Nook Wechat Writer
用 nook 内容生产方法写、改、审、拟题、适配微信公众号文章。适用于写公众号文章、长文写作、素材成文、改稿、去 AI 味、定角度、拟标题摘要、整合卡兹克/花叔式写作工作流、文章与短视频脚本互转，或从笔记/素材/转录稿/链接/粗略想法写成可发布的文章。
Nook Image Gpt
A Claude skill from captain-nook/nook_skills.
Nook Short
Plan and draft Chinese short video and Xiaohongshu image-text content for Douyin, Xiaohongshu, and WeChat Channels. Use when Codex needs to turn a mid-form transcript, project recap, idea, flash thought, hot topic, or platform sample data into a weekly 12-piece content plan, content briefs, direct oral scripts, Xiaohongshu carousel text, or when the user asks what is trending on Xiaohongshu/Douyi…
Nook Trave
Create system-driven self-driving travel roadbooks, especially long China road trips such as Xinjiang routes. Use when the user asks for a self-driving itinerary, roadbook, route guide, travel manual, multi-day driving plan, or on-trip replanning; supports guided questioning, external information orchestration, route/weather/hotel evidence, and mobile-first vertical HTML/PDF-style roadbook produc…
Nook Qwen Image
Atomic high-quality text-to-image + image-edit skill backed by ModelScope Qwen-Image and Qwen-Image-Edit. Use when Codex needs Chinese poster, cover, editorial image, typography-heavy visual material, or higher-quality Chinese/English text rendering through a paid ModelScope image channel; use nook-zimage for cheap fast drafts, batch tests, and low-stakes background exploration. Also use this ski…
Nook Tv Cover
为 Nook 内容生成视频封面。只支持长封面（YouTube）、短封面（B站）和竖封面（抖音/小红书/视频号）。默认使用科技风封面风格，图生图优先，并按平台尺寸输出。
Nook Card
|
Nook Humanizer Zh Review
审校和改写中文内容，去除 AI 味，保留 nook 的真实判断、具体细节和渠道风格。作为子审校技能用于最终风格审校、去 AI 味审校、人味审校和润色，适用于公众号文章、长文稿、视频转录稿、口播稿及其他 nook 内容。
Nook Cover
建设态多平台封面生产 skill。用于规划或生成小红书、微信公众号、B站、YouTube、抖音、视频号等自媒体平台封面。当前 V0.2 聚焦小红书封面：按运行时选择 Codex image2.0、外部原子出图工具或用户素材生成主视觉，再按需用 HTML / 后处理稳定中文标题层。
Nook Zimage
Atomic low-cost text-to-image skill backed by ModelScope Z-Image Turbo. Use when Codex needs cheap/free text-to-image generation for drafts, background assets, poster materials, testing, or batch visual exploration; use nook-image2-gpt instead for image-to-image or higher-quality production images.
Nook Slides
Create Chinese-first slide decks and editable PPTX plans through a strict template-filling workflow. Use whenever the user asks to make slides, PPT, presentation, deck, course slides, report slides, or to turn Markdown/notes/articles into slides. This skill must use the current three Chinese visual systems, locked visible copy, approved component schemas, and deterministic rendering; it must not…
Nook Image2 Gpt
Atomic image generation skill backed by the nook-image2-gpt MCP server. Use when Codex needs stable text-to-image or image-to-image generation through submit_image_task and get_image_result, especially as a low-level image provider for larger skills such as nook-poster.
Nook Title
Generate, analyze, score, and revise Chinese WeChat/AI-media titles in nook style, including high-density AI news titles with entity/number/action/consequence structures. Use when the user asks for 公众号标题, 给我取几个标题, 候选标题, 标题评分, 标题风格提炼, AI资讯标题, 爆款标题, or title optimization from an Obsidian draft, article facts, notes, links, or finished manuscript.