Chris-debug-0225

Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration

Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.

Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.

Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.

将零散的纯文本记录整理成日程、代办、提醒和复盘输出，适合接到 QClaw 或飞书等外部 MCP 进行消息触达。

Turn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non-technical people, then elevate the presentation with Vue Bits-inspired front-end effects and components. Use this skill whenever someone wants to create an interactive course, tutorial, or educational walkthrough from a codebase or project with a stronger visual layer. Also trigger when users mention 'turn this into a course,' 'explain this codebase interactively,' 'teach this code,' 'interactive tutorial from code,' 'codebase walkthrough,' 'learn from this codebase,' 'make a course from this project,' or ask for a richer front-end presentation. This skill produces a stunning, self-contained HTML file with scroll-based navigation, animated visualizations, embedded quizzes, code-with-plain-English side-by-side translations, and premium UI flourishes inspired by Vue Bits.

当用户想分析、应对、反制、摆脱现实生活中各种“傻逼”“烂人”“难缠的人”“不讲理的人”“恶心的人”“低素质的人”“爱甩锅的人”“爱挑衅的人”“爱控制的人”时，使用这个 skill。适用于职场冲突、人际边界、家庭亲戚、伴侣关系、同事合作、领导压迫、线上对喷、被羞辱、被甩锅、被道德绑架、被操控、被 gaslight、被占便宜等场景。这个 skill 要把情绪化抱怨翻译成可执行判断：先识别对方是哪一类问题人物、当前风险级别和权力关系，再给出真正能落地的应对策略、话术、边界和退出方案。除了普通文字回复外，这个 skill 还应在用户需要时生成可直接打开的单页 HTML 结果页，支持“文字回复版”“HTML版”或“两版同时产出”。目标不是讲大道理，而是让用户产生“啊，说得对，这人就是这么回事，而且这办法真能用”的感觉。