Info Funnel logo

Info Funnel

OrganizationPopular
nexu-io
info-funnel

3-6 阶递减漏斗, 突出转化率 / 筛选比例 / 流量损耗。竖图适合 IG Story / 小红书

Overview

Publishernexu-io
Repositoryhtml-anything
Skill nameinfo-funnel
Stars
8.9K
Forks
861
Bundled files
2
LicenseApache-2.0
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.

  • 2 bundled files

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

  • Open source

    Published by nexu-io on GitHub. Read the source before you install it.

Installation

Install the Info Funnel 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/nexu-io/html-anything.git /tmp/html-anything
mkdir -p .claude/skills
cp -r /tmp/html-anything/next/src/lib/templates/skills/info-funnel .claude/skills/info-funnel
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Info Funnel 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 Info Funnel 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 Info Funnel 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.

【模板: 漏斗信息图(Funnel Infographic)】

【意图】把"从大到小"的转化 / 筛选 / 损耗过程一眼看清。宽顶(输入)→ 窄底(结果), 每一阶有明确的"剩多少"和"漏多少"。典型场景:marketing funnel(曝光→点击→注册→付费)、招聘漏斗(投递→面试→录用→入职)、决策漏斗(候选→筛选→敲定)。

【数据形态】

输入应是有序的 3-6 个阶段 + 每阶的绝对数值(人数 / 件数 / 金额)。可选每阶名称、说明、单位。若用户只给了百分比, 默认顶端 = 100% / 10000 人。

阶段 1: 100,000 名访客
阶段 2:  18,500 名注册(18.5%)
阶段 3:   6,200 名启动试用(33.5%)
阶段 4:   1,450 名转付费(23.4%)
阶段 5:     920 名 30 天留存(63.4%)

【布局规则】

区域内容占比
Hero 顶部(约 15%)标题(≤ 20 字, 22-32px CJK)+ 副标题 / 时间窗口(灰色 14-16px)上 15%
漏斗主体(约 65%)3-6 个梯形 stage, 每段含:左大数字(48-72px tabular-nums)+ 右阶段名(18-22px bold)+ 右二行说明(13-15px 灰)+ 段间小箭头标转化率中 65%
底部 stat strip(约 20%)累计转化率(最大字号 80-120px)+ 1-2 句洞察文本(漏出最严重的环节 / 关键提示)下 20%

【漏斗实现】

CSS clip-path: polygon() 切梯形, 不用 SVG:

  • 每段 stage 是一个 <div>, 设固定 height(120-200px)+ 不同 clip-path
  • clip-path 的左右收缩量 = 50% × (1 - bottom_width_ratio), 累计每段比上一段窄
  • 每段背景色用同一 hue 不同 lightness, 顶端最饱和, 底端最深(accent → ink)
  • 阶段之间有 4-8px gap, 让"流动"感更明显
  • 数字用 font-variant-numeric: tabular-nums, letter-spacing -0.02em

【主题色 — 三选一, 不许混】

主题适用顶端底端inkpaper
klein-blue(默认)商业 / SaaS / AI 产品#4F7BD8#002FA7#0A0A0A#FAFAF8
sunset-amber零售 / 消费 / 餐饮#FBB040#C73E1D#0A0A0A#FFF8EC
deep-forest招聘 / 教育 / 健康#56A06E#1F4D2E#0A0A0A#F4F0E6

文字色:

  • 漏斗内部数字与名字一律白色(#FFFFFF
  • 顶端 / 副标题 / 底部 strip 用 ink(#0A0A0A
  • 灰色辅助文字:rgba(10,10,10,0.55)

【字体栈】

"PingFang SC", "Heiti SC", "Helvetica Neue", "Arial", -apple-system, sans-serif

数字(tabular-nums 必须):

