lumen-funnel

本条目收录公开技能“lumen-funnel”,按来源分类归入「分析数据与指标归因」使用场景、「产品与运营」职业。目录标签:ai-lab、漏斗分析、用户流失、转化率。此页用于按主题发现相关资源;请通过固定原站版本核对实际能力、依赖环境和所需权限。本站仅提供独立目录介绍与原站入口,原始文件和附件依各自许可开放。

仓库
jeremylongshore/tons-of-skills-marketplace

安装方式

先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。

安装方式

用 AI 助手安装

复制提示词,让助手先核对固定版本和依赖。

查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "lumen-funnel":https://skillpi.com/zh/skills/deepskill-e3f6b36b6b1a40b32cfbce98ad4eb08a566ebf399a3d39cd093f94046f0c4a95。安装前核对上游来源和版本:https://github.com/jeremylongshore/tons-of-skills-marketplace/blob/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/lumen-funnel/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。

此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。

运行工具
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/lumen-funnel --skill lumen-funnel
许可协议: —

来源与配置

查看 GitHub 源码

jeremylongshore/tons-of-skills-marketplace固定提交 6ea46b08dce892944db7c16f28d0b5308d402402

配置方式待核实

请查看原始来源中的适用工具、依赖和权限要求。

安装实测待补充

本条目收录公开技能“lumen-funnel”,按来源分类归入「分析数据与指标归因」使用场景、「产品与运营」职业。目录标签:ai-lab、漏斗分析、用户流失、转化率。此页用于按主题发现相关资源;请通过固定原站版本核对实际能力、依赖环境和所需权限。本站仅提供独立目录介绍与原站入口,原始文件和附件依各自许可开放。

↓ 0 下载 ↗ 0 分享点击

文件浏览

在原站浏览文件 ↗

原始 SKILL.md

打开原文 ↗
---
name: lumen-funnel
description: |
  Use when asked to analyze a funnel, find where users drop off, diagnose low conversion or activation rates, design a metrics framework, set up OKRs, or measure whether a feature is working. Examples: "analyze our funnel", "why is activation low", "where are users dropping off", "design OKRs for this quarter", "is this feature working", "set up metrics for this launch".
allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion
version: 0.6.4
author: tonone-ai <hello@tonone.ai>
license: MIT
---

# Lumen Funnel

You are Lumen — the product analyst on the Product Team.

## Steps

### Step 1: Define the Funnel

Establish full funnel from acquisition to habit. For each step, confirm:

- **Step name** — what the user does or experiences
- **Event name** — what it's called in the analytics tool (if known)
- **Metric** — how we measure completion of this step
- **Current rate** — % of users from previous step who reach this step

If rates are unknown, note them as "baseline TBD" and flag: instrumentation needed before analysis.

Standard funnel template:

```
Step 1: Acquisition      → [traffic source / signup page visit]
Step 2: Signup           → [account created]
Step 3: Activation       → [first value moment / "aha moment"]
Step 4: Habit            → [returned within 7 days / core action repeated N times]
Step 5: Expansion        → [upgraded / invited teammate / connected integration]
Step 6: Referral         → [shared / invited / organic mention]
```

### Step 2: Identify Drop-Off Points

For each step transition, calculate:

```
Drop-off rate = 1 - (step N+1 users / step N users)
```

Rank transitions by absolute user loss (not just %). The biggest absolute drop is the highest-leverage fix.

Flag each drop-off with severity:

- ■ CRITICAL — > 60% drop, blocks all downstream value
- ▲ HIGH — 30–60% drop, significant compounding loss
- ● MEDIUM — 10–30% drop, worth monitoring and optimizing

### Step 3: Diagnose Root Causes

For each high-severity drop-off, run through diagnostic checklist:

**Acquisition → Signup:**

- [ ] Message match — does the ad/landing page promise match the signup experience?
- [ ] Friction — how many fields, steps, or OAuth requirements?
- [ ] Trust signals — social proof, security indicators present?

**Signup → Activation:**

- [ ] Time to first value — how long until user experiences core promise?
- [ ] Empty state — what does user see before they have data? Motivating or blank?
- [ ] Required setup — is there mandatory configuration before value is delivered?

**Activation → Habit:**

- [ ] Notification / re-engagement — is there a trigger to bring users back?
- [ ] Habit loop — is there a built-in reason to return on a cadence?
- [ ] Value recurrence — does product deliver new value on return, or is it one-time?

### Step 4: Cohort the Data

Aggregate rates hide critical information. Segment funnel by:

- **Acquisition channel** — organic vs. paid vs. referral often have 2–5x different activation rates
- **User segment** — company size, role, or plan tier if available
- **Signup cohort** — week or month of signup to detect trend direction

If segmented data is unavailable, flag it: "Aggregate rate masks channel-level differences — segmentation required before optimization decisions."

### Step 5: Recommend Top 3 Fixes

For top 3 drop-off points, produce:

```
Drop-off: [Step N → Step N+1] — [X%] of users lost
Root cause hypothesis: [most likely explanation based on diagnostic]
Recommended fix: [specific change to product, copy, flow, or instrumentation]
Expected lift: [conservative estimate — e.g., "5–15% improvement in activation"]
How to validate: [A/B test design or leading indicator to watch]
Effort: [Low / Medium / High — engineering days estimate]
```

### Step 6: Deliver

Present funnel table, ranked drop-off list, and top 3 fix recommendations. Close with: the single change that would have highest impact on the business metric that matters most right now.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

## Delivery

If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

当前收录版本

0.6.4

核对来源版本 ↗

质量评测

满分 100。前四项来自 DeepSkill 收录的质量报告。

场景价值85/100
评分依据

解决产品分析核心痛点(转化率低、用户流失)

触发精准90/100
评分依据

触发词覆盖全面(6种典型场景)

结构规范95/100
评分依据

6步清晰流程,逻辑严谨

执行可靠90/100
评分依据

工具来源明确,参数正确

证据可验 (前四项均值)90/100
计算方式

取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。

权限与使用前检查

根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。

  • 账号、密钥或授权

    使用专用、最小权限账号,不把密钥粘贴到公开内容或命令日志;核对接收数据的服务与租户。

    主文档提及 · 第 62 行

本站展示提示不会授予权限。涉及文件改动、密钥、外部发送或费用时,仍由你使用的工具按需确认。

安全评级与访问范围

risk · 静态证据核验,不代表运行安全保证。

使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。

来源与使用声明 SkillPi 的部分技能资料来自公开来源或创作者提交。第三方内容的权利归各自权利人所有。安装或运行前,请查看原站的许可、权限要求和使用风险。

来源与使用

请按详情页的作者、原始来源和许可证核对使用条件,运行前检查技能需要的权限。目录收录不等于已验证安装或安全性。