1873 个 · 按相关度排序
Battle-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, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
中文简介正在准备中。当前显示原文说明。
Use when seeing WebSocket errors like "Invalid frame header", "RSV1 must be clear", or "WS_ERR_UNEXPECTED_RSV_1" - covers multiple WebSocketServer conflicts, compression issues, and raw frame debugging techniques
中文简介正在准备中。当前显示原文说明。
Plan, implement, or review systematic debugging work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests systematic debugging work.
中文简介正在准备中。当前显示原文说明。
Testing and debugging for Zephyr RTOS. Covers the Ztest framework for unit and integration tests, the Twister test runner for automated HIL/SIM validation, and advanced tracing/debugging techniques (SystemView, Thread Analyzer, Stack analysis). Trigger when writing unit tests, setting up CI/CD pipelines, or analyzing system performance and latency.
中文简介正在准备中。当前显示原文说明。
Use when running GDB: breakpoints, watchpoints, segfault or hang debugging, reverse debugging, remote gdbserver, core dumps, pretty-printers, Python scripting, or multi-threaded debugging.
中文简介正在准备中。当前显示原文说明。
This skill provides expert-level guidance for debugging and fixing bugs in VS Code extensions. Use when investigating runtime errors, fixing memory leaks, resolving WebView issues, debugging activation problems, fixing TypeScript type errors, or troubleshooting extension communication failures. Covers systematic debugging workflows, common bug patterns, root cause analysis, and prevention strategies.
中文简介正在准备中。当前显示原文说明。
Systematic 4-phase debugging framework for Unity projects with GameDebug wrapper generation. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Triggers on requests like "this doesn't work", "there's a bug", "it crashes when", "fix this error", "why is this happening", "null reference exception", "test is failing", "unexpected behavior", "something broke", or any debugging task. Four-phase framework (gather evidence, isolate, hypothesize, fix) that ensures understanding before attempting solutions.
中文简介正在准备中。当前显示原文说明。
4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.
中文简介正在准备中。当前显示原文说明。
Time-travel debugging for DAG executions. Inspect agent state at any node, replay decisions with modified inputs, compare execution traces side-by-side, and identify where reasoning diverged. Inspired by LangGraph Studio's state-editing model and Temporal's event history. Activate on "debug DAG", "replay execution", "time travel debug", "inspect node state", "what went wrong at step", "compare runs", "execution diff". NOT for live monitoring (use dag-runtime + websocket-streaming), failure analysis (use dag-ops), or general code debugging.
中文简介正在准备中。当前显示原文说明。
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.
中文简介正在准备中。当前显示原文说明。
Systematic debugging: production-level reproduce, isolate, instrument, verify. Use when implementing, reviewing or testing systematic debugging for React, Vite, Next.js or Perfect_AI projects.
中文简介正在准备中。当前显示原文说明。
Apply systematic root cause analysis and debugging methodologies to diagnose and fix bugs, test failures, and unexpected behavior. Use when encountering production issues, investigating test failures, diagnosing performance problems, tracing error sources through call stacks, analyzing logs and stack traces, reproducing inconsistent bugs, debugging race conditions, investigating memory leaks, or applying scientific method to problem-solving before proposing fixes.
中文简介正在准备中。当前显示原文说明。
4-phase root cause debugging: understand bugs before fixing.
中文简介正在准备中。当前显示原文说明。
[Extended thinking: This workflow implements a sophisticated debugging and resolution pipeline that leverages AI-assisted debugging tools and observability platforms to systematically diagnose and resolve production issues. The intelligent debugging strategy combines automated root cause analysis with human expertise, using modern 2024/2025 practices including AI code assistants (GitHub Copilot, Claude Code), observability platforms (Sentry, DataDog, OpenTelemetry), git bisect automation for ...
中文简介正在准备中。当前显示原文说明。
Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability. Masters log analysis, distributed tracing, Kubernetes debugging, performance optimization, and root cause analysis. Handles production outages, system reliability, and preventive monitoring. Use PROACTIVELY for debugging, incident response, or system troubleshooting.
中文简介正在准备中。当前显示原文说明。
You are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools. Configure debugging workflows, implement tracing solutions, and establish troubleshooting practices for development and production environments.
中文简介正在准备中。当前显示原文说明。
通过复现步骤、日志和近期更改，调查缺陷、测试失败及异常行为的原因。按证据推进假设验证、修复和修复后的测试，逐步确认问题根源。
用于检查Next.js 16及更高版本中开发启动和代码更新缓慢的问题，确认Turbopack与webpack的选择，并核对缓存及proxy.ts命名。
帮助构建和维护MCP服务器，让AI助手调用外部操作、读取数据并使用指令模板，涵盖Node/TypeScript功能注册、输入验证、本地与远程通信选择及故障排查。
协助编写和审查Kubernetes配置文件并排查故障，提供健康检查、权限控制、资源限制及自动伸缩的配置示例和调查命令，用于检查重启、内存不足和部署问题。
用于 Nuxt 4 应用开发、审查和性能改善，防止服务端与浏览器显示不一致，并整理数据获取、各页面的渲染与缓存规则及延迟加载方式。
使用 Kotlin Coroutines 和 Flow 实现 Android 与 Kotlin Multiplatform 的异步任务和数据更新，涵盖并行加载、界面状态、取消、错误处理及测试。
在AI代理反复失败或重复操作时，记录错误与环境前提、排查原因，采取影响有限的恢复操作，并汇总结果和证据，为有依据的重试与交接提供支持。
根据错误信息和执行环境，分析AI代理反复失败或重复操作的原因。通过小范围、可撤销的恢复操作检验假设，并将结果与依据整理成可供交接的报告。