Create and manipulate Excel XLSX files programmatically. Use when the user needs to generate spreadsheets, modify XLSX templates, extract spreadsheet content, or automate Excel workflows. Supports both template-based generation (for branding compliance) and from-scratch creation. Keywords: Excel, XLSX, spreadsheet, workbook, worksheet, data, report, template, financial, analysis.
npx skills add https://github.com/jwynia/agent-skills --skill xlsx-generator
Use this skill when:
{{TITLE}} or ${date} in cellsDo NOT use this skill when:
{{PLACEHOLDERS}} with actual valuesExtract cell inventory to understand what can be replaced:
deno run --allow-read scripts/analyze-template.ts financial-template.xlsx > inventory.json
Output (inventory.json):
{
"filename": "financial-template.xlsx",
"sheetCount": 3,
"sheets": [
{
"name": "Summary",
"rowCount": 25,
"colCount": 8,
"usedRange": "A1:H25",
"cells": [
{ "address": "A1", "row": 1, "col": 1, "value": "{{REPORT_TITLE}}", "type": "string" },
{ "address": "B3", "row": 3, "col": 2, "value": "{{DATE}}", "type": "string" },
{ "address": "C5", "row": 5, "col": 3, "value": null, "type": "number", "formula": "SUM(C6:C20)" }
]
}
],
"placeholders": [
{ "tag": "{{REPORT_TITLE}}", "location": "Summary!A1", "sheet": "Summary", "address": "A1" },
{ "tag": "{{DATE}}", "location": "Summary!B3", "sheet": "Summary", "address": "B3" }
],
"hasFormulas": true
}
Create replacements.json:
{
"textReplacements": [
{ "tag": "{{REPORT_TITLE}}", "value": "Q4 2024 Financial Report" },
{ "tag": "{{DATE}}", "value": "December 15, 2024" },
{ "tag": "{{COMPANY}}", "value": "Acme Corporation", "sheets": ["Summary", "Cover"] }
],
"cellUpdates": [
{ "sheet": "Data", "address": "B5", "value": 1250000 },
{ "sheet": "Data", "address": "B6", "value": 750000 }
]
}
deno run --allow-read --allow-write scripts/generate-from-template.ts \
financial-template.xlsx replacements.json output.xlsx
Create spec.json:
{
"title": "Sales Report",
"author": "Finance Team",
"sheets": [
{
"name": "Sales Data",
"data": [
["Product", "Q1", "Q2", "Q3", "Q4", "Total"],
["Widget A", 10000, 12000, 15000, 18000, null],
["Widget B", 8000, 9000, 11000, 13000, null],
["Widget C", 5000, 6000, 7000, 8000, null]
],
"cells": [
{ "address": "F2", "formula": "SUM(B2:E2)" },
{ "address": "F3", "formula": "SUM(B3:E3)" },
{ "address": "F4", "formula": "SUM(B4:E4)" }
],
"columns": [
{ "col": "A", "width": 15 },
{ "col": "B", "width": 10 },
{ "col": "C", "width": 10 },
{ "col": "D", "width": 10 },
{ "col": "E", "width": 10 },
{ "col": "F", "width": 12 }
],
"freezePane": "A2",
"autoFilter": "A1:F4"
}
]
}
deno run --allow-read --allow-write scripts/generate-scratch.ts spec.json output.xlsx
Scenario: Generate a monthly sales report from template.
Steps:
# 1. Analyze template for replaceable content
deno run --allow-read scripts/analyze-template.ts sales-template.xlsx --pretty
# 2. Create replacements.json with monthly data
# 3. Generate report
deno run --allow-read --allow-write scripts/generate-from-template.ts \
sales-template.xlsx replacements.json November-Sales.xlsx
Scenario: Create a spreadsheet with calculated totals.
spec.json:
{
"sheets": [{
"name": "Expenses",
"data": [
["Category", "January", "February", "March", "Total"],
["Office", 1500, 1600, 1400, null],
["Travel", 3000, 2500, 4000, null],
["Software", 500, 500, 500, null],
["Total", null, null, null, null]
],
"cells": [
{ "address": "E2", "formula": "SUM(B2:D2)" },
{ "address": "E3", "formula": "SUM(B3:D3)" },
{ "address": "E4", "formula": "SUM(B4:D4)" },
{ "address": "B5", "formula": "SUM(B2:B4)" },
{ "address": "C5", "formula": "SUM(C2:C4)" },
{ "address": "D5", "formula": "SUM(D2:D4)" },
{ "address": "E5", "formula": "SUM(E2:E4)" }
]
}]
}
Scenario: Create a workbook with summary and detail sheets.
spec.json:
{
"title": "Q4 Report",
"sheets": [
{
"name": "Summary",
"data": [
["Department", "Budget", "Actual", "Variance"],
["Sales", 500000, 520000, null],
["Marketing", 200000, 195000, null]
],
"cells": [
{ "address": "D2", "formula": "C2-B2" },
{ "address": "D3", "formula": "C3-B3" }
]
},
{
"name": "Sales Detail",
"data": [
["Month", "Revenue", "Cost", "Profit"],
["October", 180000, 120000, null],
["November", 170000, 115000, null],
["December", 170000, 110000, null]
],
"cells": [
{ "address": "D2", "formula": "B2-C2" },
{ "address": "D3", "formula": "B3-C3" },
{ "address": "D4", "formula": "B4-C4" }
]
}
]
}
| Script | Purpose | Permissions |
|--------|---------|-------------|
| analyze-template.ts | Extract cells, formulas, placeholders from XLSX | --allow-read |
| generate-from-template.ts | Replace placeholders in templates | --allow-read --allow-write |
| generate-scratch.ts | Create XLSX from JSON specification | --allow-read --allow-write |
| Property | Type | Description |
|----------|------|-------------|
| name | string | Sheet name |
| data | array | 2D array of cell values starting at A1 |
| cells | array | Individual cell specifications |
| rows | array | Row-based data specifications |
| columns | array | Column width and visibility settings |
| merges | array | Merged cell ranges |
| freezePane | string | Freeze panes at this cell (e.g., "A2") |
| autoFilter | string | Auto-filter range (e.g., "A1:F10") |
| Property | Type | Description |
|----------|------|-------------|
| address | string | Cell address (e.g., "A1", "B2") |
| value | mixed | Cell value (string, number, boolean, null) |
| formula | string | Formula without = sign |
| format | string | Number format (e.g., "#,##0.00") |
| type | string | Force type: "string", "number", "boolean", "date" |
| Property | Type | Description |
|----------|------|-------------|
| col | string | Column letter (e.g., "A", "B", "AA") |
| width | number | Column width in characters |
| hidden | boolean | Hide column |
| Property | Type | Description |
|----------|------|-------------|
| tag | string | Placeholder to find (e.g., "{{TITLE}}") |
| value | mixed | Replacement value |
| sheets | array | Limit to specific sheets |
| range | string | Limit to cell range (e.g., "A1:D10") |
Symptoms: Output XLSX still contains {{PLACEHOLDER}} tags.
Solution:
analyze-template.ts to verify exact tag text and locationSymptoms: Formulas display as text instead of calculating.
Solution:
Symptoms: Numbers have green triangle indicating text storage.
Solution:
Symptoms: Columns have default width despite specification.
Solution:
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
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.
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
Take jwynia/xlsx-generator from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.