Explorar skills

Distill a film's essence into a single elegant Chinese-style HTML page that reveals the film's inner workings through specific visual, sonic, and performative detail — and through five distinct critical voices in dialogue (form / politic / lyric / craft / intertext). Use this skill whenever the user mentions distilling, analyzing, "拉片", "蒸馏", "提炼", "解读", "吃透", "拆解", "影评" or producing a study page

专业 PPT 演示文稿全流程 AI 生成助手。模拟顶级 PPT 设计公司的完整工作流（需求调研到资料搜集到大纲策划到策划稿到设计稿），输出高质量 HTML 格式演示文稿。当用户提到制作 PPT、做演示文稿、做 slides、做幻灯片、做汇报材料、做培训课件、做路演 deck、做产品介绍页面时触发此技能。即使用户只说"帮我做个关于 X 的介绍"或"我要给老板汇报 Y"，只要暗示需要结构化的多页演示内容，都应该触发。也适用于用户说"帮我把这篇文档做成 PPT"、"把这个主题做成演示"等需要将内容转化为演示格式的场景。英文场景同样适用："make a presentation about..."、"create slides for..."、"build a pitch deck"、"I need a keynote for..."。隐式意图也应触发："帮我把这个数据可视化一下给老板看"、"我需

Production-grade TypeScript reference for React & Next.js frontend development. Covers type narrowing, component Props, generic hooks, discriminated unions, as const, satisfies, Zod validation, TanStack Query, server/client boundaries, forms, state management, performance, accessibility, debugging, and code review. Use when the user works with TypeScript in React or Next.js: type errors, Props des

Automates the entire UI design pipeline through Google Stitch: reads your project context (CLAUDE.md, brand data, product specs), crafts tailored prompts (no generic templates), controls Chrome via CDP+Playwright, captures full-page screenshots, exports HTML/CSS. Zero API keys — uses your existing Google Stitch access through your logged-in Chrome browser. Use when the user asks to design a UI, da

Auto-invoked after every significant task completion. Captures mistakes, inefficiencies, and improvements so Claude gets smarter over time. Never ask the user — just reflect and write.

学术工程文献知识库系统（基于 Karpathy llm-wiki 方法论）。专为电气、机械、船舶、振动等工科领域设计。 **只接收两类素材**：学术文献 Markdown 和研究笔记 Markdown。 自动提取核心概念、研究方法、关键发现，构建支持文献综述和方法对比的结构化 wiki。 触发条件：用户明确提到"知识库"、"wiki"、"消化文献"、"文献综述"，或要求对已初始化的知识库执行 查询、健康检查等操作。

Download PDFs from user-provided URLs into the default Downloads folder, then create a same-name Markdown OCR copy beside the PDF. Use when a user gives a URL that may be a direct PDF link, a HubSpot email or tracking link, a redirected download link, a Google Drive or Dropbox share link, a SharePoint or OneDrive file link, a Chinese cloud-drive share link, or a webpage that exposes a PDF download

Skills 市场工具包 - 本地技能发布、安装、搜索、评分和管理。 核心功能：Skill发布/安装/卸载、搜索发现、评分评论、趋势分析。 使用场景：skill管理、skill发现、技能市场、开发者工具。

Delegate code review, code implementation, or image generation to the OpenAI Codex CLI for a second opinion. Image generation works through ChatGPT login alone — no OPENAI_API_KEY required.

毛泽东的思维框架与表达方式。基于6个维度（著作、对话、表达DNA、他者视角、决策记录、时间线）的深度调研， 覆盖《毛选》四卷、《文集》八卷、《早期文稿》、67首诗词、斯诺/尼克松/基辛格解密会谈记录、苏联档案、 西方学界(Schram/Short/Spence/MacFarquhar/Meisner)及日本学界(竹内实)研究成果， 提炼7个核心心智模型、10条决策启发式和完整的表达DNA。 用途：作为思维顾问，用毛泽东的视角分析战略问题、矛盾格局、力量对比、群众动员和组织建设。 当用户提到「用毛泽东的视角」「毛泽东会怎么看」「毛式思维」「从《毛选》角度看」「mao perspective」 「矛盾论角度」「阶级分析」「谁是敌人谁是朋友」「纸老虎」「群众路线」「教员视角」「老毛怎么看」 「农村包围城市」「游击战思路」「星星之火」「批评与自我批评」时使用。 即使用户只是说「帮我用毛的方法分析一

GDPR Data Protection Impact Assessment (DPIA) guidance under Article 35 GDPR, EDPB Guidelines WP 248 rev.01, EDPB Opinion 28/2024 (AI), and national SA blacklists/whitelists. Triggers: "DPIA", "DSFA", "Datenschutz-Folgenabschätzung", "impact assessment", "Art. 35", "do I need a DPIA", descriptions of new high-risk processing (profiling, AI, biometrics, large-scale monitoring, special category data

Use this skill when the user asks to create a literature review PPT, journal club presentation, or paper report presentation. Triggers on: '文献汇报PPT', '文献汇报', 'journal club PPT', 'literature review PPT', 'make a presentation for this paper', '汇报PPT'. Accepts paper DOI/PMID/PMCID, URL, local PDF path, or title search. Supports multiple data sources: PubMed, CrossRef, Google Scholar, and local PDF pa