Wb Xhs Visual Router Agent Skill
Use when a Xiaohongshu request needs a finished cover or cover diagnosis, 16:9 小黑 body illustration or shot list, an explicitly requested pencil narrative body-illustration variation, material explanation image or chart beautification, and the agent must choose the correct visual specialist and preserve a truthful production state.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/jackbauerxu/workbuddy-xhs-skills --skill wb-xhs-visual-routerWhat comes with it
3 616 bytes besides the instructionThe instruction itself
1 sections, as written by the author小红书视觉路由器
只负责意图分流、共同状态和交接。不要在这里重写专家的画面方法、提示词或详细 QA；它们分别属于对应专家 skill。
先做预检
- 用户同时要“素材插画 + 封面”而没有封面精确标题：先只问这个标题。不要先选模式、生成图片或交接。
- 用户要求把没有来源的精确量化主张放上画面：保留原文逐字提问。例如：
“效率提升80%”没有可核验来源，是否允许把“效率提升80%”替换为不含数字的定性对比？不要改成泛泛的“无来源数字”。 - 必填项缺失而一个安全默认值不改变事实、交付类型或用户意图时，直接采用并披露该安全默认值；只在无法安全默认时问一个最小问题。用户说“不要问我，直接给这篇职场文章配图”且已有泛化主题时，可采用“非特定职场人物 + 中性办公室场景 + 无未证实数据”的默认值。
封面标题预检和无来源精确主张预检本身属于视觉流程：在这两种预检响应中，runtime evidence 必须为 mode: visual、imagegen: not_called、persistence: not_saved、qa: not_run。不得把已经选择视觉路由的预检写成 not_applicable。
选择专家
| 用户意图 | 交给 | 说明 |
| --- | --- | --- |
| 单张封面、标题锚点、证据可读性 | wb-xhs-cover-anchor | 专家决定锚点方向与封面 QA。 |
| 旧封面诊断或改版 | wb-xhs-cover-anchor | 专家评分信息密度、锚点、缩略图、对比和信任，再给完整改版方案。 |
| 中文文章的正文配图、shot list、小黑式认知隐喻，或明确指定的铅笔人物叙事 | wb-xhs-xiaohei-illustration | 默认由专家交付 16:9 白底小黑配图；只有用户明确指定时才切换 3:4 pencil_narrative。 |
| 机制图、流程图、图表美化或带短标签的解释图 | wb-xhs-material-illustration | 专家决定中心解释图、图表语义保真与可复用素材。 |
| 可复用图标、物件、关系箭头或栏目素材 | wb-xhs-material-illustration | 专家先确认中心解释关系，再决定可拆出的素材系统。 |
| 素材插画加封面 | 先完成精确标题预检；再按顺序交给素材专家和封面专家 | 两个专家各自保留方法所有权。 |
执行
- 读取 runtime contract 和 Visual Brief，创建或补齐共同状态。
- 交给被选专家时传递 Visual Brief 与已确认事实，并先记录内容专属
art_direction；不要编造人物身份、数据、案例或来源，也不要用“高级感”“极简”等空泛形容词代替构图决定。 - 有可用图像工具时，先生成候选，再按专家的
quality_gate审查；只修失败维度，并记录真实路径、迭代状态与 QA。 - 无工具、无写入权限或专家不可用时，保留现有资产（如有），把
imagegen写为not_called，写清能力缺口；不得声称已生成、已保存或已通过 QA。 - 一旦真实资产已持久化且用户没有要求解释，只返回必要的交付位置或下一步，不追加虚构的“成功说明”。
边界
- 不把这个 skill 当作通用文案、账号定位、选题或排期入口；这些交回相邻运营 skills。
- 不复制第三方的专属图片、模板、字体、人物或未授权提示词，只吸收可迁移的方法结构。
- 不把开发或测试方法写进面向用户的视觉运行时内容。
相关 skills
- routes-to:
wb-xhs-cover-anchor,wb-xhs-xiaohei-illustration,wb-xhs-material-illustration - composes-with:
wb-xhs-topic-bank,wb-xhs-humanize-compliance,wb-xhs-schedule-review
Other skills for the same job
different authors, same section of the catalogue
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
How to use it
Take jackbauerxu/wb-xhs-visual-router from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.