch-trainingSkillsMP@aiming-lab最佳实践构建健壮 PyTorch 训练循环. 使用生成评审 ML 训练代码.Best practices for building robust PyTorch training loops. Use when generating or reviewing ML training code.#framework-internalsaiming-lab/autoresearchclawGit 克隆查看详情与安装步骤 → 框架内核13,942open3d-cppSkillsMP@isl-org发现使用 Open3D C++ API correctly. 使用编写, 评审, 调试, porting C++ 代码对照 Open3D — point 云, triangle meshes, RGB-D 图片, 注册/ICP, odometry, SLAM/SLAC, reconstruction, ray casting, voxDiscover and use the Open3D C++ API correctly. Use when writing, reviewing, debugging, or porting C++ code against Open3D — point clouds, triangle meshes, RGB-D images, registration/ICP, odometry, SLAM/SLAC, reconstruction, ray casting, vox#framework-internalsisl-org/open3dGit 克隆查看详情与安装步骤 → 框架内核13,822implement-universalSkillsMP@Arindam200Harness-agnostic 版本 `/implement`. Drives 单个 workshop ticket SWE→Tester 循环 ONE 对话, 角色提示词 bundled `agents/software-engineer. md` `agents/tester. md` instead launched suHarness-agnostic version of `/implement`. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as `agents/software-engineer.md` and `agents/tester.md` instead of being launched as su#framework-internalsarindam200/awesome-ai-appsGit 克隆查看详情与安装步骤 → 框架内核13,755angular-modernizationSkillsMP@bitwardenModernizes Angular 代码组件 directives 遵循最佳实践使用自动 CLI 迁移 Bitwarden-特定模式. YOU 使用技能 someone 请求 modernizing Angular 代码. DO NOT 调用 foModernizes Angular code such as components and directives to follow best practices using both automatic CLI migrations and Bitwarden-specific patterns. YOU must use this skill when someone requests modernizing Angular code. DO NOT invoke fo#framework-internalsbitwarden/clientsGit 克隆查看详情与安装步骤 → 框架内核13,327trt-cpp-runtime-quickstartSkillsMP@NVIDIA加载运行 TensorRT 引擎 (. 计划 /. 引擎) C++ 使用 TensorRT 11 / 10. x **现代运行时 API**, avoiding deprecated TRT 8. x binding-索引 APIs older 指引 still promotes. 使用用户要求加载 oLoad and run a TensorRT engine (.plan / .engine) from C++ using the TensorRT 11 / 10.x **modern Runtime API**, avoiding the deprecated TRT 8.x binding-index APIs that older guidance still promotes. Use whenever the user asks about loading o#framework-internalsnvidia/tensorrtGit 克隆查看详情与安装步骤 → 框架内核13,327trt-strong-typing-migrationSkillsMP@NVIDIA迁移 TensorRT 构建 weak 类型标注 (deprecated 10.12, removed 11.0) strong 类型标注 — 跨 Python INetworkDefinition builders, trtexec CLI, C++ 构建器代码. 使用 TRT 11 升级 breaks weakly-typed 构建. 触发:Migrate a TensorRT build from weak typing (deprecated 10.12, removed 11.0) to strong typing — across Python INetworkDefinition builders, the trtexec CLI, and C++ builder code. Use when a TRT 11 upgrade breaks a weakly-typed build. Triggers:#framework-internalsnvidia/tensorrtGit 克隆查看详情与安装步骤 → 框架内核13,327trt-torch-quickstartSkillsMP@NVIDIA编译 PyTorch 模型 TensorRT 引擎通过 Torch-TensorRT — AOT JIT — 新建 strong-类型标注默认. 使用用户编译 PyTorch TensorRT 无需 ONNX, hits "enabled_precisions 用于 use_explicit_tCompile a PyTorch model to a TensorRT engine via Torch-TensorRT — AOT or JIT — under the new strong-typing default. Use when the user compiles PyTorch to TensorRT without ONNX, hits "enabled_precisions should not be used when use_explicit_t#framework-internalsnvidia/tensorrtGit 克隆查看详情与安装步骤 → 框架内核12,956effectSkillsMP@XiaomiMiMoAnswer 问题 Effect 框架Answer questions about the Effect framework#framework-internalsxiaomimimo/mimo-codeGit 克隆查看详情与安装步骤 → 框架内核12,648optimizeSkillsMP@Z3ProverSolve constrained 优化问题使用 Z3. 支持 minimization maximization objective 函数整数, 真实, bitvector 域名.Solve constrained optimization problems using Z3. Supports minimization and maximization of objective functions over integer, real, and bitvector domains.#framework-internalsz3prover/z3Git 克隆查看详情与安装步骤 → 框架内核12,641calypso-react-query-migrationSkillsMP@Automattic使用 editing 迁移 Calypso 阅读器数据-获取代码 — `client/components/data/query-reader-*` 组件, `@automattic/data-stores` 阅读器钩子, 新建阅读器 queries/mutations. 触发工作 involving `api-core`, `接口-qUse when editing or migrating Calypso Reader data-fetching code — `client/components/data/query-reader-*` components, `@automattic/data-stores` Reader hooks, or new Reader queries/mutations. Triggers on any work involving `api-core`, `api-q#framework-internalsautomattic/wp-calypsoGit 克隆查看详情与安装步骤 → 框架内核12,411pytorch-fsdp2SkillsMP@Orchestra-Research添加 PyTorch FSDP2 (fully_shard) 训练脚本 correct 初始化, sharding, mixed precision/offload 配置, 分布式 checkpointing. 使用模型 exceed 单个-GPU 记忆 need DTensor-基于 sharding DeviceMesAdds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMes#framework-internalsorchestra-research/ai-research-skillsGit 克隆查看详情与安装步骤 → 框架内核12,411ml-training-recipesSkillsMP@Orchestra-ResearchBattle-tested PyTorch 训练食谱域名 — LLMs, 视觉, diffusion, 医疗 imaging, protein/drug discovery, spatial omics, genomics. 覆盖训练循环, optimizer 选择 (AdamW, Muon), LR 排程, mixed precision, deBattle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, de#framework-internalsorchestra-research/ai-research-skillsGit 克隆查看详情与安装步骤 → 框架内核12,411fine-tuning-serving-openpiSkillsMP@Orchestra-Research精细-tune serve Physical Intelligence OpenPI 模型 (pi0, pi0-快速, pi0.5) 使用 JAX PyTorch backends 机器人政策推理计算跨 ALOHA, DROID, LIBERO environments. 使用 adapting pi0 模型自定义数据集, convertinFine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, convertin#framework-internalsorchestra-research/ai-research-skillsGit 克隆查看详情与安装步骤 → 框架内核12,238repro-apiSkillsMP@emdash-cmsReproduce EmDash 缺陷 below 浏览器层 -- REST 处理函数, CLI, MCP, 迁移, 结构注册中心, 构建 tooling. 浏览器. Prefer failing vitest 测试 affected 软件包, 运行 attached 容器.Reproduce an EmDash bug below the browser layer -- REST handlers, CLI, MCP, migrations, schema registry, or build tooling. No browser. Prefer a failing vitest test in the affected package, run in an attached container.#framework-internalsemdash-cms/emdashGit 克隆查看详情与安装步骤 → 框架内核11,980idapythonSkillsMP@mrexodiaIDA Pro Python scripting reverse 工程. 