搜索「Debugging」的结果

io.github.DigitalDefiance/ts-mcp-debugger

面向 Node.js/TypeScript 的企业级调试，25 个以上工具：断点、性能分析、卡死检测。

Web 应用测试

io.github.anthropics/skills/webapp-testing

使用 Playwright 与本地 Web 应用交互并测试的工具包。支持验证前端功能、调试 UI 行为、捕获浏览器截图和查看浏览器日志。

claude-api

io.github.anthropics/skills/claude-api

Claude API / Anthropic SDK 参考——模型 id、定价、参数、流式输出、工具调用、MCP、agent、缓存、token 计数、模型迁移。TRIGGER——在打开目标文件前先阅读本参考，不要因为“看起来只是一行代码”而跳过，凡是：提示中出现 Claude/Anthropic 的任何形式（Claude、Anthropic、Fable、Opus、Sonnet、Haiku、anthropic、@anthropic-ai、claude-*、us.anthropic.*、[1m]）；用户询问 LLM 相关问题（定价/选型/限制/缓存）——不要凭记忆作答；或任务呈 LLM 形态但未指明提供方（agent/MCP/工具定义/多智能体/RAG/LLM 评审/computer-use；对自然语言做生成/摘要/抽取/分类/改写/对话；调试拒答/截断/流式/工具调用/token）。仅当处理的是其他提供方时可 SKIP（覆盖所有触发条件）：查询中点名 OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama；或对项目执行 grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama' 命中（先跑这条 grep

io.github.ossrs/srs/internal-codemap-for-srs

把 SRS 与 Oryx 的代码任务路由到最小相关的可信代码库地图与验证指引。只要支持、开发、调试、评审或维护工作需要定位、选择、阅读、修改、测试或验证 SRS/Oryx 代码时使用。覆盖第一代 C++ 源站与边缘媒体服务器及其 State Threads 依赖、下一代 Go 服务器、浏览器推流与播放、SRS Docker 镜像工具链、SRS 测试，以及 Oryx 的 Go 后端、React 控制台、一体化运行时、打包、安装器、发布与测试。作为父级支持与发展技能的代码导航依赖；面向用户的工作流程与结果仍由父技能负责。

io.github.supabase/supabase/studio-mock-api-tests

用 MSW 在网络层 mock API 请求来编写 Supabase Studio 组件测试。在编写或评审涉及 React Query hook 或 mutation 的组件测试，或把现有测试从 vi.mock('@/data/...') 迁移走时使用。涵盖 customRender + addAPIMock 模板，以及耗费大量调试时间的 jsdom/MSW 陷阱。

io.github.deepseek-ai/deepseek-harness/cordis-plugin-development

Use when designing, reviewing, adding, enabling, disabling, installing, configuring, or debugging a plugin, bundle, feature, page, panel, tool, or MCP connection in the current Harness profile, including a shipped plugin that is disabled by default, and for any visual object, decoration, or widget request that names no other destination, which means an installed UI plugin rendered in the Harness Web UI.

io.github.skypilot-org/skypilot/skypilot

在启动云端 VM、Kubernetes pod 或 Slurm 作业以承载 GPU/TPU/CPU 负载、在云端 GPU 上训练或微调模型、部署带自动扩缩的推理服务（vllm、TGI 等）、编写或调试 SkyPilot 任务 YAML、用 spot/抢占式实例节省成本、跨云比较 GPU 价格、统一管理 25+ 云服务以及 Kubernetes、Slurm 与本地集群并在其间故障切换、排查资源可用性或 SkyPilot 错误、优化成本与 GPU 可用性，或迁移既有 Slurm 工作负载（把 sbatch 脚本、salloc 会话、job array 或 srun 调用转换为 SkyPilot 任务 YAML，并把 Slurm 命令、指令与 SLURM_* 环境变量映射到对应的 SkyPilot 写法）时使用。

io.github.streamlit/streamlit/developing-with-streamlit

**[必备]** 适用于所有 Streamlit 任务：创建、编辑、调试、美化、样式、主题或优化 Streamlit 应用。构建自定义组件（内联或打包）、使用 st.components.v2 或任何 HTML/JS/CSS 组件工作时同样必需。触发词：streamlit、st.、dashboard、app.py、beautify、style、CSS、color、background、theme、button、widget styling、custom component、st.components、packaged component、pyproject.toml、asset_dir、CCv2、HTML/JS component。

io.github.ruvnet/ruflo/pair-programming

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.

io.github.ruvnet/ruflo/pair-programming

AI 辅助结对编程，提供多模式（driver/navigator/switch）、实时校验、质量监控与完善测试，支持 TDD、调试、重构与学习式会话。具备自动角色切换、持续代码评审、安全扫描与性能优化，并以 truth-score 校验。

io.github.microsoft/vscode/project-setup-info-local

帮助用户在 VS Code 工作区中创建完整项目结构的全面设置步骤；本工具面向整体项目的初始化与脚手架搭建，而非创建单个文件。适用：用户要从零创建完整新项目；搭建整个项目框架（TypeScript 项目、React 应用、Node.js 服务等）；初始化具备完整结构的 Model Context Protocol（MCP）服务器；按规范脚手架创建 VS Code 扩展；设置 Next.js、Vite 或其他框架项目；用户要求新项目、创建工作区或设置某框架项目；需要建立含依赖、配置文件与目录结构的完整开发环境。不适用：创建单个文件或少量代码片段；向已有项目添加单个文件；修改既有代码库；用户要求创建一个文件或添加一个组件；简单代码示例或演示；调试。

io.github.garrytan/gstack/gstack

Install and use gstack in Capy and Claude Code. Load at session start to check this machine, and for gstack planning, code review, debugging, QA, design, security, documentation, and shipping workflows.

io.github.upstash/context7/context7-mcp

通过 Context7 MCP 服务器获取最新的按版本区分的库文档和代码示例。用户询问任何库、框架、SDK、API、CLI 工具或云服务(含 API 语法、配置、安装说明、版本迁移、CLI 用法、库特定调试)时使用;调用第三方库生成代码时使用;用户指明版本(如 Next.js 15、React 19)时使用。React、Vue、Next.js、Prisma、Supabase、Express、Tailwind、Django、Spring Boot 等知名库同样适用,因为训练数据可能未反映最新变化。库文档优先于网络搜索。不用于:重构、从零编写脚本、业务逻辑调试、代码审查、通用编程概念,或用户已提供相关文档时。

io.github.anomalyco/opencode/app-e2e-tests

Use when writing, changing, reviewing, or debugging Playwright e2e tests in packages/app/e2e (regression keepers and user stories). Covers the mocked opencode server harness and the Bun static server, per-test isolation, page-load and route cost, the suite-wide service-worker block, races with first mount, hover, measurement, clock, dialogs and shortcuts, projects, shards and worker scheduling, rehearsing Windows timing locally, and diagnosing a CI flake from its artifacts. Not for Storybook component tests or e2e/performance benchmarks.

io.github.anomalyco/opencode/component-tests

Use when writing, changing, debugging, or reviewing Storybook-based Playwright component tests. That covers specs in packages/app/component-tests or packages/session-ui/component-tests, `*.fixture.tsx` files there or beside source (such as packages/gui-extensions/src/browser/panel.fixture.tsx), the stories they mount, and the shared harness in packages/storybook (playwright/config.ts, playwright/story.ts, .storybook/main.ts, preview.tsx, mocks). Also use when a component test is flaky, passed on retry, or fails with "Execution context was destroyed", "Failed to fetch dynamically imported module", or `#storybook-root` hidden. Covers mount args, source modules imported by URL, Vite dependency pre-bundling and reloads, cold vs warm Storybook, mobile drawers, geometry, and checks before pushing.

io.github.volcengine/OpenViking/openviking-context-database

Use OpenViking from OpenClaw through @openviking/openclaw-plugin: long-term memory, session archives, resource and Agent Skill import, semantic recall, recall trace debugging, and externalized tool-result recovery. Prefer this skill when the user wants to use, query, debug, or operate OpenViking context from an OpenClaw agent. For first-time plugin installation, use the install-openviking-memory skill instead.

io.github.upstash/context7/find-docs

为任意开发者技术检索最新文档、API 参考和代码示例。只要用户询问特定库、框架、SDK、CLI 工具或云服务——包括 React、Next.js、Prisma、Express、Tailwind、Django、Spring Boot 等知名库——就使用本技能,因为训练数据可能未反映最近的 API 变更或版本更新。以下情况务必使用:API 语法问题、配置项、版本迁移问题、提到库名的 "how do I" 问题、涉及库特定行为的调试、安装说明,以及 CLI 工具用法。即使认为已知答案也应使用——不要依赖训练数据中的 API 细节、签名或配置项,务必对照当前文档核实;库文档与 API 细节优先于网络搜索。

io.github.affaan-m/ECC/deepseek-harness-setup

Install and operate Everything Claude Code (ECC) on the DeepSeek Harness (DSH): native skill roots (~/.dsh/skills, .agents/skills), the @deepseek-ai/dsh-hooks-claude-code bridge for command hooks, bare-insert patch mounting, generator usage, event-support limits, and update workflow. Use when setting up ECC on DeepSeek Harness, wiring ECC hooks into a DSH profile, or debugging why ECC skills or hooks do not appear in a DSH session.

io.github.anthropics/skills/claude-api

Claude API / Anthropic SDK 参考——模型 id、定价、参数、流式输出、工具调用、MCP、agent、缓存、token 计数、模型迁移。触发条件：提示中出现任何 Claude/Anthropic 相关名称（Claude、Anthropic、Fable、Opus、Sonnet、Haiku 等）；用户询问 LLM 相关问题（定价/选型/限额/缓存）时不要凭记忆回答；或任务属于 LLM 类且未指明供应商。仅当明确针对其他供应商（OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama）时跳过。

io.github.streamlit/streamlit/developing-with-streamlit

适用于所有 Streamlit 任务：创建、编辑、调试、美化、样式、主题、优化或部署 Streamlit 应用；也包括自定义组件、st.components.v2 以及 HTML/JS/CSS 工作。会从用户安装的 Streamlit（>=1.57）发现并加载版本匹配的参考文档。触发词：streamlit、st.、dashboard、app.py、beautify、style、CSS、color、background、theme、button、widget styling、custom component、st.components、CCv2、session state、performance、cache、fragment、slow rerun、deploy。

io.github.stas00/ml-engineering/ml-engineering

Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/st

io.github.microsoft/vscode/customizations-in-the-agent-host

agent host 中定制启用（插件、MCP 服务器、agents、技能）的架构与来之不易的调试经验。适用于：改动定制的发现、发布、启用/禁用或传递给提供方 SDK 的方式；界面上定制显示的错误启用状态；被禁用的 MCP 服务器或插件仍然到达模型的情形。

io.github.pytorch/pytorch/pt2-bug-basher

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

io.github.pytorch/pytorch/pt2-bug-basher

调试 PyTorch 2 编译器栈故障，包括 Dynamo 图断裂、Inductor 代码生成错误、AOTAutograd 崩溃与精度不一致。在遇到 torch.compile 错误、BackendCompilerFailed 异常、重编译问题、Triton kernel 失败、FX 图问题，或用户提到调试 PT2、Dynamo、Inductor 或编译模型问题时使用。