Document Processing AI Skills

Generate Chinese official document (公文) Word files from controlled Markdown or JSON. Use when producing or updating .docx 公文 that must follow fixed fonts, line spacing, title/recipient layout,…

将内容转化为金蝶官方风格的完整幻灯片文件（.pptx 或 .html）。当用户说「做PPT」「做个PPT」「做汇报材料」「做演示文稿」「生成deck」「生成幻灯片」「整理成幻灯片」「按金蝶模板整理」「make a presentation」「create a slide deck」「output slides」「HTML幻灯片」「交互式演示」「网页版PPT」「web slides」，或上传…

Improve decision quality by clarifying the real problem, exposing hidden assumptions, reasoning from fundamental facts, reducing unnecessary complexity, and ending with a cleaner recommendation or…

Use when an AI coding beginner needs ArchPilot, an LLM-executable architecture designer for small AI text/file analysis web apps, including step-by-step Chinese-guided requirement translation, MVP…

面向 18～55 岁、无重大疾病的健身新手与普通进阶者，提供安全、自然、可持续的训练计划、今日训练辅助、动作替代、饮食与恢复支持、训练复盘和长期训练DNA。用户提到开始健身、训练计划、今日训练、减脂、增肌、力量、有氧、居家跟练、健身房、训练复盘、训记、训练DNA、训练分享或一般运动不适时使用；不用于普通医学问诊、疾病专项康复、竞技备赛、PED/药物指导或极端减重。

将图片、PDF、图片版 PPTX 或含原生对象的混合 PPTX 转换为严格质量校验、分层可编辑的 PowerPoint；保留既有原生文字、形状、表格和图表，并使用宿主视觉 Agent 完成组件决策。用于截图、设计稿、科研图和幻灯片页面的组件重建、残影检查与可编辑输出。

拒绝人工手搓👋分析数据，使用AI+量化+大数据，诊断已有的小红书笔记📕；也可按创作主题进行灵感索引，寻找优秀笔记、归纳主题与切入点。生成内容分析报告、优化建议，给出评分以及同类型爆款笔记🎯。

Translate academic papers from arXiv to Chinese. Use when users want to (1) translate arXiv papers from English to Chinese, or (2) create technical reports summarizing academic papers. Works with…

任意长度文本翻译、审校或精编流程。PDF、EPUB 等本地材料会先规范化为 Markdown 文件，再开始翻译。当用户表现出翻译或审校精编现有译稿的意图时触发，例如提及“翻译”、“优化／审校／润色 / 精编译文”、“改成中文／英文”等。

Generate a self-contained HTML changelog report showing recent documentation changes with interactive course generation buttons. Use this skill when the user asks for a docs changelog, documentation…

润色中文计算机科学博士学位论文，去除 AI 痕迹、检查论文规范、生成 MD 审阅报告。 支持读取 PDF/DOCX/LaTeX 长文档，输出逐章详细修改意见的 MD 审阅报告文件。 凡用户粘贴论文段落、章节、摘要，或提到"论文"、"学位论文"、"博士论文"、 "毕业论文"、"润色"、"修改"、"审阅"等词，即应激活本 skill， 即使用户没有明确说"润色论文"。

Find the latest LinkedIn job openings that match a person's CV or LinkedIn profile, filtered by how recently they were posted, and deliver them as a ranked list where every job has a direct apply…

Create Chinese-, English-, or bilingual final-exam review packs and source-grounded mock exams from PDF/PPTX lecture decks, including mixed-language slides, Revision/Review decks, syllabi,…

Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare…

Analyze datasets with preserved raw inputs, explicit cleaning decisions, reproducible figures and PDF reports. Full statistics for one tabular file; descriptive time-series analysis; integrity…

Write tailored tech resumes and cover letters aimed at engineering hiring managers, built to parse cleanly in ATS and AI screeners (Greenhouse, Lever, Ashby, Workday) and to read as written by a…

Use when the user needs to plan, draft, or refine a CVPR 2026 poster under the official CVPR 2026 size, layout, and printing constraints, including adapting the official template, turning a paper into…

Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the…

World-class practice research. This skill should be used when the user asks what the best in the world does about a specific problem, technique, or situation — covering product, engineering, design,…

Job search copilot that scores a posting for fit, tailors the user's .docx CV according to best practices, logs applications in a tracker (Notion or local CSV), syncs statuses from Gmail, reports…

Use for any cap-table number, mechanic, or date before a founder signs, from a single SAFE, note or warrant described in chat or a quick 'is this dilution reasonable?' check to any draft or signed…

Export ALL reports of a HackenProof program into a structured file. User chooses report detail level (Full, No Comments, or Public) and output format (Markdown, JSON, or CSV). Trigger on "export all…

Use when the user asks to write, draft, optimize, review, package, or generate Chinese invention patent materials, Chinese patents, invention patents, patent specifications, claims, abstracts,…

从 B 站教育/讲课视频生成带截图的 DOCX 学习笔记。下载视频+字幕→全覆盖抽帧→OCR去重→AI视觉打分→提取图中内容→融合生成DOCX。

Use this skill when an AI agent needs to create, edit, render, verify, improve, batch-generate, or stockpile TikZ/PGF diagrams or animations for LaTeX papers, Beamer slides, teaching material,…

AI-driven HTML presentation generation system. Converts source documents (PDF/DOCX/URL/Markdown) into browser-ready HTML slide decks and exports them to SVG, PNG, and native PPTX through multi-role…

Use when creating a technical resume, polishing an existing resume, or preparing for technical interviews

9-command agent skill suite for Tongji Look (look.tongji.edu.cn): setup, list, transcribe, take notes, manage materials, build course wiki, create cheat sheets, batch-process entire courses, and…

Translate an academic paper PDF into Chinese (or another language) as a new PDF whose pages correspond 1:1 to the original, with figures/tables cropped as vectors from the original.

