Gzh Explosive Content Detector logo

Gzh Explosive Content Detector

CommunityPopular
SpaceZephyr
gzh-explosive-content-detector

为公众号文章创作打造的专业数据洞察工具。全网持续收录每日爆款文章,收录依据:低粉高阅读、阅读靠前、数据增长中、原创靠前,助力号主获取数据参考。

Overview

PublisherSpaceZephyr
Repositorycreator-buddy
Skill namegzh-explosive-content-detector
Stars
1.5K
Forks
234
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

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

Installation

Install the Gzh Explosive Content Detector 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.
  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/SpaceZephyr/creator-buddy.git /tmp/creator-buddy
mkdir -p .claude/skills
cp -r /tmp/creator-buddy/gzh-Skills/gzh-explosive-content-detector .claude/skills/gzh-explosive-content-detector
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gzh Explosive Content Detector 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 Gzh Explosive Content Detector 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 Gzh Explosive Content Detector 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.

公众号爆款文章查询


简介

面向公众号选题与创作的数据洞察 Skill:持续收录全网爆款文章,按「低粉高阅读、阅读靠前、数据增长中、原创靠前」等维度筛选,为号主提供可参考的爆款样本。

能做什么?

  • 🔍 关键词探测:按赛道/细分词查询最匹配的公众号爆款内容
  • 📊 智能筛选:结合用户意图与内容相关性,从候选中挑出最多 10 条高质量推荐
  • 🃏 双形态展示:Markdown 卡片 + HTML 网格卡片,便于阅读与分享
  • 🧭 细分引导:展示结果后主动给出 10 个可继续深挖的细分赛道词

适合谁用?

  • 公众号运营 / 编辑 —— 找选题、看对标
  • 内容创作者 —— 了解近期高热话题与标题范式
  • MCN / 增长 —— 批量观察某一垂类的爆款特征

运行依赖:Python requests>=2.28.0


功能特性

核心功能

  • 爆款文章探测:搜索全站热门的公众号文章
  • 时间窗口:默认最近 7 天;最多可查询近30天公众号爆款数据
  • 泛化词治理:识别大类泛词后必须先给细分推荐并等待用户「拓展 / 不拓展」,禁止同轮继续跑脚本
  • 输出产物:脚本生成 {keyword}_爆款数据.html;筛选逻辑可参考 {keyword}_爆款数据.json(若脚本产出)

特色亮点

  • 意图优先:优先提取用户描述中的细分方向词,避免只用「职场」「情感」等过大类词一查了之
  • 数据诚实:非实时快照; today / 超 30 天等诉求有固定话术说明边界
  • 禁止凑数:最多 10 条,少于 10 条如实展示,禁止编造
  • 展示闭环:每条含推荐理由(≥15 字、禁止空话模板);文末必须附 10 个细分词引导下一轮查询

使用场景

当用户提出下列类型需求时,应调用本 Skill:

用户可能会问Agent 行为概要
「最近有什么爆款」「看看全站热门」关键词传 "",按默认时间窗查询全站热门
「职场 / 情感领域有什么爆款」(大类词)走泛化词流程:先给细分词 + 等待「拓展 / 不拓展」
「职场沟通技巧」「亲子教育选题」视为细分词,可直接调用脚本(无需拓展询问)
「近 15 天的 xxx」将口语映射为 startDate = 今天 - N 天 后查询
「要高赞 / 高分享的」意图类型归为数据需求型,筛选时侧重互动与数据表现

典型示例

场景一:无赛道浏览

用户:最近公众号有什么爆款文章? 助手:--keyword "" 拉全站热门 → 展示卡片与 HTML → 再给 10 个热门赛道细分词。

场景二:大类词需拓展

用户:帮我看看职场类的爆款。 助手:识别「职场」为泛化词 → 仅回复细分词列表并说明「拓展 / 不拓展」→ 本轮不调用脚本 → 用户回复后再执行查询。

场景三:自带细分描述

用户:我是情感号,做恋爱、婚姻、婆媳方向,给我热门参考。 助手:提取「情感、恋爱技巧、婚姻经营、婆媳关系」等多词逗号查询 → 意图筛选 → 展示 ≤10 条。


重要数据说明

时间与实时性

  • 数据时间差说明:文章互动数据截止为 数据获取时间,互动量可能持续增长,后续会持续更新。
  • 默认时间范围:最近 7 天startDate = 今天 - 7 天);数据不足时 自动扩展范围,并按下文固定话术 告知用户

