pi-excel-hygiene

Review Excel files for spreadsheet errors — mechanical checks (openpyxl) + Panko–Halverson taxonomy reasoning

Packages

Package details

extension

Install pi-excel-hygiene from npm and Pi will load the resources declared by the package manifest.

$ pi install npm:pi-excel-hygiene
Package
pi-excel-hygiene
Version
1.0.2
Published
Jul 14, 2026
Downloads
398/mo · 398/wk
Author
wwyxin
License
Apache-2.0
Types
extension
Size
17.9 KB
Dependencies
0 dependencies · 3 peers
Pi manifest JSON
{
  "extensions": [
    "./index.ts"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

pi-excel-hygiene

A rigorous "second pair of eyes" on any .xlsx before it goes out — as a Pi extension.

Based on the excel-hygiene skill by Empatika Labs. Uses the Panko–Halverson (2008) spreadsheet-error taxonomy.

Install

pip install openpyxl>=3.1    # Required
pi install npm:pi-excel-hygiene

Then reload Pi (/reload).

Usage

As a tool (LLM auto-calls)

Just ask: "check this excel file for errors", "audit this spreadsheet", "review this xlsx".

As a command

/excel-hygiene path/to/file.xlsx

Mechanical checks

Check What it flags
Number as text Numeric value stored as string → SUM silently skips it
Number over formula Static number in a formula column → may have been overwritten
Cell error #DIV/0! / #REF! / … literals and division by zero
Truncated SUM SUM stops before last data row → row may be dropped
Percent as whole number Value > 1 in a % column → off by 100×

Beyond the script

After mechanical checks, the LLM uses the full Panko–Halverson taxonomy to reason further:

  • Violations vs Errors
  • Qualitative vs Quantitative
  • Mistakes / Slips / Lapses
  • Life-cycle stage analysis

Output format: sheet · cell · class · confidence · materiality · what's wrong

Requirements

  • Python 3 + openpyxl>=3.1 (pip install openpyxl)
  • Pi coding agent

Source

本扩展基于 BayramAnnakov/excel-hygiene 移植为 Pi 扩展。

  • 原始作者:BayramAnnakov (Empatika Labs)
  • 原始许可证:Apache-2.0
  • 错误分类框架:Panko–Halverson (2008)

License

Apache-2.0