使用编写 IDAPython 脚本, 分析 binaries, 处理 IDA's API disassembly, decompilation (Hex-Rays), type 系统, cross-参考, 函数, segments, IDA 数据IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA data#framework-internalsmrexodia/ida-pro-mcpGit 克隆查看详情与安装步骤 → 框架内核11,732fprime-component-implementationSkillsMP@nasaC++ 实现阶段 F Prime 组件开发. 指南智能体实现处理函数函数生成 FPP 模型. 遵循 fprime-cpp-设计规则 (CPP-1 CPP-34). 触发 FPP 模型 confiC++ implementation phase of F Prime component development. Guides the agent through implementing handler functions generated from the FPP model. Must follow fprime-cpp-design rules (CPP-1 through CPP-34). Trigger when the FPP model is confi#framework-internalsnasa/fprimeGit 克隆查看详情与安装步骤 → 框架内核11,360cpp-proSkillsMP@Jeffallan编写, 优化, 调试 C++ 应用使用现代 C++20/23 功能, 模板 metaprogramming, high-performance 系统 techniques. 使用构建重构 C++ 代码需要 concepts, ranges, coroutines, SIMD optimizWrites, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and high-performance systems techniques. Use when building or refactoring C++ code requiring concepts, ranges, coroutines, SIMD optimiz#framework-internalsjeffallan/claude-skillsGit 克隆查看详情与安装步骤 → 框架内核11,360embedded-systemsSkillsMP@Jeffallan使用 developing 固件 microcontrollers, 实现 RTOS 应用, 优化 power consumption. 调用 STM32, ESP32, FreeRTOS, bare-metal, power 优化, 实时系统, 配置 peripherals, 编写 interruptUse when developing firmware for microcontrollers, implementing RTOS applications, or optimizing power consumption. Invoke for STM32, ESP32, FreeRTOS, bare-metal, power optimization, real-time systems, configure peripherals, write interrupt#framework-internalsjeffallan/claude-skillsGit 克隆查看详情与安装步骤 → 框架内核11,353kornia-developerSkillsMP@kornia使用 developing kornia — 制作 op torch. 编译 / dynamo compatible, 修复图谱 break, 优化提速. Codifies 编译-首先工作流程 — genuine fullgraph 修复 ( is_compiling hacks), byte-to-byte eager preservUse when developing on kornia — making an op torch.compile / dynamo compatible, fixing a graph break, or optimizing for speed. Codifies the compile-first workflow — genuine fullgraph fixes (no is_compiling hacks), byte-to-byte eager preserv#framework-internalskornia/korniaGit 克隆查看详情与安装步骤 → 框架内核11,223model-redux-state-build-slices-and-selectorsSkillsMP@reduxjs使用 authoring 重构 slices createSlice, 选择器, 创建. asyncThunk, 实体适配器, lazy 归约器 injection. 覆盖 Immer-backed mutation 语法, slice 选择器, getSelectors, injectInto, withLazyLoadedSlices,Use this when authoring or refactoring slices with createSlice, selectors, create.asyncThunk, entity adapters, or lazy reducer injection. Covers Immer-backed mutation syntax, slice selectors, getSelectors, injectInto, withLazyLoadedSlices, #framework-internalsreduxjs/redux-toolkitGit 克隆查看详情与安装步骤 → 框架内核11,074smarterrSkillsMP@hashicorp重构错误处理使用 smarterr.Refactor error handling to use smarterr.#framework-internalshashicorp/terraform-provider-awsGit 克隆查看详情与安装步骤 → 框架内核11,025huggingface-local-modelsSkillsMP@huggingface使用选择模型运行 locally llama. cpp GGUF CPU, Mac Metal, CUDA, ROCm. 覆盖 finding GGUFs, quant 选择, running 服务器, exact GGUF 文件查找, 转化, OpenAI-compatible 本地 serving.Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.#framework-internalshuggingface/skillsGit 克隆查看详情与安装步骤 → 框架内核11,025huggingface-zerogpuSkillsMP@huggingfaceAI 演示 GPU compute Gradio Spaces Hugging Face Spaces ZeroGPU. 使用编写评审代码使用 `@spaces. GPU`, 配置 `python_version` `requirements. txt` ZeroGPU Space, handling ZeroGPU-特定 coAI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific co#framework-internalshuggingface/skillsGit 克隆查看详情与安装步骤 → 框架内核10,809ov-gguf-add-architectureSkillsMP@openvinotoolkit启用新建模型 architecture/family OpenVINO GGUF 前端's 原生. gguf 构建器, 检查是否 GGUF 模型支持. 使用用户要求启用, 支持 bring up GGUF/llama. cpp 模型 (llama, qwen, phi, gemma,Enable a new model architecture/family in the OpenVINO GGUF frontend's native .gguf builder, or check whether a GGUF model is supported. Use when the user asks to enable, support or bring up a GGUF/llama.cpp model (llama, qwen, phi, gemma, #framework-internalsopenvinotoolkit/openvinoGit 克隆查看详情与安装步骤 → 框架内核10,809ov-gguf-enable-opSkillsMP@openvinotoolkit启用 ggml operation OpenVINO GGUF 前端新增修复 op translator. 使用转化 fails "翻译 operation type GGML_OP_* 实现", 用户要求 add/implement/fix GGUF ggmlEnable a ggml operation in the OpenVINO GGUF frontend by adding or fixing an op translator. Use when conversion fails with "Translation for operation type GGML_OP_* is not implemented", when the user asks to add/implement/fix a GGUF or ggml#framework-internalsopenvinotoolkit/openvinoGit 克隆查看详情与安装步骤 → 框架内核10,809ov-update-pytorch-versionSkillsMP@openvinotoolkit升级 PyTorch 版本用于 OpenVINO 测试 (torch / torchvision / torchaudio) 解决 fallout — 缺失运维者 translators, 新建 functionalized `*_copy` aten ops, decomposition 变更, FX- 测试 failing TorchScript 模式Upgrade the PyTorch version used by OpenVINO tests (torch / torchvision / torchaudio) and resolve fallout — missing operator translators, new functionalized `*_copy` aten ops, decomposition changes, FX-only tests failing in TorchScript mode#framework-internalsopenvinotoolkit/openvinoGit 克隆查看详情与安装步骤 → 框架内核10,809add-core-opSkillsMP@openvinotoolkit添加核心运维者 OpenVINO 工具集. 使用要求实现新建 operation OpenVINO.Adds a core operator to the OpenVINO toolkit. Use when asked to implement a new operation into OpenVINO.#framework-internalsopenvinotoolkit/openvinoGit 克隆查看详情与安装步骤 → 框架内核10,809add-gpu-opSkillsMP@openvinotoolkit添加新建 operation OpenVINO GPU 插件 — OpenCL kernel 设计, oneDNN-backed 路径, sub-分组/LWS tuning, functional 测试.Add a new operation to the OpenVINO GPU plugin — OpenCL kernel design, oneDNN-backed paths, sub-group/LWS tuning, and functional tests.#framework-internalsopenvinotoolkit/openvinoGit 克隆查看详情与安装步骤 → 框架内核10,313minicpm5-deploy-mlxSkillsMP@OpenBMB运行 MiniCPM5-1B natively Apple Silicon Apple's MLX 框架. 使用用户 Apple Silicon Mac 要求 "MLX", "mlx_lm", "mlx_lm. convert", "mlx_lm. generate", 需求 fastest 路径 Apple Silicon.Run MiniCPM5-1B natively on Apple Silicon with Apple's MLX framework. Use when the user has an Apple Silicon Mac and asks for "MLX", "mlx_lm", "mlx_lm.convert", "mlx_lm.generate", or wants the fastest path on Apple Silicon.#framework-internalsopenbmb/minicpmGit 克隆查看详情与安装步骤 → 框架内核10,313minicpm5-deploy-transformersSkillsMP@OpenBMB运行 MiniCPM5-1B Hugging Face Transformers 一个-shot Python generation GPU (bfloat16) CPU (float32). 使用用户需求快速 Python 脚本, 服务端, extra deps, 要求 "Transformers", "AutoModelForCausalLM", "Run MiniCPM5-1B with Hugging Face Transformers for one-shot Python generation on GPU (bfloat16) or CPU (float32). Use when the user wants a quick Python script, no server, no extra deps, or asks for "Transformers", "AutoModelForCausalLM", "#framework-internalsopenbmb/minicpmGit 克隆查看详情与安装步骤 → 框架内核10,313minicpm5-finetuneSkillsMP@OpenBMBPick 正确精细-tuning 框架 MiniCPM5-1B 基础 checkpoint 路由框架-特定 cookbook 技能. 使用用户需求 SFT / LoRA / DPO / continue-pretrain MiniCPM5 yet committed 特定 framewPick the right fine-tuning framework for a MiniCPM5-1B base checkpoint and route to a framework-specific cookbook skill. Use when the user wants to SFT / LoRA / DPO / continue-pretrain MiniCPM5 and has not yet committed to a specific framew#framework-internalsopenbmb/minicpmGit 克隆查看详情与安装步骤 → 框架内核10,313minicpm5-finetune-unslothSkillsMP@OpenBMB精细-tune MiniCPM5-1B unsloth tight-VRAM 单个-GPU LoRA / QLoRA. 使用用户需求 "unsloth", "FastLanguageModel", QLoRA 24 GB 消费方 GPU, 要求 smallest VRAM footprint.Fine-tune MiniCPM5-1B with unsloth for tight-VRAM single-GPU LoRA / QLoRA. Use when the user wants "unsloth", "FastLanguageModel", QLoRA on a 24 GB consumer GPU, or asks for the smallest VRAM footprint.#framework-internalsopenbmb/minicpmGit 克隆查看详情与安装步骤 → 框架内核10,251pinchtab-optSkillsMP@pinchtab运行 PinchTab 优化循环 (Docker, 3 blind subagents runner's HIGH 模型, 108 步骤跨 47 分组) 对照 chrome, cloak, ghost-chrome, 三个提供方. Pass `setup` (optionally followed 提供方 `all`)Run the PinchTab optimization loop (Docker, 3 blind subagents on the runner's HIGH model, 108 steps across 47 groups) against chrome, cloak, ghost-chrome, or all three providers. Pass `setup` (optionally followed by a provider or `all`) to #framework-internalspinchtab/pinchtabGit 克隆查看详情与安装步骤 → 框架内核9,905et-codeSkillsMP@egametangET 框架 C# 代码 authoring 评审工作流程. 使用创建修改实体, 组件, 系统, 辅助工具, 消息处理函数, 软件包依赖, assemblies, 模块 analyzer 边界, C# 文件 placement,. meta handling, ECS layET framework C# code authoring and review workflow. Use when creating or modifying Entity, Component, System, Helper, message handlers, package dependencies, assemblies, module analyzer boundaries, C# file placement, .meta handling, ECS lay#framework-internalsegametang/etGit 克隆查看详情与安装步骤 → 框架内核9,784openchamber-change-disciplineSkillsMP@openchamber使用实现, 修复, 重构, otherwise 修改 OpenChamber 源码, 依赖, 导出, 构建配置, 生成素材资源, 软件包合同, 模块 ownership.Use when implementing, fixing, refactoring, or otherwise modifying OpenChamber source code, dependencies, exports, build configuration, generated assets, package contracts, or module ownership.#framework-internalsopenchamber/openchamberGit 克隆查看详情与安装步骤 → 框架内核9,768detect-frameworkSkillsMP@omnigent-ai检测 Python 智能体框架代码导入映射 Omnigent executor types. 加载用户现有智能体代码集成.Detect Python agent frameworks from code imports and map them to Omnigent executor types. Load when the user has existing agent code to integrate.#framework-internalsomnigent-ai/omnigentGit 克隆查看详情与安装步骤 → 框架内核9,749review-cudf-polars-expressionsSkillsMP@NVIDIA使用实现评审支持 Polars Expressions cudf-polarsUse when implementing or reviewing support for Polars Expressions in cudf-polars#framework-internalsnvidia/cudfGit 克隆查看详情与安装步骤 → 框架内核9,254remote-compute-modalSkillsMP@advaitpaliwalDispatch Feynman 研究 notebook 实验作业弹窗. 使用任务显式地 chosen 弹窗 bounded 云端 compute, GPU 作业, reproducible 远程执行.Dispatch Feynman research notebook or experiment jobs to Modal. Use when a task has explicitly chosen Modal for bounded cloud compute, GPU jobs, or reproducible remote execution.#framework-internalsadvaitpaliwal/feynmanGit 克隆查看详情与安装步骤 → 框架内核8,658beam-dofn-modernizerSkillsMP@apacheRewrite Apache Beam DoFn 方法 (@ProcessElement, @OnTimer, @OnWindowExpiration) 移除遗留 ProcessContext OnTimerContext 用法. 使用技能 encounter DoFn 方法使用上下文. element(), 上下文. 输出(),.,Rewrite Apache Beam DoFn methods (@ProcessElement, @OnTimer, @OnWindowExpiration) to remove legacy ProcessContext or OnTimerContext usage. Use this skill when you encounter DoFn methods that use context.element(), context.output(), etc., an#framework-internalsapache/beamGit 克隆查看详情与安装步骤 → 框架内核8,443deepep-to-cam-converterSkillsMP@openJiuwen-ai识别代码中可替换为CAM算子的DeepEP算子，基于实际运行参数校验约束，自动完成通信域转换（NCCL->HCCL）、设备适配（CUDA->NPU）及算子替换。#framework-internalsopenjiuwen-ai/jiuwenswarmGit 克隆查看详情与安装步骤 → 框架内核8,171simplify-codeSkillsMP@vudovnReduce complexity over-engineered 代码. 识别 unnecessary abstractions, 移除 dead 代码, flatten 深度 nesting, 简化逻辑 preserving 行为.Reduce complexity of over-engineered code. Identify unnecessary abstractions, remove dead code, flatten deep nesting, and simplify logic while preserving behavior.#framework-internalsvudovn/ag-kitGit 克隆查看详情与安装步骤 → 框架内核8,044docker-buildSkillsMP@InternLM构建 CUDA 13.0 CUDA 12.8 LMDeploy Docker 镜像 push inner 注册中心.Build a CUDA 13.0 or CUDA 12.8 LMDeploy Docker image and push it to the inner registry.#framework-internalsinternlm/lmdeployGit 克隆查看详情与安装步骤 → 框架内核8,044support-new-modelSkillsMP@InternLM添加新建 LLM VLM LMDeploy's PyTorch 后端.Add a new LLM or VLM to LMDeploy's PyTorch backend.#framework-internalsinternlm/lmdeployGit 克隆查看详情与安装步骤 → 框架内核7,527code-execution-fallbackSkillsMP@HKUDS处理代码执行失败 fallback 策略 anchored 工作区路径Handle code execution failures with fallback strategies and anchored workspace paths#framework-internalshkuds/openspaceGit 克隆查看详情与安装步骤 → 框架内核7,527python-execution-fallbackSkillsMP@HKUDSFour-步骤 recovery 工作流程代码执行失败行内 Python failsFour-step recovery workflow for code execution failures when inline Python fails#framework-internalshkuds/openspaceGit 克隆查看详情与安装步骤 → 框架内核7,484fix-intSkillsMP@FastLED修复整数 type definitions 指定平台. Researches correct primitive type mappings 应用修复平台-特定 int 请求头.Fix integer type definitions for specified platform. Researches correct primitive type mappings and applies fixes to platform-specific int headers.