"SF Mono", "JetBrains Mono", "Menlo", "Roboto Mono", monospace

禁用 Inter —— 它太"AI 默认味"。优先 PingFang SC(CJK)+ Helvetica Neue(拉丁)。

【字号 / 间距锁死】

  • 主标题:clamp(28px, 2.8vw, 36px) font-weight 800 letter-spacing -0.02em
  • 副标题:14-16px font-weight 500 ink/0.6
  • 段内大数字:clamp(48px, 5.5vw, 72px) tabular-nums font-weight 900 white
  • 段内阶段名:20-22px font-weight 700 white
  • 段内说明:13-15px font-weight 400 white/0.85
  • 段间转化率徽章:13px font-weight 700, paper 底 ink 字, 圆角 6px, padding 2px 8px
  • 底部累计大数字:clamp(80px, 12vw, 120px) font-weight 900 ink letter-spacing -0.04em
  • 底部洞察:16-18px font-weight 500 ink/0.75 max-width 80%
  • 整体 padding:6vmin 7vmin
  • 段间 gap:6px
  • Hero 与漏斗之间 gap:32-48px
  • 漏斗与 strip 之间 gap:48-64px

【输出契约】

输出单文件 HTML, inline CSS, 不写 JS(静态图)。不外链 CDN / 图标库 / 字体文件

  • 不放图标 / 不用 emoji 装饰(漏斗本身就是图)
  • 不放图表(饼图 / 柱状图)—— 一篇一个漏斗
  • 不放公司 logo
  • background 是 paper, 整张图占满 viewport
  • aspect-ratio: 9 / 16 锁定容器, 内容用 flex column 填充

【数据规范】

  • 顶端数 = 100% 基准
  • 每阶转化率 = 当前段 / 上一段
  • 累计转化率 = 末段 / 顶段
  • 数字千分位用半角逗号(10,000 不要 10000)
  • 百分比保留 1 位小数(18.5% 不要 18.50% 也不要 19%)
  • 单位(人 / 件 / $)放在数字后, 13-15px 灰色
  • 编绝对数比写百分比更有说服力("少了 81,500 人"比"漏掉 81.5%"更扎心)

【洞察文本(底部 strip)】

1-2 句, 总长 ≤ 60 字:

  • 第一句:累计数字 + 评价("100,000 个访客中, 只剩 920 个真正留下")
  • 第二句(可选):指出最大漏出环节("最大流失在『访客→注册』, 81.5% 在第一步就走了")

禁止 AI 文案腔("通过本图表可以看出"、"由此可见"、"综上所述")。直接说事实。

【分阶段视觉宽度计算】

5 阶时, top_width=100%, bottom_width=30%(漏斗收口)。每段 bottom_width 比上一段窄 (100-30)/5 = 14%。例如:

  • Stage 1: top 100% → bottom 86%
  • Stage 2: top 86% → bottom 72%
  • Stage 3: top 72% → bottom 58%
  • Stage 4: top 58% → bottom 44%
  • Stage 5: top 44% → bottom 30%

clip-path 公式(每段独立 div):

css
clip-path: polygon(
  {(100-top)/2}% 0%,
  {100-(100-top)/2}% 0%,
  {100-(100-bottom)/2}% 100%,
  {(100-bottom)/2}% 100%
);

3-4 阶时收口可以放宽到 40-45%, 6 阶时压到 22-25%

【禁区】

  • 不要在漏斗段内画图标 / 插画
  • 不要把数字放在段右、名字放在左(要左数字 / 右名字, 形成视觉重力)
  • 不要让段高度跟数值挂钩(这是 funnel 不是 H-bar chart, 信息密度靠宽度收缩传达)
  • 不要让漏斗居中悬浮——它该填满中段, 顶部贴 Hero, 底部贴 strip
  • 不要超过 6 阶(信息过载, 拆成两张图)
  • 不要 3D / 阴影 / 发光(platine 干净版式)
  • 不要 Inter 字体(见上)
  • 不要写"以下是漏斗"、"如下图所示"之类的 meta 文字

【致谢】 本 skill 设计参考 baoyu-skills · baoyu-infographic 的 funnel layout 规范, 视觉补完 + HTML 实现由 html-anything 独立编写。

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 Info Funnel AI skill do?

3-6 阶递减漏斗, 突出转化率 / 筛选比例 / 流量损耗。竖图适合 IG Story / 小红书

Why use Info Funnel on TypingMind?

Because you install it once and use it with any model. Info Funnel 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 Info Funnel in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nexu-io/html-anything/tree/main/next/src/lib/templates/skills/info-funnel. 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 Info Funnel?

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 Info Funnel?

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

Is the Info Funnel AI skill free?

Yes. It is published on GitHub by nexu-io under the Apache-2.0 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 👇