zhouwei713

Convert books, course transcripts, article collections, podcast transcripts, workshop notes, reports, manuals, or other methodology-rich source materials into source-grounded installable Agent Skills. Use when the user wants to extract practical methods,…

The user has product evidence and wants to decide whether to change direction. Use when the user wants to apply The Lean Startup's Pivot method to produce A pivot diagnosis report with evidence, failed assumption, recommended pivot, risks, and next validation…

The user wants to test a product idea with the smallest useful experiment. Use when the user wants to apply The Lean Startup's Minimum Viable Product method to produce A concise MVP experiment plan with assumption, prototype scope, metric, threshold,…

The user wants to run an iterative product learning cycle. Use when the user wants to apply The Lean Startup's Build Measure Learn method to produce A Build Measure Learn cycle plan and learning record..

The user has product evidence and wants to decide whether to change direction. Use when the user wants to apply The Lean Startup's Pivot method.

The user wants to test a product idea with the smallest useful experiment. Use when the user wants to apply The Lean Startup's Minimum Viable Product method.

The user wants to run an iterative product learning cycle. Use when the user wants to apply The Lean Startup's Build Measure Learn method.

Use when the user wants to turn a static scene, character images, aerial map, drawn path, or route-control image into an immersive first-person FPV AI video prompt, especially Seedance/Kling/Runway/Veo style one-shot videos with numbered stop markers,…

Use when the user wants to turn a static scene, character images, aerial map, drawn path, or route-control image into an immersive first-person FPV AI video prompt, especially Seedance/Kling/Runway/Veo style one-shot videos with numbered stop markers,…

Install, start, customize, verify, diagnose, or restore the external WorkBuddy Windows desktop theme in this directory.

Create, refine, diagnose, and release adaptive WorkBuddy Dream Skin themes in this project, including image driven light or dark UI selection, lively nonblocking decorations, readable chat and artifact surfaces, external CDP injection, and strict visual…

做 PPT 和美化 PPT 的一站式 skill，输出可编辑的原生 .pptx。从零生成时，给一个题目、一篇文章或口播稿、一份大纲，产出结论式标题、带口播备注、风格统一的 PPT；按参考图美化时，给一份朴素的 .pptx 和一张参考图，文字一字不改地换上统一的配色、母版、版式、图标和插画。当用户说"做个PPT""把这篇文章做成PPT""生成口播PPT""美化PPT""照这张图的风格改PPT""套个风格""用公司模板做""make slides""beautify my deck"，或丢来 pptx、potx…

为AI视频生成模型（Seedance、Sora、Kling、Runway、Veo等）撰写真实感、去AI感、纪录片质感的结构化视频提示词。当用户想生成AI视频提示词、优化现有视频提示词、追求"真实感""家庭录像感""手机随拍感""DV感""监控录像感"的视频效果，或提到Seedance、文生视频、视频prompt时，务必使用此skill。即使用户只是描述了一个想拍的场景或氛围，也应使用此skill将其转化为完整提示词。

Write high-quality GPT-Image-2 prompts with strong structure, layout logic, and production-ready visual direction. Use this skill whenever the user asks for image prompts, wants better GPT-Image-2 prompting, wants to upgrade a weak image prompt, asks for…

Direct believable character performance and generate complete AI video prompts for text-to-video models. Use for facial acting, microexpressions, emotional transitions, dialogue performance, or vague character ideas such as “an ancient beauty breaks down.”…

中文标题工具，覆盖生成、诊断、评审、复盘四种场景。适用于一稿多发（公众号、小红书、X 短帖、X 长文、抖音、视频号）、已有标题改写、多候选比较、带账号数据的标题复盘。挖一次内核按落点分发，每个落点给稳妥、有点冲、顶格三档，每档再给作者语气和通用语气两版，内置 AI 工具赛道的网感公式与取词表。

Generate a set of storyboard style image prompts from a user's idea. Use when the user asks for visual planning prompts, storyboard prompts, advertising storyboard prompts, director boards, concept boards, preproduction boards, visual proposal prompts, or…

为 Seedance 2.5 编写、诊断和重写可直接投喂的视频提示词，覆盖文生视频、图生视频、多图片视频音频参考、最长 30 秒叙事、多轮延长、指定时间段编辑、运镜与视角编辑、绿幕合成、白模渲染、声音与口型同步。用户提到 Seedance 2.5、即梦视频、@图片、@视频、@音频、长视频延长、局部编辑、白模参考、绿幕背景，或要求优化 Seedance 提示词时使用。普通跨模型写实短视频优先使用 realistic-video-prompting。

把任意主题做成一本能转圈翻看的 3D 纸雕立体书网页（旋转木马式 pop-up book），书页围成一圈，每一幕是分层纸雕场景，点按钮角色会动。用户给出故事、寓言、童话、绘本或科普主题，说做立体书、纸雕绘本、3D 故事书、pop-up book、carousel book、互动绘本网站时使用。默认用代码绘制角色，检测到生图模型时自动改用生图素材。输出单个 HTML 文件。

Use when the user wants realistic low-angle or high-angle wide portrait photography prompts, including ground-level sneaker foreground, overhead/downward shots, travel/campus/street/Japanese architecture scenes, adult youth-style characters, candid lifestyle…