Illustrated Manual Word logo

Illustrated Manual Word

Community
liucongg
illustrated-manual-word

制作含结构、原理和步骤插图的可编辑 Word 手册。

Overview

Publisherliucongg
Repositoryliucong-skills
Skill nameillustrated-manual-word
Stars
251
Forks
31
Bundled files
59
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 59 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by liucongg on GitHub. Read the source before you install it.

Installation

Install the Illustrated Manual Word AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/liucongg/liucong-skills/tree/main/skills/illustrated-manual-word
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/liucongg/liucong-skills.git /tmp/liucong-skills
mkdir -p .claude/skills
cp -r /tmp/liucong-skills/skills/illustrated-manual-word .claude/skills/illustrated-manual-word
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Illustrated Manual Word in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Illustrated Manual Word on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Illustrated Manual Word is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

图解 Word 手册

将主题或技术资料制作成可编辑的 Word 手册,包含结构图、原理图、步骤图、说明文字和可追溯来源。流程包括资料核查、图片选择或绘制、Word 编排、实际渲染和逐页检查。

适用范围

  • 产品部件与操作说明、机械和科学原理图解、带剖面与状态图的读物、软件机制的概念类比。
  • 输入可以是对象、机制、仓库或资料。默认中文、A4 纵向,面向无专业背景的成年人;读者和用途可按任务调整。
  • 不用于认证维修手册、制造公差或压力设计、医疗和危险操作指南。纯润色、PDF 转 Word、统计报告不适用本流程。

输入与输出

在 BRIEF.md 记录对象、型号或版本、读者问题、真实结构或概念类比、适用范围、排除事项、用途与篇幅。仅在缺项会改变事实或安全结论时询问。

输出可下载的 .docx;保留 book.json、media.json、来源、图形源码和生成记录。PDF 与逐页预览用于验收,不替代 Word。标题、正文、步骤、图注、表格和来源为 Word 原生内容;内嵌插图为 PNG,图内零件和短标签不承诺在 Word 中独立编辑。

先完成小样章,再扩展全书。delivery_kind=sample-chapter 必须声明 sample_objectives 和 sample_limits;完整书使用 production,最低编辑单元、图数、视图和字数只用于识别空壳,不证明出版质量。technical-smoke 只用于技术测试,不作为成品交付。

中性内容与平台分发

  • 描述只说明用途、输入、输出和操作方法,不加入本 Skill 的作者介绍、个人称呼、团队署名、开发故事、推广语或内部调度说明。
  • Word 正文、封面、图注、表格、页眉页脚及图片替代文字只保留主题内容。页眉用书名或中性系列名,页脚用页码;不加入制作人、助手人设、平台推荐和无关制作说明。
  • 构建器不写入作者或最后修改者;清空备注、关键词等默认模板元数据。保留中性的主题标题和适用范围,不把旧书稿的作者字段自动带入新文件。
  • 用准确、客观的说明替代自我评价和夸张措辞;型号差异、来源、AI 图片披露、必要警告和适用限制不得因中性化而删除。
  • 分发前检查文档属性、隐藏文字、批注、修订及外部链接。未解决的审阅记录不能静默删除或视为通过;生成干净副本并保留原稿。
  • 包内不含个人绝对路径、账号、凭据、内部沟通记录、缓存或临时日志。第三方依赖的许可证和必要版权声明独立保留,不混入手册正文。本 Skill 的许可不替代外部图片或品牌素材的许可。

前提

通过当前宿主的命令工具运行 python <skill>/scripts/manual.py preflight。Word 构建需要 python-docx 和 Pillow;排版验收需要 PyMuPDF 和 LibreOffice。SVG 需要 Node 或 Python 绘图,以及 rsvg-convert、CairoSVG、Chrome 中至少一种栅格工具。依赖见 scripts/requirements.txt,在项目虚拟环境安装,不修改宿主全局环境。

搜图和生图使用宿主已有工具,不绑定模型、平台或账号。图片搜索不可用时回到来源网页或 PDF;不读取凭据、不打包密钥、不虚构工具执行结果。官方图片也需要核对使用权。

命令

<skill> 为本 Skill 根目录,<project> 为独立书稿目录。路径均可替换;脚本不会自动安装服务、调用另一个 AI 或执行发布。

text
python <skill>/scripts/manual.py preflight
python <skill>/scripts/media.py plan <project>/figure-brief.json
python <skill>/scripts/media.py fetch https://public.example/image.png --out <project>/research/image.png --allow-host public.example
python <skill>/scripts/media.py check <project>/media.json --out <project>/qa/media-check.json
python <skill>/scripts/media.py contact <project>/media.json --out <project>/qa/contact.png
python <skill>/scripts/manual.py raster <project>/figures/figure.svg --out <project>/figures/figure.png --width 2400
python <skill>/scripts/manual.py validate <project>/book.json
python <skill>/scripts/manual.py build <project>/book.json --out <project>/out/book.docx
python <skill>/scripts/manual.py render <project>/out/book.docx --out-dir <project>/qa
python <skill>/scripts/manual.py inspect <project>/out/book.docx --out <project>/qa/package.json
python <skill>/scripts/distribution_check.py <project>/out/book.docx
python <skill>/scripts/manual.py qa <project>/book.json <project>/out/book.docx --qa-dir <project>/qa
python <skill>/scripts/test_manual.py
python <skill>/scripts/test_media.py

