Wechat Inline Visuals logo

Wechat Inline Visuals

Community
843645440
wechat-inline-visuals

从已完成写作的微信公众号文章中提取观点、对比、流程或已核实数据,并交给固定渲染器一次生成当前主题的公众号正文与原生 HTML 信息模块。用于已选定排版主题后增强手机端扫读体验,同时不生成正文图片、不调用图片模型、不让 Agent 临时编码排版的场景。

Overview

Publisher843645440
Repositorywechat-skill
Skill namewechat-inline-visuals
Stars
132
Forks
29
Bundled files
6
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.

  • 6 bundled files

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

  • Open source

    Published by 843645440 on GitHub. Read the source before you install it.

Installation

Install the Wechat Inline Visuals 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/843645440/wechat-skill/tree/release/optional-skills/wechat-inline-visuals
  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/843645440/wechat-skill.git /tmp/wechat-skill
mkdir -p .claude/skills
cp -r /tmp/wechat-skill/optional-skills/wechat-inline-visuals .claude/skills/wechat-inline-visuals
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wechat Inline Visuals 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 Wechat Inline Visuals 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 Wechat Inline Visuals 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.

微信公众号原生信息模块

从 article.md 提取 0—3 个语义模块,再由流水线固定渲染器把正文和模块一次写入 article.html。最终模块是公众号正文 HTML,不是 PNG。

输入

必须同时取得:

  • 最终 article.md。
  • 本轮已固定的主题标识。

先读 references/plan-schema.md 与 references/plan-shell-coerce.md。theme-component-map.md 仅保留为旧组件对应关系参考,流水线不再要求 Agent 按它手工组装 HTML。

工作流

被 wechat-content-pipeline 调用时,本 Skill 只负责一次生成 inline-visuals.json;随后立即交还 pipeline_runtime.py finish。不要自行运行校验器或渲染器,因为统一运行器会机械完成校验、降级和排版。下面的校验与渲染步骤只用于单独调用本 Skill 的场景。

  1. 从文章已有内容识别最值得扫读的结构。优先顺序为:核心影响对象、清晰二元对比、真实流程、已核实数据。
  2. 只在内容自然成立时选 1—3 个模块;没有合适内容时输出空 modules,不得为凑数量制造结构。 正文已经用 Markdown 表格或列表清楚表达的一组信息不得再次包装成对比、指标或观点模块。
  3. 只尝试一次,写入 inline-visuals.json。顶层必须且只能包含 version(固定为 1)、theme(与本轮固定主题完全一致)、modules(0—3 项)。空计划也必须写成:
json
{"version": 1, "theme": "<SELECTED_THEME>", "modules": []}

禁止只写 {"modules": []} 或漏掉 version/theme。每个模块记录原文锚点和原文证据。placement.after_text 必须直接复制所在章节中一段短、连续、唯一的原文,不得概括改写;优先取完整短句或能唯一定位的半句。evidence 同样复制原文连续片段。正文含 **、__、反引号、==、++ 或 <u> 等行内 Markdown 时,计划里使用读者可见的纯文本;校验器与渲染器必须使用同一套“仅移除行内标记、保留文字和标点”的规范化规则,不能因排版标记误判,也不能退化为模糊语义匹配。运行:

bash
python3 <SKILL_ROOT>/scripts/validate_plan.py \
  --plan <WORK_DIR>/inline-visuals.json \
  --article <WORK_DIR>/article.md \
  --theme-index <PROJECT_ROOT>/references/theme-index.md \
  --degrade-on-error --fallback-theme <SELECTED_THEME>
  1. 校验失败时接受脚本生成的当前主题空计划,不修改字段、不重新提取、不重试。若降级原因是“锚点/证据不是原文”,维护时先区分真正改写与 Markdown 标记误杀;后者应修校验器并加回归测试,而不是放宽为模糊匹配。具体案例和测试要点见 references/anchor-normalization.md。
  2. 调用 wechat-content-pipeline/scripts/render_article.py,由固定组件按 placement.after_heading 和 placement.after_text 一次完成正文与模块排版。不得手工复制主题组件,不得为当前文章新写 Python、HTML 模板或二次插入脚本。
  3. 渲染器若发现插入异常,会把计划降级为空并保留完整纯正文 HTML;记录降级原因后继续。最后运行根目录的 validate_gzh_html.py,ERROR、WARNING、占位符必须全部清零。

提取边界

  • insight:2—4 个受影响对象、成本承担者或关键判断。
  • comparison:两个对象或阶段在同一维度下的真实差异。
  • process:正文明确支持的 3—5 个连续环节。
  • metrics:2—4 个正文中已核实的数据;没有可靠数字时改用 insight。

字段名硬坑(曾整包降级)

  • 顶层只能是 version / theme / modules;空计划也必须三字段齐全。
  • insight.items:label + text(不是 title/name)。
  • process.steps:label + text。禁止 name 或 title。 写 name 会触发 包含未知字段:name,校验失败后 modules 被清空。
  • comparison:left/right 各含 heading + items[]。
  • metrics:条目用 value + label + 可选 note;value 必须原样出现在正文。
  • 完整示例见 references/plan-schema.md。写 plan 前对照 schema,不要凭记忆猜键名。

同篇不要重复模块类型,不要连续插入两个模块,不要把标题、导读或结尾 CTA 重新包装成模块。 表格由正文渲染器直接按当前主题处理,不新增 table 信息块类型。

硬性限制

  • 不新增事实、数字、公司表述、人物、引用、因果关系或作者经历。
  • 不把推测压缩成事实,不删除“可能”“短期内”“仍取决于”等限制条件。
  • 模块内容只能来自 article.md 正文已有信息,不引入正文之外的来源材料。
  • 不生成正文 PNG、SVG 文件或截图,不调用 Agnes、Baoyu 或任何图片模型。
  • 输出必须遵守根排版 Skill 的微信红线:内联样式、<span leaf="">、无 class、无 <style>、无 Grid 和复杂定位。

完成标准

inline-visuals.json 是通过校验的计划或明确降级后的空计划;文章原文完整保留;最终 article.html 严格校验为零错误、零警告。记录 module_count、kinds 和 degraded。计划或插入失败只降级一次,不阻塞草稿流程。

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 Wechat Inline Visuals AI skill do?

从已完成写作的微信公众号文章中提取观点、对比、流程或已核实数据,并交给固定渲染器一次生成当前主题的公众号正文与原生 HTML 信息模块。用于已选定排版主题后增强手机端扫读体验,同时不生成正文图片、不调用图片模型、不让 Agent 临时编码排版的场景。

Why use Wechat Inline Visuals on TypingMind?

Because you install it once and use it with any model. Wechat Inline Visuals 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 Wechat Inline Visuals in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/843645440/wechat-skill/tree/release/optional-skills/wechat-inline-visuals. 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 Wechat Inline Visuals?

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 Wechat Inline Visuals?

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

Is the Wechat Inline Visuals AI skill free?

It is published on GitHub by 843645440. Check the repository for licensing terms. 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 👇