florianbonnet14/ThePowerOfAnalytics_ClaudeSkills / influential-factors-detective
influential-factors-detective
VerifiedIdentify and analyze qualitative factors that influence KPIs but can't be measured as numbers. Use when users need to find non-quantifiable drivers affecting metrics (like copy quality, design aesthetics, timing), plan A/B tests for subjective elements, bridge the gap between data and design/content decisions, understand why quantitative analysis is incomplete, optimize messaging or UX elements, or identify the actual levers to pull for improving KPIs at the leaf nodes of a KPI tree.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.6 KB |
| influential-factor-detective-tutorial.md | markdown | 2.3 KB |
| references/case-studies.md | markdown | 16.8 KB |
| references/common-factors.md | markdown | 10.3 KB |
| references/templates.md | markdown | 6.7 KB |
influential-factor-detective-tutorial.md
View on GitHubThe influential factor detective is here to help you thoroughly find which are the elements of your operations and custoemr experience that can influence a certain KPI.
An easy example is the Subject Line of an email that will influence the Open Rate of that email.
To know more about Influential Factors, I recommend you to read the dedicated chapter of my book The Power of Analytics.
# Getting Started
To get started, open Claude Code and type the `/influential-factors-detective` command.
the Detective will ask you questions abou the KPI you want to focus on.
If you have a KPI Tree markdown file built with the KPI Tree Architect, you can refer to it directly.
<img width="891" height="551" alt="influential 1" src="https://github.com/user-attachments/assets/1ebc8d25-40d3-4392-bf47-e3ab930e5cd3" />
# Zeroing in on Influential Factors
In the example below, the Detective will use the context of the work done previously in defining the KPI Tree to ask further questions.
<img width="891" height="540" alt="influential 3" src="https://github.com/user-attachments/assets/13cb451b-10a2-4b5f-b800-84e49272df63" />
In this example we converge very fast and the Detective is ready to give us a full list of Factors as well as prioritization on which to focus on first to impact the KPI's value.
| | |
|:-------------------------:|:-------------------------:|
|<img width="881" height="544" alt="influential 4" src="https://github.com/user-attachments/assets/eccbef4a-c3c8-455c-bd15-db0c09174a6d" />|<img width="884" height="543" alt="influential 5" src="https://github.com/user-attachments/assets/c617b388-0028-4b0e-b748-8c4a151ebbed" />|
| <img width="877" height="543" alt="influential 6" src="https://github.com/user-attachments/assets/4070f77e-d41d-4347-9e03-5f85614f1cdf" />|<img width="882" height="761" alt="influential 7" src="https://github.com/user-attachments/assets/89abeec0-2f90-4e8c-a6fa-44fc13df7415" />
|
Note that you can discuss about nay factor, challenge them or propose new one - this is a collaborative work!
# Saving your work
Like with all the skills, you can save your work in a markdown file by asking Claude to do so.
The file will contain the elements printed in the Terminal.
<img width="1041" height="778" alt="influential file" src="https://github.com/user-attachments/assets/9a648ada-5336-406b-823e-ddedfb602246" />
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |