ada-document-artifacts

Create, edit, and validate DOCX, PDF, XLSX, and SVG document artifacts.

Updated Jul 23, 2026
One-click install
npx skills add https://github.com/wubing7755/Ada --skill ada-document-artifacts-wubing7755
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ada-document-artifacts
Source: https://github.com/wubing7755/Ada/tree/main/skills/software-development/ada-document-artifacts
Command: npx skills add https://github.com/wubing7755/Ada --skill ada-document-artifacts-wubing7755

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Working with document deliverables like Word files, PDFs, spreadsheets, and SVG diagrams involves format-specific tooling and subtle pitfalls — broken styles, hardcoded spreadsheet values, unscannable PDFs, and silently failing SVGs. This Skill provides the correct toolchain and validation steps for each format. ## Core Features & Use Cases - DOCX editing: Unpack the ZIP/XML structure for precise edits like section replacement while preserving template styles, numbering, and embedded charts. - PDF processing: Choose the right tool per task — pypdf for merging and metadata, pdfplumber for text/table extraction, reportlab for creation, and OCR for scanned pages. - XLSX spreadsheets: Preserve formulas and formatting, recalculate with zero formula errors, and apply financial modeling color conventions. - SVG diagrams: Generate flowcharts with correct viewBox, spacing, and VS Code markdown preview compatibility. - Use Case: You need to update a quarterly report — edit the DOCX via XML without breaking styles, fill the PDF form programmatically, recalculate the Excel model, and render an SVG architecture diagram that previews correctly in markdown. ## Quick Start Use the document artifacts skill to update this DOCX report, recalculate the linked XLSX model, and render the architecture diagram as an SVG that previews correctly in VS Code markdown.

Frequently Asked Questions about ada-document-artifacts

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

FAQPage Schema
How do I edit a DOCX file without breaking its formatting?

DOCX files are ZIP archives containing XML, so precise edits like section replacement should unpack the archive, edit the XML directly, and repack it. Plain text search-and-replace breaks styles and numbering, so use paragraph and table boundaries instead.

Which Python library should I use for PDF tasks?

Use pypdf for merging, splitting, rotating, and metadata; pdfplumber for text and table extraction; reportlab for creating new PDFs; and Poppler tools for rendering pages. Scanned pages without a text layer require OCR first.

Why does my SVG not render in VS Code markdown preview?

Common causes include special Unicode characters like ✕ that fail silently, using rx as a CSS property instead of an inline rect attribute, missing stroke-width with stroke-dasharray, and omitting explicit width, height, or viewBox. Use inline SVG without external fonts or scripts.

Should I hardcode calculated values in Excel spreadsheets?

No. Keep Excel formulas instead of hardcoding Python-computed values, because formulas preserve auditability and stay correct when data changes. Recalculate the workbook and verify zero formula errors before delivery.

How do I extract text from a scanned PDF?

Scanned PDFs have no text layer, so standard parsers like pdfplumber return nothing. Run OCR on the page images first, then extract the recognized text, and verify the output before delivery.