#framework-internalsfastled/fastledGit 克隆查看详情与安装步骤 → 框架内核7,484platform-portSkillsMP@FastLED指南 porting FastLED 新建 MCU 平台, 包括 int. h types, clockless drivers, SPI implementations, 平台检测. 使用新增支持新建单片机 family board.Guide porting FastLED to new MCU platforms, including int.h types, clockless drivers, SPI implementations, and platform detection. Use when adding support for a new microcontroller family or board.#framework-internalsfastled/fastledGit 克隆查看详情与安装步骤 → 框架内核7,224adapter-opsSkillsMP@ZipstackExtend LLM 向量嵌入适配器 unstract/sdk1. 使用新增新建适配器 (LLM 向量嵌入), removing 适配器, adding/removing 模型现有适配器, editing 适配器 configurations. 支持 OpenAI-compatible 提供方, clExtend LLM and embedding adapters in unstract/sdk1. Use when adding new adapters (LLM or embedding), removing adapters, adding/removing models to existing adapters, or editing adapter configurations. Supports OpenAI-compatible providers, cl#framework-internalszipstack/unstractGit 克隆查看详情与安装步骤 → 框架内核7,130honcho-integrationSkillsMP@plastic-labs集成 Honcho 记忆现有 Python TypeScript codebases. 使用新增 Honcho SDK, 设置项 up peers, 配置 sessions, accessing Honcho's representation.Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.#framework-internalsplastic-labs/honchoGit 克隆查看详情与安装步骤 → 框架内核7,085warp-compile-time-optimizerSkillsMP@NVIDIA使用编译时间 startup 时间问题代码使用 Warp: 请求改进, 优化, cut 编译 times; 应用缓慢启动 stalls 首先 wp. 上线; seconds compiling 在…之前真实工作 begins;Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start or stalls at the first wp.launch; seconds of compiling before real work begins; #framework-internalsnvidia/warpGit 克隆查看详情与安装步骤 → 框架内核7,065internal-extend-css-converterSkillsMP@elementor内部: Extend atomic CSS 转换器核心 fork submit 核心 PR. Shorthand_Expander_Base, Property_Converter_Base, 公开 discovery 钩子.Internal: Extend the atomic CSS converter in a Core fork and submit a Core PR. Shorthand_Expander_Base, Property_Converter_Base, no public discovery hook.#framework-internalselementor/elementorGit 克隆查看详情与安装步骤 → 框架内核7,065internal-extend-interactionsSkillsMP@elementor内部: Extend v4 interactions 端到端核心 fork submit 核心 PR. Editor APIs exist externally; 发布-页面运行时公开钩子.Internal: Extend v4 interactions end-to-end in a Core fork and submit a Core PR. Editor APIs exist externally; published-page runtime has no public hook.#framework-internalselementor/elementorGit 克隆查看详情与安装步骤 → 框架内核6,941add-torch-shapes-exampleSkillsMP@facebook使用新增新建 PyTorch 模型 Pyrefly's shape-跟踪示例 corpus tensor-shapes/pyrefly-torch-stubs/examples —. e. importing 模型 tested, corpus-质量参考 port. 维护者-facing fbsource 工作. FoUse when adding a new PyTorch model to Pyrefly's shape-tracking example corpus under tensor-shapes/pyrefly-torch-stubs/examples — i.e. importing a model as a tested, corpus-quality reference port. This is maintainer-facing fbsource work. Fo#framework-internalsfacebook/pyreflyGit 克隆查看详情与安装步骤 → 框架内核6,834chrome-extension-developmentSkillsMP@midudev专家规范指南 Chrome 扩展开发 Manifest V3, 覆盖安全, performance, 最佳实践Expert guidelines for Chrome extension development with Manifest V3, covering security, performance, and best practices#framework-internalsmidudev/autoskillsGit 克隆查看详情与安装步骤 → 框架内核6,834fastmcpSkillsMP@midudev生产环境模式 FastMCP Python MCP 服务器. 使用编写, improving, 调试 FastMCP Python 代码 — tool 结构设计, 多-operation 工具, pre-formatted 输出, 上下文用法, 中间件, lifespan startup/shutdown hoProduction patterns for FastMCP Python MCP servers. Use when writing, improving, or debugging FastMCP Python code — tool schema design, multi-operation tools, pre-formatted output, Context usage, middleware, lifespan and startup/shutdown ho#framework-internalsmidudev/autoskillsGit 克隆查看详情与安装步骤 → 框架内核6,804cavemanSkillsMP@stagewise-ioUltra-compressed communication 模式. Cuts 输出词元 65% (measured) speaking 例如 caveman keeping 完整 technical accuracy. 支持 intensity levels: lite, 完整 (默认), ultra, wenyan-lite, wenyan-完整, wenyan-ultra. 使用Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when #framework-internalsstagewise-io/stagewiseGit 克隆查看详情与安装步骤 → 框架内核6,601liger-kernel-devSkillsMP@linkedinDevelops 生产环境-就绪 Triton kernels Liger Kernel. 创建新建 kernels PyTorch 运维 (本地文件, URLs, 代码片段, 自然语言) ops, 模块封装, functional APIs, 单元测试, 基准测试, plots. AlDevelops production-ready Triton kernels for Liger Kernel. Creates new kernels from PyTorch operations (local files, URLs, code snippets, or natural language) with ops, module wrappers, functional APIs, unit tests, benchmarks, and plots. Al#framework-internalslinkedin/liger-kernelGit 克隆查看详情与安装步骤 → 框架内核6,601liger-kernel-perfSkillsMP@linkedin优化 performance 现有 Liger Kernel Triton kernels. Profiles kernels, diagnoses bottlenecks (记忆-bound vs compute-bound), 生成多个优化 variants benchmarking, 应用 best variant maintOptimizes the performance of existing Liger Kernel Triton kernels. Profiles kernels, diagnoses bottlenecks (memory-bound vs compute-bound), generates multiple optimization variants with benchmarking, and applies the best variant while maint#framework-internalslinkedin/liger-kernelGit 克隆查看详情与安装步骤 → 框架内核6,368mz-adapter-guideSkillsMP@MaterializeIncCorrectness invariants + 架构: 适配器, coordinator, pgwire, peek 路径, timestamp oracle. 触发: 问题 subsystems — " coordinator 工作", " 读取 holds", "explain peek 路径", " timestamp seleCorrectness invariants + architecture: adapter, coordinator, pgwire, peek paths, timestamp oracle. Trigger: questions about these subsystems — "how does coordinator work", "what are read holds", "explain peek path", "how does timestamp sele#framework-internalsmaterializeinc/materializeGit 克隆查看详情与安装步骤 → 框架内核6,340add-cuda-kernelSkillsMP@flashinfer-ai分步教程新增新建 CUDA kernels FlashInferStep-by-step tutorial for adding new CUDA kernels to FlashInfer#framework-internalsflashinfer-ai/flashinferGit 克隆查看详情与安装步骤 → 框架内核6,340benchmark-kernelSkillsMP@flashinfer-ai指南 benchmarking FlashInfer kernels CUPTI timingGuide for benchmarking FlashInfer kernels with CUPTI timing#framework-internalsflashinfer-ai/flashinferGit 克隆查看详情与安装步骤 → 框架内核6,324squirrel-input-method-architectureSkillsMP@rimeUnderstand 修改 Squirrel macOS 输入方法前端. 