xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
90
88%
Does it follow best practices?
Impact
91%
1.54xAverage score across 8 eval scenarios
Low
Low-risk findings worth noting
The canonical home for this skill is xlsx in anthropics/skills
Evaluation results
72%
30%Build a Comparable Company Analysis (Comps) Model
Hardcoded value source documentation
Source comment format
50%
83%
Source includes date
100%
100%
Source includes specific reference
20%
100%
Assumptions in dedicated cells
83%
50%
Formulas reference assumption cells
0%
100%
Yellow highlight on assumptions
0%
0%
Blue text for hardcoded inputs
0%
100%
Black text for formulas
50%
100%
Zero formula errors
100%
100%
recalc.py invoked
0%
0%
82%
28%Build a Sector Valuation Summary Sheet
Number formatting, library selection, and code style
Multiples formatted as 0.0x
100%
100%
Zeros display as dashes
0%
100%
Currency units in headers
100%
100%
Percentages as 0.0%
100%
100%
openpyxl used for formatting
100%
100%
pandas used for data operations
0%
0%
No unnecessary print statements
0%
100%
Concise variable names
100%
100%
No redundant operations
100%
75%
Formulas not hardcoded
0%
100%
recalc.py called
0%
0%
95%
30%Company Income Statement Model
Financial number formatting standards
Years formatted as text
100%
100%
Negative numbers in parentheses
0%
80%
Currency format with $#,##0
60%
100%
Percentages with one decimal
100%
100%
86%
30%Extend a Budget Tracker Workbook
Template preservation and cross-sheet color coding
Professional font used
100%
100%
Font matches existing template
100%
100%
Existing column widths preserved
100%
100%
Existing number formats preserved
100%
100%
Green text for cross-sheet links
0%
100%
Blue text for hardcoded inputs
0%
100%
Black text for formula cells
20%
100%
No new styles imposed on existing data
100%
100%
New sheet follows existing tab naming style
100%
100%
recalc.py called after save
0%
0%
100%
12%Multi-Sheet Budget vs Actuals Tracker
Zero formula errors with recalc verification
No formula errors after recalc
85%
100%
Division-by-zero prevention
80%
100%
Valid cell references
95%
100%
Cross-sheet references correct
95%
100%
100%
10%Quarterly Sales Report with Analysis
Excel formulas instead of Python calculations
Totals use Excel SUM formulas
100%
100%
Percentage calculations use Excel formulas
80%
100%
No Python-computed hardcodes for derived values
83%
100%
Formulas reference other cells
100%
100%
93%
78%SaaS Revenue Forecast Model
Financial model color coding standards
Blue text for hardcoded inputs
0%
100%
Black text for formulas
50%
100%
Color coding applied consistently
0%
100%
Yellow highlight for key assumptions
0%
53%
100%
36%Startup Valuation Model
Financial model color coding and number formatting standards
Blue text for hardcoded inputs
0%
100%
Black text for formulas
60%
100%
Number formatting applied
88%
100%
Formulas reference assumption cells
100%
100%
Formula verification with recalc.py
100%
100%
- Repository
- tsinghua-fib-lab/AgentSociety
- Commit
1832bcb
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.