Wechat Viral Writer logo

Wechat Viral Writer

Community
843645440
wechat-viral-writer

写有人愿意读完的中文微信公众号文章,并用脚本把「好不好」量化成分数。四个维度:信息量(每 300 字一个具体信息)、利他性(读者能带走的东西)、可读性(手机竖屏节奏)、抓人(钩子密度与闭环)。写完必须跑 score_draft.py 体检并修到 blocking=0 且 score≥75。自带默认关闭的热点雷达开关(hot_radar.py),开启后聚合 8 个公开榜单产出选题候选,但不自动选题、不自动写稿。用于用户要求「写公众号」「提高完读率」「这篇没人读」「找选题」时。

Overview

Publisher843645440
Repositorywechat-skill
Skill namewechat-viral-writer
Stars
132
Forks
29
Bundled files
14
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.

  • 14 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 Viral Writer 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/.agents/skills/wechat-viral-writer
  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/.agents/skills/wechat-viral-writer .claude/skills/wechat-viral-writer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wechat Viral Writer 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 Viral Writer 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 Viral Writer 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.

公众号写作 · 可量化版

这个 Skill 解决一件具体的事:模型写完总觉得自己写得不错,但读者第三屏就退出了。

办法是把「读者会不会读完」拆成四个能被脚本量出来的维度,写完必须过体检。 不靠感觉,靠分数。

30 秒上手

bash
<SKILL> = .agents/skills/wechat-viral-writer

# 1)写稿前:读 references/writing-checklist.md(一页纸的全部硬要求)
# 1.5)先挑标题(写正文之前,30 秒):三个候选用不同刺点,让它排序
python3 <SKILL>/scripts/score_draft.py --markdown --titles "候选A" "候选B" "候选C"

# 2)写完之后立刻体检,看 markdown 版逐条修法
python3 <SKILL>/scripts/score_draft.py --article <article.md> --markdown

# 3)改完重跑,直到 blocking_count = 0 且 score ≥ 75
# 4)(可选,默认关闭)今天写什么都不知道时,开热点雷达
python3 <SKILL>/scripts/hot_radar.py --force --markdown

体检脚本退出码恒为 0:不合格是结果不是故障,看 stdout 的 status 字段。

四个维度(体检脚本的 100 分怎么来的)

维度分一句话判据量化指标
开头/标题20前 3 秒有没有留住人标题 ≤32 字、有可指认的主体、前 16 字有刺点、150 字内进正题
信息量25读者每 20 秒能不能拿到新东西最长无锚区间 ≤300 字、注水词 ≤4/千字
利他性20读完能带走什么≥2 种利他物、结尾四分之一有落点
可读性20手机上滑不滑得下去段落 ≤180 字、长句 ≤20%、每 800 字一个小标题
抓人15有没有一直被拽着走最长无钩区间 ≤500 字、结尾回扣开头

**及格线 75 分,且 high 级问题必须清零。**参考锚点:仓库里五篇旧的「新闻汇报腔」 稿件跑出来是 61–76 分(D/C),examples/gold-sample.md 是 95.8 分(A)。

资源路由

每次写稿必读:

按需读:

和其他 Skill 的关系:

  • 排版、配图、封面、入草稿箱 → ../wechat-content-pipeline/SKILL.md(本 Skill 不碰这些)
  • 去 AI 味的具体改写手法 → ../humanizer-zh/SKILL.md
  • 账号声口与题材边界 → ../wechat-tech-insight-writer/SKILL.md

接入流水线的位置

流水线写作时读 checklist 写 article.md。不要单独再跑一遍 score_draft.py: pipeline_runtime.py check 已经调用它,prepare / finish 会把 score ≥75 且 high=0 当硬门禁。

单独用本 Skill(不走流水线)时,才在写完后手动跑 score_draft.py。

init → brief → topic → shape → begin
   → 【本 Skill:按 checklist 写 article.md + digest.txt】
   → check(内含体检)→ humanize → prepare → finish
  • check 同时管结构合法性(标题、字数、图片路径)和完读体检。
  • 单独调用 score_draft.py 只用于流水线外改稿,或看 markdown 版逐条修法。

硬门禁:不得交付

  1. score_draft.py 的 blocking_count > 0,或 score < 75。
  2. 全文没有任何读者可带走的东西(体检里的 reader_benefit = 0)——白看一场。
  3. 标题没有可指认的主体(谁 / 什么产品 / 哪件事)。读者在推荐页只看得到标题, 说不出这写的是谁就不会点——这比没有刺点更致命。体检脚本能认出机构/人名 (美联储、特朗普、财政部等);纯中文技术名词仍可能漏判,那是 medium 提醒,不是硬拦。
  4. 标题前 16 字没有刺点:数字、反差、断言、疑问,一个都没有。
  5. 为了凑指标塞假数字、假案例、假亲历。体检分数是用来发现问题的,不是用来刷的。 编一个数字能加 3 分,但会让整个账号失去可信度——这条没得商量。
  6. 硬塞与题材无关的「普通人怎么办」清单。利他性按题材选形态,见 reader-benefit.md。
  7. 热点雷达输出的榜单标题被原样当成选题。榜单标题是新闻标签,不是你的观点。

一句话原则

读者不欠你注意力。每一段都要重新赢一次。

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 Viral Writer AI skill do?

写有人愿意读完的中文微信公众号文章,并用脚本把「好不好」量化成分数。四个维度:信息量(每 300 字一个具体信息)、利他性(读者能带走的东西)、可读性(手机竖屏节奏)、抓人(钩子密度与闭环)。写完必须跑 score_draft.py 体检并修到 blocking=0 且 score≥75。自带默认关闭的热点雷达开关(hot_radar.py),开启后聚合 8 个公开榜单产出选题候选,但不自动选题、不自动写稿。用于用户要求「写公众号」「提高完读率」「这篇没人读」「找选题」时。

Why use Wechat Viral Writer on TypingMind?

Because you install it once and use it with any model. Wechat Viral Writer 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 Viral Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/843645440/wechat-skill/tree/release/.agents/skills/wechat-viral-writer. 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 Viral Writer?

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 Viral Writer?

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

Is the Wechat Viral Writer 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 👇