使用处理输入 handling, librime sessions, candidate UI, 配置, 生命周期, 安装器命令, backend/frontend coordination 仓库.Understand and modify the Squirrel macOS input method frontend. Use this when working on input handling, librime sessions, candidate UI, configuration, lifecycle, installer commands, or backend/frontend coordination in this repository.#framework-internalsrime/squirrelGit 克隆查看详情与安装步骤 → 框架内核6,055create-framework-componentSkillsMP@skeletonlabs创建框架组件跨 支持软件包使用仓库's anatomy/modules 约定.Create framework components across all supported packages using the repository's anatomy/modules conventions.#framework-internalsskeletonlabs/skeletonGit 克隆查看详情与安装步骤 → 框架内核5,918optimizeSkillsMP@FlorianBruniaux分析 suggest performance improvements 代码, 查询, 系统Analyze and suggest performance improvements for code, queries, or systems#framework-internals#database-tools#sql-databasesflorianbruniaux/claude-code-ultimate-guideGit 克隆查看详情与安装步骤 → 框架内核5,748daft-udf-tuningSkillsMP@Eventual-Inc优化 Daft UDF performance. 调用用户需要 GPU 推理计算, encounters 缓慢 UDFs, 要求 async/batch 处理.Optimize Daft UDF performance. Invoke when user needs GPU inference, encounters slow UDFs, or asks about async/batch processing.#framework-internalseventual-inc/daftGit 克隆查看详情与安装步骤 → 框架内核5,706fla-ascend-performanceSkillsMP@fla-org规范指南 Ascend NPU kernel / Triton-Ascend 后端 performance 工作 FLA 仓库. 覆盖 profiling torch_npu, PipeUtilization/MemoryUB CSV 分析, Cube/Vector/MTE/UB bottleneck 诊断, kernel 优化 (UB tiling,Guidelines for Ascend NPU kernel / Triton-Ascend backend performance work in the FLA repo. Covers profiling with torch_npu, PipeUtilization/MemoryUB CSV analysis, Cube/Vector/MTE/UB bottleneck diagnosis, and kernel optimization (UB tiling, #framework-internalsfla-org/flash-linear-attentionGit 克隆查看详情与安装步骤 → 框架内核5,706fla-correctness-coverageSkillsMP@fla-org规范指南 kernel correctness testing coverage fla/ops/** 相关模块, 包括通用 Triton grid/addressing pitfalls. 帮助 decide 测试添加运行在…之前 MR.Guidelines for kernel correctness testing and coverage in fla/ops/** and related modules, including common Triton grid/addressing pitfalls. Helps decide what tests to add or run before an MR.#framework-internalsfla-org/flash-linear-attentionGit 克隆查看详情与安装步骤 → 框架内核5,706fla-dispatch-backendsSkillsMP@fla-org工作流程 FLA 后端 dispatch decorators 后端 implementations. 使用 touching fla. ops. backends, @dispatch-decorated 函数, BaseBackend subclasses, 后端 verifier 方法, 后端 env vars, 后端测试.Workflow for FLA backend dispatch decorators and backend implementations. Use when touching fla.ops.backends, @dispatch-decorated functions, BaseBackend subclasses, backend verifier methods, backend env vars, or backend tests.#framework-internalsfla-org/flash-linear-attentionGit 克隆查看详情与安装步骤 → 框架内核5,706fla-optimization-loopSkillsMP@fla-orgDisciplined, reproducible 循环制作 FLA kernel 更快 (Triton, Gluon, TileLang, CuTe) 无需 breaking 游戏 correctness. Synthesizes 任务-合同 / 三个-阶段 / 迭代-协议 / silent-缺陷-目录 disciplineDisciplined, reproducible loop for making an FLA kernel faster (Triton, Gluon, TileLang, CuTe) without ever breaking or gaming correctness. Synthesizes the task-contract / three-phase / iteration-protocol / silent-bug-catalog discipline of #framework-internalsfla-org/flash-linear-attentionGit 克隆查看详情与安装步骤 → 框架内核5,706fla-triton-to-gluonSkillsMP@fla-org工作流程 porting 现有 Triton kernel `fla/ops/**` Gluon (`triton. experimental. gluon`) gain 显式控制 tensor 布局, 共享记忆, 异步数据 movement (cp. 异步 / TMA), MMA (WGMMA / tcgen05), 排程 (Workflow for porting an existing Triton kernel in `fla/ops/**` to Gluon (`triton.experimental.gluon`) to gain explicit control over tensor layouts, shared memory, async data movement (cp.async / TMA), MMA (WGMMA / tcgen05), and scheduling (#framework-internalsfla-org/flash-linear-attentionGit 克隆查看详情与安装步骤 → 框架内核5,547cswin32-interopSkillsMP@dotnet指南 CsWin32 P/Invoke interop MSBuild. Consult 处理 PInvoke 类, Windows. Win32 namespaces, FEATURE_WINDOWSINTEROP, HANDLE/HMODULE/HRESULT types, BufferScope<T>, replacing [DllImport] CsWin32, conditioning WinGuides CsWin32 P/Invoke interop in MSBuild. Consult when working with the PInvoke class, Windows.Win32 namespaces, FEATURE_WINDOWSINTEROP, HANDLE/HMODULE/HRESULT types, BufferScope<T>, replacing [DllImport] with CsWin32, or conditioning Win#framework-internalsdotnet/msbuildGit 克隆查看详情与安装步骤 → 框架内核5,547dotnet-aot-compatSkillsMP@dotnet制作. NET 项目 compatible 原生 AOT trimming systematically 解决 IL trim/AOT analyzer 警告. USE FOR: 制作项目 AOT-compatible, 修复 trimming 警告, 解决 IL 警告 (IL2026, IL2070, IL2067, IL2072,Make .NET projects compatible with Native AOT and trimming by systematically resolving IL trim/AOT analyzer warnings. USE FOR: making projects AOT-compatible, fixing trimming warnings, resolving IL warnings (IL2026, IL2070, IL2067, IL2072, #framework-internalsdotnet/msbuildGit 克隆查看详情与安装步骤 → 框架内核5,493defense-evasionSkillsMP@PurpleAILAB接口 defense bypass — AMSI/ETW patching, ScareCrow 框架, 自定义 loaders, direct/indirect syscalls, LOLBAS 执行, 流程 injection.Endpoint defense bypass — AMSI/ETW patching, ScareCrow framework, custom loaders, direct/indirect syscalls, LOLBAS execution, process injection.#framework-internalspurpleailab/decepticonGit 克隆查看详情与安装步骤 → 框架内核5,493command-injectionSkillsMP@PurpleAILABHunt OS 命令 injection (CWE-78) — 用户输入 reaching Shell, exec, 系统调用. 覆盖 argument-数组 bypasses, 路径 confusion, 模板-字符串 injection 现代框架.Hunt OS command injection (CWE-78) — user input reaching shell, exec, or system calls. Covers argument-array bypasses, path confusion, and template-string injection in modern frameworks.