← 返回
未分类 中文

Spillover Estimator

Estimate whether one commerce channel is creating measurable spillover into another channel using simple exports, campaign timing, and directional evidence....
利用简单导出数据、营销活动时间节点及方向性证据,评估某一商业渠道是否对其他渠道产生可量化的溢出效应。
leooooooow leooooooow 来源
未分类 clawhub v1.0.0 1 版本 100000 Key: 无需
★ 0
Stars
📥 415
下载
💾 0
安装
1
版本
#latest

概述

Spillover Estimator

Estimate cross-channel spillover without pretending to prove perfect attribution.

Skill Card

  • Category: Measurement
  • Core problem: Did growth in one channel also lift another channel?
  • Best for: Operators comparing TikTok, Amazon, DTC, creator, paid, and marketplace channel effects
  • Expected input: Source channel data + downstream channel data + timing context
  • Expected output: Directional spillover estimate + confidence note + action recommendation
  • Creatop handoff: Feed findings into budget allocation and channel planning

Before you run

Ask the user to clarify:

  • source channel to evaluate
  • downstream channel(s) to check for spillover
  • date range
  • major campaign or promo dates
  • whether they have exports, screenshots, or CSV data

If structured data is missing, say the result will be directional, not causal proof.

Optional tools / APIs

Useful but not required:

  • Shopify / WooCommerce export
  • Amazon sales export
  • TikTok Shop export
  • ad platform export
  • Google Sheets / CSV

If the user does not have APIs connected, ask for manual exports first instead of blocking the workflow.

Workflow

  1. Confirm channel scope and time window.
  2. Collect source-channel change signals.
  3. Collect downstream-channel change signals.
  4. Align timing around campaigns, creator drops, content bursts, or promo windows.
  5. Judge whether the downstream lift looks:
    • likely related
    • weak / mixed
    • insufficient evidence
  6. Explain the estimate with honest caveats.

Output format

Return in this order:

  1. Executive summary
  2. Spillover estimate
  3. Evidence blocks
  4. Confidence and caveats
  5. Recommended next step

Fallback mode

If the user only has weekly snapshots, rough screenshots, or partial exports:

  • use simple directional comparison
  • do not claim causal attribution
  • clearly label missing data and confidence limits

Quality rules

  • Never overclaim causality from timing alone.
  • Prefer directional clarity over fake precision.
  • Separate channel correlation from verified lift.
  • Make the user’s next measurement step obvious.

License

Copyright (c) 2026 Razestar.

This skill is provided under CC BY-NC-SA 4.0 for non-commercial use.

You may reuse and adapt it with attribution to Razestar, and share derivatives

under the same license.

Commercial use requires a separate paid commercial license from Razestar.

No trademark rights are granted.

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-03-30 23:14 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

data-analysis

Data Analysis

ivangdavila
{"answer":"数据分析与可视化。查询数据库、生成报告、自动化电子表格,将原始数据转化为清晰可行的见解。适用于:(1) 您……"}
★ 211 📥 70,408
data-analysis

Tavily 搜索

jacky1n7
通过 Tavily API 进行网页搜索(Brave 替代方案)。当用户要求搜索网页、查找来源或链接,且 Brave 网页搜索不可用时使用。
★ 275 📥 101,114
data-analysis

AdMapix

fly0pants
AdMapix 原始数据层,提供广告创意、应用、排名、下载/收入及市场元数据。返回 AdMapix API 的结构化 JSON;调用方...
★ 297 📥 142,305