Wb Xhs Xiaohei Illustration Agent Skill
Use when a Chinese article, post, blog, or methodology piece needs default 16:9 小黑 hand-drawn body illustrations, a multi-image shot list, or an explicitly requested 3:4 pencil-style human narrative variation rather than a cover, poster, or formal infographic.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/jackbauerxu/workbuddy-xhs-skills --skill wb-xhs-xiaohei-illustrationWhat comes with it
1 177 bytes besides the instructionThe instruction itself
as written by the author小黑怪诞正文配图
把中文文章里的判断、流程、状态和隐喻变成纯白、手绘、怪诞但清爽的正文配图。默认交付是16:9 横版正文配图，不是 3:4 封面、PPT 信息图或通用人物插画。
默认交付
- 单张正文配图，或一篇文章的 4-8 张 shot list。
- 每张 shot 写明放置段落、核心意思、结构类型、小黑动作和 2-5 个中文批注建议。
- 最终资产保存到
assets/<article-slug>-illustrations/；未调用图像工具时必须保留not_called。 - 默认
style_variant是xiaohei_body。只有用户明确提出铅笔、人物叙事、3:4 或顶部标题留白时，才可选择下面的pencil_narrative变体。
创造的边界
这里的风格 DNA 是一组可用的视觉语法，不是固定模板。保留默认交付的画幅、角色职责、留白和可读性；但必须围绕当前文章重新创造主题、动作、物件、构图、色彩重心和隐喻。不要为了“像原版”而复刻来源案例，也不要为了追求变化而丢掉正文配图应有的单一认知锚点。
可选铅笔叙事变体
pencil_narrative 仅在用户明确请求“铅笔”“写实人物叙事”“3:4”或“顶部标题留白”时使用；它不替代小黑默认的 16:9 白底正文配图。
- 采用 3:4 竖版、非特定人物、黑白铅笔线稿与干净白底；保留上方标题留白，用一个可信的工作、学习或生活动作承载文章意思。
- 人物、道具和场景应随主题重新设计，不能暗示真实身份、未经证实的成绩或来源案例；除非用户要求，不叠加虚构数字、品牌、课程页或夸张成果。
- 在交付中注明
style_variant: pencil_narrative、触发它的用户要求、画幅、留白位置和生成状态。若请求不够明确，仍回到xiaohei_body默认模式，或先提出最小澄清。
过程
- 读文章、段落、截图或主题，找出一个值得视觉化的认知锚点；每张图只表达一个核心动作、结构、状态或隐喻。
- 需要多图时，先给 4-8 张 shot list；单图只选择一种结构：流程、系统局部、前后对比、角色状态、概念隐喻、方法分层、地图路线或小漫画分镜。
- 为当前内容重新发明“物理动作 + 低科技物件”的隐喻，再让小黑承担核心动作；不复刻来源示例的物件或构图。
- 小黑的基础形态是黑色实心、白点眼、细腿、空表情；它是认真参与系统运转的荒诞工作者，不是角落贴纸、吉祥物或可爱卡通。
- 生成 16:9 横版、纯白背景、黑色细手绘线稿。主体约占 40-60%，保留大块白区；最多 5-8 处红色、橙色、蓝色中文手写批注。橙色只给主路径/箭头，红色只给重点/问题/结果，蓝色只给补充或系统状态。
- QA（
xiaohei_body）：白底、16:9、小黑承担动作、隐喻非旧例复刻、主体不超过约 60%、短批注可读、没有课程页/PPT/UI/纸纹/渐变或左上角类型标题。 - QA（
pencil_narrative）：确认用户已明确触发该变体、3:4 画幅、非特定人物、顶部留白和单一动作成立；它不能被标成小黑默认输出。
质量门
在生成前先写 art_direction：当前文章的矛盾或变化、一个新造的物理动作与低科技物件、主体的取景角度、留白位置和批注节奏。高质量不是把“办公桌、电脑、便签”换一种摆法；画面必须让读者不看正文也能感到这篇文章在讨论的具体关系。
quality_gate 按叙事动作、线稿完成度、留白、批注和原创性逐项审查：
叙事动作：小黑（或明确选择pencil_narrative的非特定人物）真的推动关系变化，不能只站在道具旁。线稿完成度：动作、物件比例和空间关系清楚；线条有前后层次，不出现肢体、透视、物件连接或文字的明显错误。留白：主体约占规定比例，画面在手机尺寸仍呼吸；铅笔变体保留顶部标题位。批注：只保留能帮助理解的短中文，颜色职责明确，不把术语或乱码当装饰。原创性：隐喻、动作和物件来自当前文章，既不复刻来源示例，也不回退为无关的通用办公场景。
先生成候选，再记录 quality_gate 结果。若失败，只修失败的动作、线稿、留白、批注或隐喻；不能因为满足白底和画幅就把平庸候选标为完成。
来源与边界
本模块基于 helloianneo/ian-xiaohei-illustrations 的 MIT 许可，保留来源归属，并使用其“小黑参与核心动作”的可迁移角色与正文配图方法。不得复制其示例成图、既有构图、提示词或案例物件；同一主题也要重新发明隐喻。封面、长文排版和严格图表交给相邻视觉专家。
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-xiaohei-illustration 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.