#framework-internalspurpleailab/decepticonGit 克隆查看详情与安装步骤 → 框架内核5,493il2cppSkillsMP@PurpleAILABUnity IL2CPP 游戏 reversing — Il2CppDumper 元数据 recovery, 全局-元数据. dat decryption, IDA/Ghidra symbol 恢复通过生成脚本, Frida 方法 hooking, IAP/许可证 bypass, zygisk-il2cpp-dumper obfuscated 元数据.Unity IL2CPP game reversing — Il2CppDumper metadata recovery, global-metadata.dat decryption, IDA/Ghidra symbol restore via generated scripts, Frida method hooking, IAP/license bypass, and zygisk-il2cpp-dumper for obfuscated metadata.#framework-internalspurpleailab/decepticonGit 克隆查看详情与安装步骤 → 框架内核5,493c2-havocSkillsMP@PurpleAILABHavoc C2 框架 (C5pider/Havoc) — 现代 Sliver/CS alternative, Demon 智能体 indirect syscalls, 睡眠 obfuscation (Ekko/Zilean/FOLIAGE), Donut PIC loader 集成, 个人资料-driven HTTP comms, MaterialUI 网页客户端. Best neHavoc C2 framework (C5pider/Havoc) — modern Sliver/CS alternative, Demon agent with indirect syscalls, sleep obfuscation (Ekko/Zilean/FOLIAGE), Donut PIC loader integration, profile-driven HTTP comms, MaterialUI web client. Best when you ne#framework-internalspurpleailab/decepticonGit 克隆查看详情与安装步骤 → 框架内核5,493c2-sliverSkillsMP@PurpleAILABSliver C2 框架运维 — 服务端 connection, 监听器初始化设置, implant generation, BOF/Armory 扩展, 帖子-implant 运维, HTTP C2 profiles.Sliver C2 framework operations — server connection, listener setup, implant generation, BOF/Armory extensions, post-implant operations, HTTP C2 profiles.#framework-internalspurpleailab/decepticonGit 克隆查看详情与安装步骤 → 框架内核5,493reverser-virtualized-protectorsSkillsMP@PurpleAILABVMProtect, VMP2, Themida, CodeVirtualizer reversing 工作流程使用 Radare2/Ghidra facts Back 工程 Labs 研究指引.VMProtect, VMP2, Themida, and CodeVirtualizer reversing workflow using Radare2/Ghidra facts and Back Engineering Labs research guidance.#framework-internalspurpleailab/decepticonGit 克隆查看详情与安装步骤 → 框架内核5,426zoom-meeting-sdk-unrealSkillsMP@openaiZoom Meeting SDK Unreal 引擎封装 integrations. 使用构建 Unreal 项目 embed Zoom meetings C++ 蓝图封装, 包括封装-to-SDK 映射 concerns.Zoom Meeting SDK for Unreal Engine wrapper integrations. Use when building Unreal projects that embed Zoom meetings with C++ and Blueprint wrappers, including wrapper-to-SDK mapping concerns.#framework-internalsopenai/pluginsGit 克隆查看详情与安装步骤 → 框架内核5,383dotnet-pinvokeSkillsMP@dotnetCorrectly 调用原生 (C/C++) 函数库. NET 使用 P/Invoke LibraryImport. 覆盖函数签名, 字符串 marshalling, 记忆 lifetime, SafeHandle, 跨平台模式. USE FOR: 编写新建 P/Invoke LibraryImport decCorrectly call native (C/C++) libraries from .NET using P/Invoke and LibraryImport. Covers function signatures, string marshalling, memory lifetime, SafeHandle, and cross-platform patterns. USE FOR: writing new P/Invoke or LibraryImport dec#framework-internalsdotnet/skillsGit 克隆查看详情与安装步骤 → 框架内核5,383migrate-dotnet8-to-dotnet9SkillsMP@dotnet迁移. NET 8 项目. NET 9 解决 breaking 变更. USE FOR: 升级 TargetFramework net8.0 net9.0, 修复构建错误在…之后更新. NET 9 SDK, 解决行为变更. NET 9 / C# 13 / ASP. NET 核心Migrate a .NET 8 project to .NET 9 and resolve all breaking changes. USE FOR: upgrading TargetFramework from net8.0 to net9.0, fixing build errors after updating the .NET 9 SDK, resolving behavioral changes in .NET 9 / C# 13 / ASP.NET Core #framework-internalsdotnet/skillsGit 克隆查看详情与安装步骤 → 框架内核5,383migrate-dotnet9-to-dotnet10SkillsMP@dotnet迁移. NET 9 项目解决方案. NET 10 解决 breaking 变更. USE FOR: 升级 TargetFramework net9.0 net10.0, 修复构建错误在…之后更新. NET 10 SDK, 解决来源行为变更. NETMigrate a .NET 9 project or solution to .NET 10 and resolve all breaking changes. USE FOR: upgrading TargetFramework from net9.0 to net10.0, fixing build errors after updating the .NET 10 SDK, resolving source and behavioral changes in .NET#framework-internalsdotnet/skillsGit 克隆查看详情与安装步骤 → 框架内核5,383thread-abort-migrationSkillsMP@dotnet指南迁移. NET 框架线程. Abort 用法 cooperative cancellation 现代. NET. USE FOR: modernizing 代码调用线程. Abort, catching ThreadAbortException, replacing 线程. ResetAbort, replacing 线程. InterruptGuides migration of .NET Framework Thread.Abort usage to cooperative cancellation in modern .NET. USE FOR: modernizing code that calls Thread.Abort, catching ThreadAbortException, replacing Thread.ResetAbort, replacing Thread.Interrupt for #framework-internalsdotnet/skillsGit 克隆查看详情与安装步骤 → 框架内核5,303exporting-to-fhirSkillsMP@maziyarpanahi转换 OpenMed NER 输出 (实体 openmed. analyze_text) FHIR R4 资源 — Condition, MedicationStatement, Observation — 使用 OpenMed's 构建- FHIR R4 导出辅助函数 openmed. 临床. exporters. 覆盖 verified CodeabConvert OpenMed NER output (entities from openmed.analyze_text) into FHIR R4 resources — Condition, MedicationStatement, Observation — using OpenMed's built-in FHIR R4 export helpers in openmed.clinical.exporters. Covers the verified Codeab#framework-internalsmaziyarpanahi/openmedGit 克隆查看详情与安装步骤 → 框架内核5,303extract-clinical-entities-to-fhirSkillsMP@maziyarpanahi提取临床实体 synthetic already de-识别文本 OpenMed 映射 deterministic FHIR R4 资源打包合集. 使用智能体转换本地临床 NER 输出 Conditions, MedicationStatements,Extract clinical entities from synthetic or already de-identified text with OpenMed and map them into deterministic FHIR R4 resources and a Bundle. Use when an agent must turn local clinical NER output into Conditions, MedicationStatements,#framework-internalsmaziyarpanahi/openmedGit 克隆查看详情与安装步骤 → 框架内核5,303running-openmed-ondeviceSkillsMP@maziyarpanahi运行 OpenMed 模型 fully on-设备 MLX (Apple Silicon), CoreML (iOS/macOS), ONNX/WebGPU (cross-platform/browser) backends, 包括转换-quantize-运行工作流程. 使用用户需求部署 OpenMed edge, 运行 NER/Run OpenMed models fully on-device with the MLX (Apple Silicon), CoreML (iOS/macOS), or ONNX/WebGPU (cross-platform/browser) backends, including convert-quantize-run workflows. Use when the user wants to deploy OpenMed at the edge, run NER/#framework-internalsmaziyarpanahi/openmedGit 克隆查看详情与安装步骤 → 框架内核5,290gluestack-ui-v4-performanceSkillsMP@gluestack性能优化跨平台模式 gluestack-界面 v4 - 覆盖 native/web compatibility, TypeScript, memoization, 动画, 最佳实践.Performance optimization and cross-platform patterns for gluestack-ui v4 - covers native/web compatibility, TypeScript, memoization, animations, and best practices.