didi-skills

Use when user asks for a hand-drawn style report, notebook-style report, or says "手绘板报告", "手绘风", "笔记本风格". Generates warm paper-textured HTML reports with handwriting fonts, sketchy borders, and notebook aesthetics. Also exports PNG via Playwright.

Use when user provides a job description (JD) and wants to customize their resume for a specific job application, or when user says "tailor resume", "定制简历", "修改简历", "投简历"

Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.

Use when user has a messy Word document or plain text that needs professional formatting, auto-layout, and intelligent image generation. Triggers on requests to format, beautify, or reorganize documents.

Use when user has a Word document that needs typo correction, text polishing, or proofreading. Triggers on requests to fix typos, correct errors, polish writing, proofread, or when user says "校对", "纠错", "润色", "改错别字", "检查错别字".

Use when user provides a 口播稿 (spoken script) and wants it converted into an HTML slide presentation with hand-drawn SVG illustrations for screen recording. Trigger on "做板书", "口播稿转板书", "/board", "生成板书", "做背景板", or when user pastes a script and wants visual slides for video recording.

生成苹果简约风格的竞品分析 HTML 报告，含 Chart.js 数据可视化。使用波特五力、蓝海策略、竞争定位地图等分析框架。适用于竞品分析、市场定位、竞争优势评估。

Calculate TAM/SAM/SOM for market opportunities using top-down, bottom-up, and value theory methodologies. Use this skill when sizing markets, estimating addressable revenue, validating market opportunity for a new venture, or building investor-ready market analysis for a startup pitch or business plan.

论文剥洋葱 — 逐层深入的论文阅读技能。将一篇学术论文拆解为四层渐进式阅读，最终生成一张手绘风格的思维导图笔记卡片（React artifact）。 当用户上传论文PDF、粘贴论文内容、给出论文链接，或说出以下任何意图时，使用此技能： - "帮我读这篇论文" / "分析这篇paper" - "论文笔记" / "论文总结" / "读论文" - "剥洋葱" / "逐层分析" - 上传了 .pdf 文件且内容看起来是学术论文 此技能与一次性输出报告的方式不同——它模拟真实的深度阅读过程，分四层逐步深入，每层都有明确的阅读任务和产出，最终浓缩为一张可保存的笔记卡。