下载示例域名是占位符,需替换为已核实的来源。media.py 不调用生图 API;下载限公开 HTTPS 白名单和 20 MB。plan 仅提供初步方法建议。

制作流程

1. 核对事实与解释目标

读取 references/research.md 和 references/editorial.md。每章回答一个读者问题,每图声明 question/kind/caption/alt_text/source_ids/claim_ids/part_ids。真实对象不编造内部结构;概念类比明确对应关系和限制。

优先读取官方手册、教材或机构原文,保留摘录、日期和用途;扫描 PDF 需检查页图。核心结论绑定实际读取的来源,至少一项权威来源直接支撑结构或机制。冲突和高风险结论另做交叉核查,可通过 min_verified_sources 提高门槛。计算和状态测试使用实际代码输出。

完成条件:任务说明、术语、部件、结论和来源可互相追溯;未读取的资料只列为候选。

2. 逐图选择图片方法

读取 references/image-workflow.md,参照 templates/media.example.json。

  • 产品外观和接口:使用有使用权的实拍或官方素材;资料充分时重绘。
  • 精确连接、数量、数据或状态:使用 SVG 或确定性绘图。
  • 材质、人物、环境和情境:使用已有图或生成图片,披露用途和生成性质。
  • 在实物图上解释:保留原图和独立标注层。
  • 生成的技术插画:必须逐项核对结构与跨图一致性,不作为独立事实证据。

回到来源页核对原图、型号和许可;缩略图与搜索摘要不是已验证素材。media.json 记录方法、用途、权利范围、实际文件和 hash;schema_version=0.3 将书稿与媒体清单互锁验证。

完成条件:每图有明确用途、方法依据、文件和权利记录;生成图有真实生成记录。

3. 绘制一致的结构与状态

读取 references/figures.md、references/benchmark-review.md 及 Anatomy 的 craft.md、walkthrough.md、verify.md 和最接近的完整示例。几何工具及许可位于 assets/vendor/anatomy/。

总览、剖面、爆炸和步骤图共享结构、坐标、部件与状态。检查真实接合、支撑、遮挡、连接和运动方向;不能只保持编号而改变实体。整体需辨认对象,4× 局部检查穿透、断线、悬空和错误遮挡。箭头和件号有明确语义,不用剖面代替开盖动作。

SVG 自包含,禁止脚本、事件、远程资源和 foreignObject。动画转换成表达因果的状态序列,图片中的长段文字不能替代原生正文。

完成条件:结构与状态测试实际运行;最终图与参照在同尺寸下比较,关键局部经过检查并记录修正。

4. 编排原生 Word

读取 references/word-layout.md。先确定图文单元和阅读顺序,再安排页型;图注与图同页,警告紧邻相关操作。默认流式排版,完整图版可固定分页。固定分页需真实渲染,不能靠额外空段落产生空页。

按内容调整字号、行距、功能色和图宽,避免夸张标题、无效留白和为凑页数而重复图。检查最终尺寸下的细线与标签,不只检查图片分辨率。

完成条件:原生正文可回读;实际 DOCX 页图无孤段、空白页、挤字、截断和图注错页;中性内容检查通过。

5. 分别验收

读取 references/acceptance.md,记录四项结果:事实与安全、图形与状态、版面与阅读、技术与可迁移性。

机器检查只证明声明和文件匹配,不证明科学或视觉正确。实际看过最终页图后才能填写 reviewed=true。修改 DOCX 后旧 hash 和旧审阅结果失效;缺工具、未测试环境和未解决问题分别报告。

完成条件:最终每页和关键局部已审阅,来源与状态可核查,结构、媒体和中性内容检查通过,记录匹配最终文件。

6. 交付与分发

交付所需 Word 及必要预览,简短说明主题、实际页数、图片格式和限制。公开发布前另核素材权利与发布权限。打包排除秘密、个人路径、参考专用版权原页、临时日志和内部交流记录,保留必要许可证。

复制或解压到新目录后重新运行脚本;重建产物需重新渲染和审阅,不能继承旧文件的通过声明。

示例与限制

references/v03-example.md 说明表带操作与活塞泵两个样章的重建方法。示例采用 SVG 技术图和已有生成情境图,不需要再次付费生图。历史磨豆机脚本只供技术回归,不作为合格视觉基准。

已验证的宿主环境为 macOS;其他操作系统和 Agent 平台需本地测试。Word 内嵌图为 PNG;教学重绘不构成品牌授权、尺寸认证、制造图或维修指导。

常见问题

  • 搜索摘要、模型回答和 verified=true 不能替代来源回读。
  • 图精致不代表结构正确;生成图不能补充未知事实。
  • 页数、图数和回归通过不代表成品质量。
  • 没有真实渲染器时只能报告文件构建完成,不能报告排版验收完成。
  • 去除本 Skill 的署名不等于可以删除第三方许可证、来源或必要的权利披露。

验收记录

保留 qa/render.json、review.json、media-check.json、package.json、中性内容检查结果、来源、结构测试和修正记录。以实际最终文件为准;未验证的能力和环境明确标注。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Illustrated Manual Word AI skill do?

制作含结构、原理和步骤插图的可编辑 Word 手册。

Why use Illustrated Manual Word on TypingMind?

Because you install it once and use it with any model. Illustrated Manual Word is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Illustrated Manual Word in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/liucongg/liucong-skills/tree/main/skills/illustrated-manual-word. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Illustrated Manual Word?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Illustrated Manual Word?

As many as you like. As long as a model supports skills, you can use Illustrated Manual Word with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Illustrated Manual Word AI skill free?

Yes. It is published on GitHub by liucongg under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