#framework-internalsgluestack/gluestack-uiGit 克隆查看详情与安装步骤 → 框架内核5,290gluestack-ui-v4-variantsSkillsMP@gluestack指南创建自定义 variants gluestack-界面 v4 组件 - 覆盖 tva 用法, extending 组件, variant 模式, customization 策略.Guide for creating custom variants for gluestack-ui v4 components - covers tva usage, extending components, variant patterns, and customization strategies.#framework-internalsgluestack/gluestack-uiGit 克隆查看详情与安装步骤 → 框架内核5,181vyper-compilerSkillsMP@vyperlangVyper 智能合约编译器 internals. 使用处理 Vyper 编译器代码库 — 编译流水线, Venom IR, 语义分析, 代码生成, testing, contributing. 触发 vyper 编译器开发, Venom passes,Vyper smart contract compiler internals. Use when working on the Vyper compiler codebase — compilation pipeline, Venom IR, semantic analysis, code generation, testing, or contributing. Triggers on vyper compiler development, Venom passes, A#framework-internalsvyperlang/vyperGit 克隆查看详情与安装步骤 → 框架内核4,998binary-sizeSkillsMP@pytorch分析 reduce ExecuTorch binary size. 使用 investigating binary size, running size 测试, 优化运行时 size-constrained 部署.Analyze and reduce ExecuTorch binary size. Use when investigating binary size, running size tests, or optimizing the runtime for size-constrained deployments.#framework-internalspytorch/executorchGit 克隆查看详情与安装步骤 → 框架内核4,998buildingSkillsMP@pytorch构建 ExecuTorch 来源 — Python 软件包, C++ 运行时, runners, cross-编译, 后端-特定构建. 使用 compiling anything ExecuTorch 仓库, diagnosing 构建失败, 设置项 up 平台-特定构建.Build ExecuTorch from source — Python package, C++ runtime, runners, cross-compilation, and backend-specific builds. Use when compiling anything in the ExecuTorch repo, diagnosing build failures, or setting up platform-specific builds.#framework-internalspytorch/executorchGit 克隆查看详情与安装步骤 → 框架内核4,998executorch-kbSkillsMP@pytorch搜索 ExecuTorch tribal 知识库覆盖 QNN, XNNPACK, Vulkan, CoreML, Arm, Cadence backends, quantization 食谱, 导出 pitfalls, 运行时错误, SoC compatibility. 使用调试 ExecuTorch 错误, 选择 quantSearch the ExecuTorch tribal knowledge base covering QNN, XNNPACK, Vulkan, CoreML, Arm, and Cadence backends, quantization recipes, export pitfalls, runtime errors, and SoC compatibility. Use when debugging ExecuTorch errors, choosing quant#framework-internalspytorch/executorchGit 克隆查看详情与安装步骤 → 框架内核4,998exportSkillsMP@pytorch导出 PyTorch 模型. pte 格式化 ExecuTorch. 使用 converting 模型, lowering edge, 生成. pte 文件.Export a PyTorch model to .pte format for ExecuTorch. Use when converting models, lowering to edge, or generating .pte files.#framework-internalspytorch/executorchGit 克隆查看详情与安装步骤 → 框架内核4,998zephyrSkillsMP@pytorch构建配置 ExecuTorch Zephyr RTOS 模块嵌入式 boards. 使用设置项 up Zephyr 工作区 ET, 新增 board 支持 (overlays, confs, 记忆布局), 构建 west, 调试 linker 记忆 overflow.Build and configure ExecuTorch as a Zephyr RTOS module for embedded boards. Use when setting up a Zephyr workspace with ET, adding board support (overlays, confs, memory layout), building with west, or debugging linker memory overflow.#framework-internalspytorch/executorchGit 克隆查看详情与安装步骤 → 框架内核4,956fastllm-triton-opsSkillsMP@ztxz16指南新增 Triton-backed CUDA operators FastLLM. 使用修改 FastLLM CUDA op 代码添加, extend, 调试, 校验, 基准测试 Triton-生成 kernels 工具/fastllm_triton_server. py, src/devices/cuda/cudadevice. cppGuide for adding Triton-backed CUDA operators to FastLLM. Use when modifying FastLLM CUDA op code to add, extend, debug, validate, or benchmark Triton-generated kernels through tools/fastllm_triton_server.py, src/devices/cuda/cudadevice.cpp#framework-internalsztxz16/fastllmGit 克隆查看详情与安装步骤 → 框架内核4,858connector-transformSkillsMP@apache添加新建转换 `core/connectors/sdk/src/transforms/`. 转换 mutate, 筛选, 转换消息 source/encode decode/sink. 使用新增 field-级别转换 (add/delete/update/filter), 格式化转化, enAdd a new transform under `core/connectors/sdk/src/transforms/`. Transforms mutate, filter, or convert messages between source/encode and decode/sink. Use when adding field-level transforms (add/delete/update/filter), format conversions, en#framework-internalsapache/iggyGit 克隆查看详情与安装步骤 → 框架内核4,858download-sdkSkillsMP@dotnet操作说明 downloading installing. NET preview 运行时版本必需 WinForms 仓库. 使用测试 executables fail "框架 found" 错误特定. NET preview 运行时版本需要 instInstructions for downloading and installing .NET preview runtime versions required by the WinForms repository. Use when test executables fail with "framework not found" errors or when a specific .NET preview runtime version needs to be inst#framework-internalsdotnet/winformsGit 克隆查看详情与安装步骤 → 框架内核4,856meojsonSkillsMP@MaaXYZ指南使用 meojson C++ JSON 函数库 MaaFramework. 使用编写代码 involves JSON 解析, 序列化, struct jsonization (MEO_JSONIZATION), JSON:: value manipulation, ext:: jsonization 自定义 type 支持, 日志记录Guide for using the meojson C++ JSON library in MaaFramework. Use when writing code that involves JSON parsing, serialization, struct jsonization (MEO_JSONIZATION), json::value manipulation, ext::jsonization custom type support, or logging #framework-internalsmaaxyz/maaframeworkGit 克隆查看详情与安装步骤 → 框架内核4,760error-consolidation-setupSkillsMP@dotnet创建 consolidated C# 编译器诊断文章 skeleton, TOC 入口, 可选 seed-代码元数据. 使用启动新建错误-consolidation 工作流程.Creates a consolidated C# compiler diagnostic article skeleton, TOC entry, and optional seed-code metadata. Use to start a new error-consolidation workflow.#framework-internalsdotnet/docsGit 克隆查看详情与安装步骤 → 框架内核4,736agent-native-docsSkillsMP@BuilderIO如何查找版本-匹配智能体-原生框架文档来源 bundled node_modules. 使用在…之前实现 answering 问题 @智能体-native/core APIs, 生成应用, 工作区, 模板, 先进功能.How to find version-matched Agent-Native framework docs and source bundled in node_modules. Use before implementing or answering questions about @agent-native/core APIs, generated apps, workspaces, templates, or advanced features.#framework-internalsbuilderio/agent-nativeGit 克隆查看详情与安装步骤 → 框架内核4,736harness-agentsSkillsMP@BuilderIO添加使用完整智能体 harness runtimes 例如 Claude 代码, Codex, Pi, 游标, Mastra, ACP 智能体内部智能体-原生.Add or use full agent harness runtimes like Claude Code, Codex, Pi, Cursor, Mastra, or ACP agents inside Agent-Native.