菜单
Batch convert a directory of slides and PDFs into Markdown. Supports ppt/pptx/pps/ppsx/odp to pdf+md, and text-based pdf to md (no OCR).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
OpenHarmony (鸿蒙) 服务层/框架层代码仓库架构与命名规范领域知识。 适用于识别、导航、分析和创建符合 OpenHarmony 分层架构标准的代码仓库。 当用户需要以下任一场景时使用此 Skill： (1) 分析 OpenHarmony 服务层或框架层代码仓库的目录结构与命名约定， (2) 判断一个仓库是否符合 OpenHarmony foundation 分层架构规范（subsystem/component 路径模式）， (3) 理解 bundle.json 组件描述符与 GN 构建系统的路径映射关系， (4) 在 OpenHarmony 项目内新增组件、服务或接口时遵循正确的命名格式, (5) 理解 frameworks/ vs services/ vs interfaces/ vs common/ 的分层职责边界。
Convert a macOS Electron app (from .dmg) into a runnable Linux Electron app. Use when the user needs to port a macOS-only Electron desktop application to Linux, build a .deb/.rpm package from a macOS DMG, patch app.asar for Linux window behavior, or fix startup crashes after such conversion (e.g., missing chunks, t.join errors, transparent background flickering, deb dependency issues).
Reverse engineer and deobfuscate bundled JavaScript/Electron applications. Extracts DMG/AppImage/pkg archives, unpacks app.asar, deobfuscates webpack/Vite/browserify bundles with scope-aware Babel-based variable renaming, and outputs readable source code. Use when the user wants to reverse engineer, deobfuscate, unminify, or analyze a bundled JS application (Electron, web app, Node.js), extract readable source from minified bundles, unpack app.asar, or understand how a third-party JS app works internally.
Up-to-date Zig programming language patterns for version 0.16.0. Use when writing, reviewing, or debugging Zig code, working with build.zig and build.zig.zon files, or using comptime metaprogramming. Critical for avoiding outdated patterns from training data - especially build system APIs (root_module instead of root_source_file), I/O APIs (buffered writer pattern), container initialization (.empty/.init), allocator selection (DebugAllocator), and removed language features (@Type, @cImport, async/await, usingnamespace).
Fix WSL git proxy connection errors (Failed to connect to 127.0.0.1 port 7890)
CS 课程系统性学习 Skill。融合横纵分析法与结构化写作质检体系，用于深度学习一门计算机科学课程（含 lecture notes、syllabus、paper list），最终输出一份结构完整、有个人洞察的学习报告。 触发词包括但不限于：学习这门课、帮我梳理一下这个课程、研究一下这门 CS 课程、输出学习报告、课程分析、lecture notes 整理、帮我搞懂这门课。 适用于用户丢来一个课程主页（如 https://cs.brown.edu/courses/csci1650/）说"帮我学习一下"或"帮我写个学习报告"的场景。 不要用于简单名词解释（如"什么是 OS"），也不要用于写公众号文章。
| name | x2md-skill |
| description | Batch convert a directory of slides and PDFs into Markdown. Supports ppt/pptx/pps/ppsx/odp to pdf+md, and text-based pdf to md (no OCR). |
Use this skill when the user wants batch conversion to Markdown from common document formats.
soffice --headless).ppt, .pptx, .pps, .ppsx, .odp, .pdfpython-pptx (pip install python-pptx)pypdf (pip install pypdf)soffice in PATH)python3 /home/ares/yysnotes/x2md-skill/scripts/convert_x2md.py \
/path/to/input \
--output-dir /path/to/out \
--recursive
OUTPUT/pdf/**/*.pdfOUTPUT/md/**/*.md.ppt, the script first converts to .pptx (temp file) so Markdown can be extracted..pdf, this skill only extracts embedded text. Scanned/image PDFs are skipped (OCR not included).