dynamic-percentage-and-large-file-analysis

Compute dynamic percentages from uploaded Excel datasets and generate .xlsx summaries with charts.

2|Updated May 19, 2026
One-click install
npx skills add https://github.com/aiyinluya/SenseNova-Skills-Studio --skill dynamic-percentage-and-large-file-analysis-aiyinluya
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dynamic-percentage-and-large-file-analysis
Source: https://github.com/aiyinluya/SenseNova-Skills-Studio/tree/main/skills/sn-da-excel-workflow/capability/excel-data-statistics/percentage-calculation
Command: npx skills add https://github.com/aiyinluya/SenseNova-Skills-Studio --skill dynamic-percentage-and-large-file-analysis-aiyinluya

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you calculate key ratios and descriptive statistics from Excel-like tabular data by dynamically detecting the relevant fields and extracting indicator values, then producing a structured Excel output with visuals.

Core Features & Use Cases

  • Dynamic field discovery: Locates the target category column by scanning header names and then selects rows that match a specific category value.
  • Keyword-driven indicator extraction: Scans rows to find indicator-associated numeric values (e.g., positive numbers tied to “指标A/指标B” patterns) for robust ratio computation.
  • Output-ready reporting: Writes a summarized .xlsx file and generates a high-resolution chart (e.g., pie chart) to visualize the computed percentage.
  • Use Case: You have a messy quarterly dataset where the relevant category column name can vary. Use this skill to automatically compute the percentage between two key indicators for the target category and generate both the Excel summary and a chart for stakeholders.

Quick Start

Ask the AI to compute the percentage between 指标A and 指标B for the specified category from your uploaded analysis table, save the results as output_analysis_result.xlsx, and generate percentage_chart.png.

Frequently Asked Questions about dynamic-percentage-and-large-file-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I calculate dynamic percentages from Excel data when column names vary?

To calculate dynamic percentages from Excel data, this skill scans header names to detect the target category column and extracts keyword-linked indicator values. It filters rows by category, coerces numeric values, computes ratios, and generates a structured Excel output with charts.

Can I generate a pie chart from Excel tabular data with Chinese font support?

Yes, you can generate a pie chart from Excel tabular data with Chinese font support. The skill creates high-resolution chart visualizations alongside the summarized Excel report, ensuring Chinese characters render correctly in the output chart image.

How do I compute summary statistics and ratios from a messy quarterly dataset?

You can compute summary statistics and ratios from a messy quarterly dataset by uploading the file and specifying the target category and indicators. The skill dynamically locates relevant fields, extracts numeric values, and derives means and ratios for stakeholder reporting.

Does this tool support parquet conversion for large file analysis workflows?

This tool processes uploaded tabular datasets for percentage calculation and summary statistics. While parquet conversion is listed as a related capability, the core function focuses on Excel data analysis, numeric coercion for aggregation, and generating Excel and chart outputs.

What is the best way to automate report generation for indicator percentage analysis?

The best way to automate report generation for indicator percentage analysis is to use this skill's keyword-driven extraction. It scans rows for indicator-associated numeric values, computes dynamic percentages, and writes a ready-to-use Excel summary with a visual chart.

Why does my Excel analytics workflow fail when category column names change between files?

Excel analytics workflows fail with changing column names because static scripts cannot locate the target field. This skill solves that by dynamically scanning header names to discover the category column, ensuring robust ratio computation across varying dataset structures.