#framework-internalsbuilderio/agent-nativeGit 克隆查看详情与安装步骤 → IDE 插件4,546refactorSkillsMP@phodalSuggest 重构 improvements 代码质量Suggest refactoring improvements for code quality#ide-plugins#framework-internalsphodal/auto-devGit 克隆查看详情与安装步骤 → 框架内核4,412reference-controls-enricherSkillsMP@intuitemEnrich CISO 助手框架 YAML linking assessable 需求参考控制 URNs 中心文档-pol 函数库 (CISO 助手关键参考控件). 产出 reviewable xlsx 补丁框架 YAML pEnrich a CISO Assistant framework YAML by linking each assessable requirement to reference control URNs from the central doc-pol library (CISO Assistant Key Reference Controls). Produces a reviewable xlsx and patches the framework YAML in p#framework-internalsintuitem/ciso-assistant-communityGit 克隆查看详情与安装步骤 → 框架内核4,037devtools-importsSkillsMP@ChromeDevTools约定 importing 代码 Devtools 避免构建错误. 覆盖 cross-模块导入, 内部导入, "导入 * " 需求.Conventions for importing code in Devtools to avoid build errors. Covers cross-module imports, internal imports, and the "import * as" requirement.#framework-internalschromedevtools/devtools-frontendGit 克隆查看详情与安装步骤 → 框架内核3,977code-optimizationSkillsMP@huangruiteng优化代码 performance iterative improvements (max 2 rounds). 基准测试执行时间内存占用, compare 对照 baseline implementations, 生成详细优化报告. 支持 C++, Python, Java, Rust,Optimize code performance through iterative improvements (max 2 rounds). Benchmark execution time and memory usage, compare against baseline implementations, and generate detailed optimization reports. Supports C++, Python, Java, Rust, and #framework-internalshuangruiteng/cs-notesGit 克隆查看详情与安装步骤 → 框架内核3,936second-order-odesSkillsMP@parcadei问题-solving 策略 second 订单 odes odes pdesProblem-solving strategies for second order odes in odes pdes#framework-internalsparcadei/continuous-claude-v3Git 克隆查看详情与安装步骤 → 框架内核3,936convex-optimizationSkillsMP@parcadei问题-solving 策略 convex 优化优化Problem-solving strategies for convex optimization in optimization#framework-internalsparcadei/continuous-claude-v3Git 克隆查看详情与安装步骤 → 框架内核3,936compactnessSkillsMP@parcadei问题-solving 策略 compactness topologyProblem-solving strategies for compactness in topology#framework-internalsparcadei/continuous-claude-v3Git 克隆查看详情与安装步骤 → 框架内核3,936modular-codeSkillsMP@parcadei模块化代码 OrganizationModular Code Organization#framework-internalsparcadei/continuous-claude-v3Git 克隆查看详情与安装步骤 → 框架内核3,936qlty-during-developmentSkillsMP@parcadeiQLTY 在…期间开发QLTY During Development#framework-internalsparcadei/continuous-claude-v3Git 克隆查看详情与安装步骤 → 框架内核3,913kemal-coreSkillsMP@kemalcr核心 Kemal 开发 (路由 verbs, parameters, 模块化路由, 版本 gates, 响应辅助函数).Core Kemal development (routing verbs, parameters, modular router, version gates, response helpers).#framework-internalskemalcr/kemalGit 克隆查看详情与安装步骤 → 框架内核3,835cpp-algo-styleSkillsMP@MaaEndMaaEnd cpp-algo C++ 编码风格与工程规范指南。参考 MaaFramework 的优秀实践，规范命名、头文件、公共工具、错误处理、日志、CMake 等方面。在编写、修改或审查 agent/cpp-algo/ 下的 C++ 代码时使用。#framework-internalsmaaend/maaendGit 克隆查看详情与安装步骤 → 框架内核3,830librarySkillsMP@atopileFaebryk 组件函数库结构化, `_F. py` 生成, conventions/invariants 新增新建函数库模块. 使用新增修改函数库组件, traits, 模块 definitions.How the Faebryk component library is structured, how `_F.py` is generated, and the conventions/invariants for adding new library modules. Use when adding or modifying library components, traits, or module definitions.#framework-internalsatopile/atopileGit 克隆查看详情与安装步骤 → 框架内核3,724injector-devSkillsMP@DataDog构建, 部署, 测试 Datadog 智能体组件 (智能体, 集群-智能体, 运维者, CSI driver) 本地 Kubernetes 集群使用 injector-开发 CLI. 使用用户需求 iterate 本地智能体运维者变更, spin up 本地 k8Build, deploy, and test Datadog Agent components (agent, cluster-agent, operator, CSI driver) on a local Kubernetes cluster using the injector-dev CLI. Use when the user wants to iterate on local Agent or Operator change, spin up a local k8#framework-internalsdatadog/datadog-agentGit 克隆查看详情与安装步骤 → 框架内核3,709deep-learning-papers-guideSkillsMP@brycewang-stanfordAnnotated 深度学习论文 implementations 代码 walkthroughsAnnotated deep learning paper implementations with code walkthroughs#framework-internalsbrycewang-stanford/auto-empirical-research-skillsGit 克隆查看详情与安装步骤 → 框架内核3,709pytorch-guideSkillsMP@brycewang-stanford避免通用 PyTorch mistakes 应用健壮训练模式Avoid common PyTorch mistakes and apply robust training patterns#framework-internalsbrycewang-stanford/auto-empirical-research-skillsGit 克隆查看详情与安装步骤 → 框架内核3,709pytorch-lightning-guideSkillsMP@brycewang-stanfordPyTorch Lightning 框架可扩展模型训练研究PyTorch Lightning framework for scalable model training and research#framework-internalsbrycewang-stanford/auto-empirical-research-skillsGit 克隆查看详情与安装步骤 → 框架内核3,709tensorflow-guideSkillsMP@brycewang-stanfordTensorFlow 最佳实践 tf. 函数, GPU 记忆, 部署TensorFlow best practices for tf.function, GPU memory, and deployment#framework-internalsbrycewang-stanford/auto-empirical-research-skillsGit 克隆查看详情与安装步骤 → 框架内核3,709r-oopSkillsMP@brycewang-stanfordR 对象-oriented programming 指南 S7, S3, S4, vctrs. 使用设计 R 类选择 OOP 系统.R object-oriented programming guide for S7, S3, S4, and vctrs. Use when designing R classes or choosing an OOP system.#framework-internalsbrycewang-stanford/auto-empirical-research-skillsGit 克隆查看详情与安装步骤 → 框架内核3,678annotate-pybind-adaptersSkillsMP@borglabDiagnose 生成 pybind 编译失败 caused 封装接口定义签名 differ C++ declarations, 应用 wrap `@pybind_lambda` 注解 affected 方法, 静态方法, 全局函数Diagnose generated pybind compilation failures caused by wrapper interface signatures that differ from their C++ declarations, then apply the wrap `@pybind_lambda` annotation to only the affected methods, static methods, or global functions#framework-internalsborglab/gtsamGit 克隆查看详情与安装步骤 → 框架内核3,675k8s-model-updateSkillsMP@fabric8io更新 Fabric8 Kubernetes 客户端模型 DSL 新建 Kubernetes 版本 released. 处理 downloading OpenAPI 规格说明, regenerating Java 模型, 分析 API 变更 (新建 GA 资源, graduations, deprecations, removals), updatUpdates Fabric8 Kubernetes Client models and DSL when a new Kubernetes version is released. Handles downloading the OpenAPI spec, regenerating Java models, analyzing API changes (new GA resources, graduations, deprecations, removals), updat#framework-internalsfabric8io/kubernetes-clientGit 克隆查看详情与安装步骤 →