Diagnose and fix Microsoft Excel XLSX workbook issues involving formulas, named ranges, Power Query refreshes, pivot tables, VBA/macro preservation, workbook...
Documents
Office Open XML Automation Helper
Try itBuild and troubleshoot cross-Office automation pipelines that move content between Word, Excel, and PowerPoint using Open XML, VBA, python-docx, openpyxl, py...
What it does
Build and troubleshoot cross-Office automation pipelines that move content between Word, Excel, and PowerPoint using Open XML, VBA, python-docx, openpyxl, py...
The skill document
Office Open XML Automation Helper
Use this skill when the task crosses Office file types: extract Word tables into Excel, turn Excel results into PowerPoint slides, populate Word reports from spreadsheets, batch-convert Office files, or coordinate DOCX/XLSX/PPTX templates.
Workflow
- Define the pipeline: source files, destination files, templates, generated artifacts, batch size, and success criteria.
- Classify each operation:
- DOCX text, tables, styles, comments, headers, content controls.
- XLSX worksheets, tables, formulas, named ranges, charts, pivots, macros.
- PPTX slide masters, layouts, placeholders, charts, media, speaker notes.
- Preserve source packages. Work on copies and keep an audit trail of inputs, outputs, and record IDs.
- Choose the safest layer for each step:
python-docxfor supported Word document content.openpyxlfor supported Excel workbook structure.python-pptxfor supported slide content and basic charts.- Direct Open XML edits for relationships, unsupported features, and preserving package parts.
- VBA or Office desktop automation only when live Office behavior is required, such as field updates, Power Query refresh, PDF export, or chart rendering fidelity.
- Keep data transformations separate from document rendering. Normalize data first, then populate templates.
- Validate each artifact independently, then validate the whole chain.
Design Rules
- Do not use plain string replacement inside zipped Office XML unless escaping, run boundaries, relationships, and namespaces are understood.
- Preserve relationship IDs and content types when copying media, charts, embedded workbooks, or custom XML parts.
- Avoid saving
.xlsmor macro-enabled packages through a library path that strips macros. - Prefer named ranges, content controls, placeholders, and template fields over positional guesses.
- Log generated filenames, input records, warnings, skipped records, and validation totals.
Validation
Check:
- DOCX page structure, styles, headers/footers, tables, fields, comments, and tracked changes.
- XLSX formulas, named ranges, tables, charts, macros, hidden sheets, and recalculation requirements.
- PPTX slide count, layout assignment, placeholders, charts, media, theme fonts/colors, and notes.
- Batch totals and file-open sanity for every generated output.
Output
Provide a pipeline design, implementation steps or scripts, validation checklist, and any Office desktop steps that cannot be performed locally.
Read references/requirement-plan.md only when the original discovery evidence is needed.
Related skills
Create and troubleshoot Excel reporting workbooks with charts, dashboards, conditional formatting, print areas, PDF/image export, openpyxl or Office automati...
Build, read, and edit .xlsx workbooks through a CLI with enforced rules for formulas, formatting, and financial-model standards.
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 and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files into proper spreadsheets.
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.
Diagnose and fix Microsoft Excel XLSX workbook issues involving formulas, named ranges, Power Query refreshes, pivot tables, VBA/macro preservation, workbook...