gitwtfhub

wtf is business-analysis-learning-agent-skill?

ysx12138/business-analysis-learning-agent-skill — explained in plain English

Analysis updated 2026-05-18

20PythonAudience · dataComplexity · 2/5Setup · moderate

TL;DR

A Python tool that walks business students through analyzing a CSV or Excel file step by step, explaining the business meaning of each field and producing Excel, HTML, PDF, and JSON audit reports without any machine learning.

Mindmap

mindmap
  root((business-analysis-agent))
    Input
      CSV or Excel file
      Field name inspection
      Metric library matching
    Analysis steps
      Ranking analysis
      Trend analysis
      Distribution analysis
    Outputs
      Excel workbook charts
      HTML browser report
      PDF report
      JSON audit log
    Usage modes
      Claude Code adapter
      ChatGPT or Gemini
      Standalone CLI

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Upload a retail sales CSV and get an automatically explained report showing what each column means and which business metrics it supports

REASON 2

Run the standalone CLI command to produce a beginner-friendly summary or full audit report from any spreadsheet without an AI agent

REASON 3

Use as an agent skill inside Claude Code or ChatGPT to interactively guide a non-technical colleague through understanding their own business data

What's in the stack?

PythonExcelHTMLPDFJSON

How it stacks up

ysx12138/business-analysis-learning-agent-skillalex72-py/aria-termuxanime0t4ku/gentleman
Stars202020
LanguagePythonPythonPython
Setup difficultymoderatemoderatemoderate
Complexity2/52/52/5
Audiencedatadevelopergeneral

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · moderate Time to first run · 30min

Project README and user-facing text are in Chinese, familiarity with Chinese or a translation tool is helpful when reading the documentation.

No license information is stated in the repository.

Wtf does this do

This is a Python-based tool designed to help business students and data analysis beginners learn how to analyze real datasets, not just see the results. The project is written primarily in Chinese and intended for Chinese-speaking learners, but the code and pipeline architecture are language-agnostic. You provide a CSV or Excel file, and the tool walks through an analysis while explaining the thinking at each step: what each data field likely means, which business metrics can be calculated from the available columns, and what the findings do and do not prove. The analysis pipeline runs in a fixed sequence: it reads the data, inspects field names to guess their business meaning, matches those fields against a library of common metrics (things like click-through rate, average order value, or profit margin), then runs ranking, trend, and distribution analysis. Each step is rule-driven and auditable. The tool explicitly is not a machine learning system and does not fit statistical models automatically. It stays in the territory of descriptive business analysis, which is appropriate for the audience. After each run, the tool produces four types of output: an Excel workbook with charts and a dashboard, an HTML report designed for reading in a browser, a PDF version of that same report, and a JSON audit log that records what was executed, what was skipped, and why. These files are meant to be kept and reviewed later, not just read once during the session. The project can be used through Claude Code (via a .claude/ adapter), Claude desktop or web, ChatGPT, or Gemini. It packages its behavior as an agent skill file, so any AI assistant that can read instruction files can follow the same workflow. The command-line tool also works standalone without an AI agent: one Python command with an input path and an output mode (beginner summary, standard report, or audit report). Sample outputs for a retail sales dataset and a multi-table dataset are included in the repo so you can see what the Excel, PDF, and audit log look like before running anything yourself. The project README and all user-facing text default to Chinese.

Yoink these prompts

Prompt 1
I have a CSV with columns: date, product_id, units_sold, revenue, region. Use the ysx12138/business-analysis-learning-agent-skill approach to identify which business metrics I can calculate and run a ranking and trend analysis on it.
Prompt 2
Walk me through what the JSON audit log produced by business-analysis-learning-agent-skill records, and how I can use it to reproduce or explain an analysis to a stakeholder.
Prompt 3
I want to add a new metric to the metric library in business-analysis-learning-agent-skill, customer lifetime value. Show me the exact format to register it so the pipeline picks it up automatically.
Prompt 4
Using the beginner-summary output mode of business-analysis-learning-agent-skill, explain how it decides which findings to include and which to skip for a non-technical audience.

Frequently asked questions

wtf is business-analysis-learning-agent-skill?

A Python tool that walks business students through analyzing a CSV or Excel file step by step, explaining the business meaning of each field and producing Excel, HTML, PDF, and JSON audit reports without any machine learning.

What language is business-analysis-learning-agent-skill written in?

Mainly Python. The stack also includes Python, Excel, HTML.

What license does business-analysis-learning-agent-skill use?

No license information is stated in the repository.

How hard is business-analysis-learning-agent-skill to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is business-analysis-learning-agent-skill for?

Mainly data.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.