Editorial Magazine logo

Editorial Magazine

Organization
VisActor
editorial-magazine

用 HTML/CSS 制作小红书、抖音的杂志图文,支持新闻资讯、人物生平、穿搭解析、旅行攻略、时序故事、观点解读与概念科普。按场景模板生成可编辑 HTML 与 PNG;穿搭优先使用用户照片,制作统一中性背景的多套组合与单套拆解组图。

Overview

PublisherVisActor
Repositoryskills
Skill nameeditorial-magazine
Stars
472
Forks
88
Bundled files
29
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.

  • 29 bundled files

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

  • Open source

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

Installation

Install the Editorial Magazine 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/VisActor/skills/tree/main/skills/editorial-magazine
  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/VisActor/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/editorial-magazine .claude/skills/editorial-magazine
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Editorial Magazine 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 Editorial Magazine 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 Editorial Magazine 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.

图文编辑室

将内容写入按场景选择的杂志版式,交付可编辑的 HTML 和独立 PNG。正文是 HTML 文本,布局用 CSS Grid/Flex,装饰可用内联 SVG。无需 VInfo/VStory/VChart/VSeed、页面 schema、布局 DSL 或前端构建工程。

选版

内容必读指导直接复制并编辑的 HTML
新闻资讯新闻新闻版
人物生平、人生阶段、代表成果与影响人物生平全景主图 + 三张多图详解
穿搭图片、搭配思路、穿搭分析穿搭组图及抠图多套组合 + 单套拆解
目的地旅行攻略、文化介绍、多日行程旅行组图风景填字封面+文化页+每日路线
围绕关键时间节点展开的经历、事件、项目故事时序故事概览+三种节点页
观点解读、概念科普、多页专题四页编辑拼贴整组四页版

未明确场景时依据材料选择上述六类场景。人物生平强调跨阶段的时间脉络、代表成果和影响,默认全景主图+人生相册、作品图集、人物与世界三张多图详解,材料与用户页数要求优先。用户明确指定时优先沿用。穿搭默认先出多套组合总览,再为每套造型出单套拆解;同套不同角度不重复算套数,只有一套时直接用拆解页,用户指定页型与页数优先。观点与概念科普使用同一组四种子版式,依据写作目的组织正文;用户指定页数优先。旅行攻略默认封面+文化介绍+每天一张行程示意图;路线形状可自由变化,但相邻点的交通方式与时间必须明确,详见旅行指导。时序故事围绕一段经历或事件的推进,默认概览主图+逐节点故事页,按材料选用三种图文页型;与人物全人生回顾、独立新闻汇总、未来旅行路线、按论点展开的科普分流,详见时序故事指导。本技能目前不主动把其他经验教程、数据图表或交互网站套入上述版式;需要其他内容时先说明范围或按用户另给的版式处理。

生成流程

新闻与多页专题的原文无图、只有头像或界面图标时,默认主动联网搜索相关配图,不能直接转为纯文字。保留原文约束正文,不等于禁止外部配图;用户明确要求纯文字、仅用所给素材或禁止联网时才按其限制处理。具体选图与失败兜底见配图规则。

  1. 整理内容与来源。 新闻分出一条主新闻与其他新闻,每条子新闻默认配一张相关图片;人物生平整理身份、经历和有出处的摘句,核对年代、关键转折、代表成果及在世状态,并分配主图概览与三张详情的增量内容;穿搭逐图对应造型和解析;旅行整理目的地文化、逐日有序打卡点和每段交通方式/耗时及来源;观点与概念科普先组织整组论述,再分配到封面、三栏论述、横向展开和不对称收束页。时序故事提取同一主线下各节点的时间或阶段、事件、照片与变化,主图概览,详情增量展开。读共同编辑规则。已经给出的主题、图片、尺寸与页数直接沿用,不重复确认。需要“最新”新闻时按宿主可用的检索工具核验时间与来源;没有联网能力不能编造最新资讯。
  2. 准备素材。 需要摄影/拼贴/插画而素材不足时,先读正式配图与宿主生图,缺少用户素材时主动联网搜图,取得实际文件后替换图槽;需要原创插画时调用生图。故事与资讯禁止用代码绘制 SVG/CSS 几何图代替内容图片,或将其转 PNG 规避;豆包的新图生成与 MediaKit 去背景分开执行,失败明确保留缺图草稿,不能用装饰几何图冒充完成配图。需要去背景时先读透明素材与宿主路由:豆包办公直接使用内置 MediaKit 抠图,检查脚本不负责去背景。旅行封面的填景大字用英文或拼音,中文名作小字注释。用户上传的实际素材优先,排版参考图只提供构图依据,不当人物、新闻或穿搭素材。肖像保留身份与原色,不默认转黑白;已故人物也按原始素材、专题语境和用户要求选择,详见人物生平指导。穿搭先准备透明抠图,按专用指导处理边缘、孔洞与色彩。缺失的事实、图片、人物引语不能由模板示例补齐。旅行另备风景填字图片、透明场景前景、文化圆图与景点照片。先获取可用素材,再制作成品。
  3. 编辑 HTML。 复制对应模板,替换全部示例文字、示意图与示例标记;直接改语义 DOM/CSS,不生成中间页面数据协议。默认1080×1440,按用户尺寸重排。同一作品保持相同字体、纸色和强调色。模板固定的是构图关系,内容数量和高度可以调整。新闻、人物生平及观点/概念科普组图按全局主题配色从合适候选中随机选一套,写入 CSS,整组共用,导出不再随机;用户指定色优先。人物生平主图与三张详情默认统一纯白底(#FFFFFF),不随随机主题改变;强调色仍随机。穿搭按专用指导一次选定简洁中性背景,组合与拆解所有页共用同一底色、纹理与线条,不改变服装色彩。 旅行按专用指导共享字体与强调色;封面和风俗文化页共用按主题选色、低不透明度叠白后得到的浅色纯色底,默认不加纹理。每日路线页继续使用风景深底。时序故事默认白底与一种低饱和强调色,按主题确定后整组共用。
  4. 保留内容密度。 先识别参考图的正文面积、栏数、字号比例和阅读顺序,再用完整稿件排版。新闻、生平全景主图与观点/概念科普正文页遵循参考的长文密度,不擅自压成三条摘要或提前分页;生平第2–4张详情按专用指导采用多图叙事、短图注,穿搭默认大图、配色与简短解析;时序故事以大幅场景图、细节图和连续段落展开每个节点,不套用生平详情的短图注策略。1080宽的密集杂志正文可从20–24px、1.4–1.55行高起调,生平绕排版按专用指导可用18–20px承载连续叙事;穿搭短解析及大字简读版可用28–36px,不把同一密度强加给所有场景。容量由实排决定,不能只按人物数或字数拆页。禁止缩放整页、裁切正文或省略号隐藏内容。详见各版的容量与变体。
  5. 导出验收。 按字体加载准备字体:默认 CDN → 可选本地 WOFF2 → 系统回退,按实际字符和字重加载,成功字体内嵌到成品,skill 不附字体二进制。再按导出规则嵌入图片、CSS及需要的字体,运行 scripts/export.py。旅行核对每日 n 个点的 n−1 段交通标签、线路与编号映射。时序故事核对主图与详情的节点、时间、标题及照片映射,按实际页数更新页码。逐页查看原尺寸 PNG 与约375px宽预览(密集杂志页检查缩略层级与放大后的正文,不为免放大而强行删文),检查来源、肖像身份、图文对应、透明边缘、服装完整性、配色与正文。机器检查不代表视觉通过,确有问题就改 HTML 再导出。
  6. 交付。 HTML、逐页 PNG、图片 ZIP、sources.md;穿搭保留全身及单品抠图 PNG、原图映射与背景 seed/色值/纹理,主题色和生成/编辑素材记在来源记录中。需要发布文案时附 post.md。报告真实完成项与限制,不自动发布。
bash
# 路径以 skill 根目录为基准,导出到新目录
python scripts/export.py --html /绝对路径/magazine.html --output /绝对路径/export
# 已有 Chromium/Chrome 可加 --browser /绝对路径/浏览器

所有模板都是可修改的静态源文件,仅包含轻量矢量占位,不附带摄影图片、高清演示素材或内嵌栅格图。图槽保留用途与构图关系:人物主肖像/辅图、透明主体、旅行风景/前景、文化与景点配图等。正式制作按本次材料替换占位,并重新校准裁切、透明轮廓及绕排边界;占位不能充当真实配图或完整素材交付。最终作品仍按导出规则内嵌实际图片,确保离线可用。

模板中的虚构人物、生平、作品、时序故事、目的地“海屿”、交通数字及原创示例稿件只用于展示构图与容量,必须替换并核验,不能作为真实资料或内容配额。新闻、人物生平主图及概念科普保留完整示例正文,穿搭保留大图与短解析。修改作品直接修改 HTML 后重导出,不把整张参考截图当背景再覆盖文字。

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 Editorial Magazine AI skill do?

用 HTML/CSS 制作小红书、抖音的杂志图文,支持新闻资讯、人物生平、穿搭解析、旅行攻略、时序故事、观点解读与概念科普。按场景模板生成可编辑 HTML 与 PNG;穿搭优先使用用户照片,制作统一中性背景的多套组合与单套拆解组图。

Why use Editorial Magazine on TypingMind?

Because you install it once and use it with any model. Editorial Magazine 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 Editorial Magazine in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/VisActor/skills/tree/main/skills/editorial-magazine. 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 Editorial Magazine?

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 Editorial Magazine?

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

Is the Editorial Magazine AI skill free?

Yes. It is published on GitHub by VisActor 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 👇