使用 python-docx 精确读取、分析、修改 Word 文档（.docx）格式。当用户需要分析文档格式、批量修改格式、统一排版规范、处理中英文混排字体、修改交叉引用样式时使用此 skill。

拆解参考图并把视觉手法迁移到用户产品；或从产品图/基础资料出发，检索可核验信息，策划详情页并输出逐屏生产级豆包生图执行稿。详情页只有产品图/零散身份规格且无完整合格卖点集时，先交付调研卖点大纲并经用户确认。适用于参考反推、主图套系、整套详情页和稀疏资料补全。不用于纯文案、普通修图或翻译。

Use when the user asks for slides, a slide deck, or a presentation about a code repository, one of its subsystems, a feature, an architecture area, or its recent changes. Triggers include "make…

根据用户描述生成高质量绘图 prompt，并按通用、roadmap、schematic 模式通过 BenszAPI 直接完成 gpt-image-2.5-flare、gpt-image-2.5-sunburst、gpt-image-2 或 Nano Banana/Gemini 出图、编辑和多轮迭代；这是自包含的图片生成工作流，选中后不得调用或依赖 imagegen，除非用户明确要求同时使用…

让知识工作项目对 Agent 自描述、跨 session 可接续，并治理项目里的规则与工作纪律。 两类场景使用：（一）项目组织——新建或初始化项目、整理或健康检查项目结构、 设计目录与导航、写 frontmatter/index/log/决策记录、把探索期的临时文件沉淀下来、 恢复一个还没有规则文件的项目的上下文；（二）工作方法论——同类问题反复出现要固化成规则、…

Interactive learning tutor with spaced repetition, research helpers, and restart-safe study workspaces. Use when the user wants to learn something new: teach me, I want to study, help me learn, study…

End-to-end stateful workflow for designing and generating editable PowerPoint decks from briefs, templates, reference decks, brand assets, data, ImageGen comps, or user-supplied slide images. Uses…

AI Builder for Power Platform. Use when: document processing, prediction models, GPT prompt actions in flows, prebuilt models (text recognition, sentiment, entity extraction), custom models, AI…

Emitir facturas electrónicas de Argentina (AFIP/ARCA) para monotributistas — Factura C con CAE, PDF con QR según RG 4291/2018, vía web services WSAA/WSFE. Usar este skill cuando el usuario quiera…

用 reveal.js 製作或修改 HTML 簡報（單檔、可離線、深色專業版型、真實截圖、QR、互動頁、觀眾手機即時投票），逐頁截圖 QA 並驗證 QR，再輸出講義 PPTX／PDF 或原生可編輯 PPTX。當使用者說「做一份 HTML 簡報」「reveal.js 簡報」「簡報加底圖／截圖／QR」「簡報加互動／現場投票／觀眾用手機作答」「HTML 簡報轉…

Convert slide/page images into editable PowerPoint PPTX decks by using Image Split visual layers, region schemas, transparent editable text, and QA gates. Use when Codex is given…

Use when creating, improving, converting, or redesigning design-system-driven PPT, PowerPoint, PPTX, slides, decks, webpage PPT, HTML-first presentations, pitch decks, reports, defense decks,…

Design and generate polished, on-brand presentation decks as clean 1920×1080 HTML — with real charts, tables, and AI or stock imagery. Use whenever someone wants to create, design, or improve a…

WCAG 2.2 AA enforcement as a package of Agent Skills: router skills for web UI, full-site audits, Office/PDF/ePub documents, markdown, desktop and Python tooling, and GitHub workflows dispatch…

Generate editable learning PPTX decks by first creating HTML slides, or convert local HTML slide decks and single-page HTML presentations into editable PPTX files by rendering in a browser, reading…

Turn existing spatial or coordinate data into portable, browser-openable interactive map files and report-ready figures. Use when the user wants parcels, buildings, facilities, parking, roads, water,…

Rebuild two to nine raster slide pages concurrently with V2.1 fidelity and editability gates, isolated page agents, shared preflight, temporary QA bundles and ordered merging. Deliver only one merged…

Use when generating consulting-grade slide decks, MBB-style presentations, McKinsey/Bain/BCG-format slides, board prereads, executive readouts, recommendation decks, market entry decks, due diligence…

Create or edit information-dense, componentized, and fully editable Japanese corporate PowerPoint decks (.pptx) and one-page ポンチ絵 in the style of Japanese manufacturers, industry associations,…

生成或还原咨询风格（麦肯锡/BCG式）的高密度、全可编辑 PowerPoint。只要用户提到制作 PPT、幻灯片、slides、deck、汇报材料、路演材料、提案，或要求把文档/研报/数据/旧PPT/截图转成演示文稿，或提到"咨询风格""行动性标题""SCR""还原成可编辑PPT"，都必须使用本…

Turn one sentence or a Markdown document into a complete, presentation-ready deck: a standalone HTML web slideshow plus an editable PPTX export, with 5 built-in visual themes (Swiss Pulse / Velvet…

Create polished competition, product, and technical PPTs through a content-to-template workflow: analyze supplied documents and user goals, lock deck style tokens and image asset roles, map each…