Use when analyzing source code repositories for 源码理解, 源码可视化, code asset maps, interface visualization, architecture companion pages, API/boundary diagrams, runtime case overlays, resource lifecycle views, or complex module deep dives across AI infra, compilers, databases, backend systems, SDKs, libraries, and frameworks.
Use when removing AI writing patterns, humanizing text, making prose sound natural, fixing robotic writing, or handling prompts such as anti-ai, humanize, AI-generated traces, 去除 AI 写作痕迹, 人性化处理, 让文字更自然, or 机器味. Supports English and Chinese prose.
Use when Codex needs to inspect, configure, debug, build, or explain Microsoft Visual Studio projects, solutions, CMake workspaces, IDE settings, project properties, build errors, debugger state, EnvDTE/DTE automation, toolchain issues, or Visual Studio GUI-only behavior, especially when deciding between shell/CLI, EnvDTE, and Computer Use control.
Use when planning a sourced, budget-constrained trip in mainland China, including attractions, train or flight comparisons, hotel alternatives, local transportation, route maps, and itinerary HTML.
Use when creating, modifying, refactoring, or reviewing Python code and when checking imports, type annotations, docstrings, error handling, state management, prompts, or structured LLM outputs.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.