Wb Xhs Cover Anchor Agent Skill
Use when a Xiaohongshu or WeChat post needs a truthful finished cover, a cover-template recommendation, or an existing-cover diagnosis and redesign that must preserve factual claims, visual anchoring, and thumbnail readability.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/jackbauerxu/workbuddy-xhs-skills --skill wb-xhs-cover-anchorWhat comes with it
1 009 bytes besides the instructionThe instruction itself
as written by the author小红书封面锚点
先读取路由器交来的 Visual Brief。封面优先解决信息密度 × 视觉锚点：用户能否在信息流里 3 秒看懂承诺，以及画面是否有唯一的停留点。只使用已确认事实、已获授权的定性改写或中性默认值。
选择模板与锚点
- 先选一个完整封面模板，而非把所有元素堆到同一张图：
- 冲突型、数字型、截图型、情绪型分别用于观点、已验证步骤/数量、真实案例/测评、生活/故事内容。
- 数字型只能使用已确认的数字；截图型只能使用真实且已获授权的截图；情绪型必须有可用主体或中性场景。
- 确定一个唯一锚点：人脸/主体、已确认的大号数字、真实截图、前后对照或有强轮廓的物件。标题位优先在上 1/3，主体/物件多在中下区域，左上可放小分类标签。
- 做三层文字层级：主标题承担 60-75% 的文字权重，支持行 20-30%，角标 5-10%；缩略到约 80px 宽时，主标题、锚点和色块仍可辨认。
- 用户明确要生活方式封面时再选对应变体：
- 涂鸦描边小清新：真实生活照片基底、一个主体白色手绘描边、手帐贴纸标题和少量路线/箭头涂鸦。
- 阳光胶片拼贴白描边：暖阳真实照片、顶部 2-4 格胶片条、右侧/右下主体白描边、左侧手写标题与少量黄绿关键词高亮。
两种变体都不默认添加作者名、@、二维码、虚构品牌或水印。
没有主体、证据或可确认对照时，使用事实中性占位骨架：大标题、抽象几何或中性物件、清晰留白，不暗示具体人物、业绩或案例。
生成完成封面
- 检查封面精确标题、受众、目标、画布和事实边界；标题未给时交回路由器预检。
- 输出推荐模板、锚点位置、两种主色与一个强调色、字重层级、标题—证据—禁称事实，以及可直接调用图像工具的完成封面提示词。
- 生成或设计 1080×1440、3:4 画面；主标题与背景对比至少 4.5:1，缩略图目标 7:1。
- QA：比例、标题逐字一致、唯一锚点、三层文字权重、80px 缩略图、对比度、边距、信任信号和事实边界。只修失败维度。
- 持久化后回传真实路径和 QA 状态；未生成时明确
not_called或not_run。
质量门
在调用图像工具前，先写一条内容专属艺术方向：由当前标题和已确认事实导出的视觉前提、唯一锚点、构图动势、颜色/材质和留白策略。它必须能解释“为什么这张图只能服务这篇内容”，不能只列“高级、干净、治愈”等泛化形容词，也不复刻参考封面的构图。
对生成候选逐项检查缩略图、文字、锚点、信任：
缩略图：在约 80px 宽时仍先看见标题承诺与主体关系；没有被装饰、细碎文本或背景吞掉。文字：标题逐字准确、层级清楚、与背景有足够反差，不把错误汉字或假数字藏在小字里。锚点：主体、对照、截图或物件确实服务标题，而非随手摆放的通用笔记本、咖啡杯或抽象色块。信任：截图、人物、数字、结果和品牌均有授权或事实依据，画面没有模板水印、伪案例或夸张承诺。
第一次生成只是候选。任一维度失败时，在 quality_gate.failed_dimensions 记录原因，重做对应的文字、层级、构图或事实素材；四项通过后才可标记 quality_gate.status: passed。
旧封面诊断与改版
用户要求旧封面诊断或改版时，按以下结构输出：
template_fit：冲突 / 数字 / 截图 / 情绪 / 混合。main_problem与click_risk：一句话说明用户为什么会划走。- 1-10 分：信息密度、视觉锚点、缩略图可读性、色彩对比、信任/真实感。
- 最高影响的 3 个修正动作，以及一份不虚构事实的完成封面提示词。
先重写短而明确的封面承诺，再选单一模板、单一锚点、两种主色和一个强调色；不要把文章解释页误做成封面。
边界
- 不把无来源的百分比、排名、收益或案例作为视觉事实。
- 不复制参考封面中的专属视觉资产。
- 不替代素材插画或黑白手绘专家。
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-cover-anchor 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.