边界话术(须原文使用)

  • 用户提及「今天 / 今日」:「非常抱歉,今天的数据暂未更新,已为您展示最近可用的数据」
  • 用户要求的时间超出 30 天:「非常抱歉,当前仅支持最近30天的数据,已为您展示最接近的数据」

核心执行规则(必须遵守)

  1. 泛化词必须先问再查:识别为泛化词时 禁止直接调用脚本;须先输出细分词推荐并等待用户选择。
  2. 正确顺序:关键词提取 → 判断是否泛化词 → 泛化词则询问 → 用户回复后再调用脚本
  3. 强制等待:输出细分推荐后 必须停止本轮脚本执行;不得在同一 assistant 回合内继续调用脚本。

泛化词 vs 具体词(定义须保留,用于判定)

  • 泛词:抽象层级高、覆盖范围广的概括性词汇,无具体场景/属性修饰,常为行业大类;语义为上位概念(如「职场」含工作/打工人;「情感」含恋爱/婚姻;如 AI);上下文中常搭配「领域」「类型」等(如「职场领域」「情感类型」)。
  • 具体词:抽象层级低、指向明确,含场景/属性修饰,为某泛词的直接子类;语义为下位概念(如「职场沟通」属职场技能子类;「恋爱技巧」属情感子类);结构常含修饰(如「婆媳」→「婆媳关系」;「亲子」→「亲子教育」)。

项目架构

目录与脚本(参考)

gzh-explosive-content-detector/
├── SKILL.md                          # 本技能文档
├── scripts/
│   └── fetch_gzh_trends.py           # 数据拉取与 HTML 生成入口
└── (运行产出){keyword}_爆款数据.html
    (若脚本生成){keyword}_爆款数据.json

数据流(概念)

用户请求 → 意图/关键词/泛化词判定 → fetch_gzh_trends.py → HTML(+ JSON)
        筛选与卡片渲染说明 ← 意图 + 相关性 + 数据分

常见问答

Q1:用户只说「职场」,能不能直接查? A:不能。须先走泛化词拓展并等待「拓展 / 不拓展」,同一轮禁止脚本。

Q2:什么时候关键词传空? A:用户 未给出任何赛道或主题词,仅泛泛要看爆款 / 热门时,传 "" 查全站。

Q3:数据为空怎么办? A:提示关键词较为冷门,建议更换为更热门的赛道关键词;不得因数据少而改用无关关键词或误触发泛化词拓展流程。


更新日志

v1.1.1

  • 与原版执行逻辑对齐校验:补回固定话术、筛选步骤、卡片示例、自检原文及「拓展=逗号多词」等约束,避免重构引入歧义

v1.1.0

  • 参照模板重构文档结构(简介 / 场景 / 指南 / 架构 / FAQ)
  • 合并重复的数据说明与展示要求,修正泛化词示例代码块格式

v1.0.0

  • 爆款探测、泛化词治理、筛选与双形态展示、细分推荐与自检清单

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 Gzh Explosive Content Detector AI skill do?

为公众号文章创作打造的专业数据洞察工具。全网持续收录每日爆款文章,收录依据:低粉高阅读、阅读靠前、数据增长中、原创靠前,助力号主获取数据参考。

Why use Gzh Explosive Content Detector on TypingMind?

Because you install it once and use it with any model. Gzh Explosive Content Detector 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 Gzh Explosive Content Detector in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SpaceZephyr/creator-buddy/tree/main/gzh-Skills/gzh-explosive-content-detector. 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 Gzh Explosive Content Detector?

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 Gzh Explosive Content Detector?

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

Is the Gzh Explosive Content Detector AI skill free?

It is published on GitHub by SpaceZephyr. 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 👇