Document Processing
Handles the full spectrum of office document work: extracting text and tables from PDFs, merging and splitting files, OCR for scanned documents, creating Word docs and PowerPoint decks from scratch, and manipulating Excel spreadsheets. Built on solid tools like pdfplumber for PDFs, pandoc for Word conversions, and pandas for Excel analysis. The OOXML unpacking approach for deep Word and PowerPoint edits is clever, letting you modify the raw XML when higher-level libraries fall short. Covers both Python and JavaScript implementations depending on the task. If you're building document workflows or need to automate report generation, this gives you working code for most common scenarios without hunting through multiple library docs.
- skills.sh installs
- 311
- GitHub stars
- 33
- last updated
- Jun 3, 2026
Install
$ npx -y skills add dirnbauer/webconsulting-skills --skill document-processing --agent claude-codeInstalls into .claude/skills of the current project.
Files
Document Processing
Source: This skill is adapted from Anthropic's document-processing skill document processing skills (pdf, docx, pptx, xlsx) for Claude Code and AI agents.
Create, edit, and analyze office documents including PDFs, Word documents, PowerPoint presentations, and Excel spreadsheets.
Quick Reference: Which Tool to Use
| Task | Document Type | Best Tool |
|---|---|---|
| Extract text | pdfplumber, pdftotext | |
| Merge/split | pypdf, qpdf | |
| Fill forms | pdf-lib (JS), pypdf | |
| Create new | reportlab | |
| OCR scanned | pytesseract + pdf2image | |
| Extract text | DOCX | pandoc, markitdown |
| Create new | DOCX | docx-js (JS) |
| Edit existing | DOCX | OOXML (unpack/edit/pack) |
| Extract text | PPTX | markitdown |
| Create new | PPTX | html2pptx, PptxGenJS |
| Edit existing | PPTX | OOXML (unpack/edit/pack) |
| Data analysis | XLSX | pandas |
| Formulas/formatting | XLSX | openpyxl |
PDF Processing
Text Extraction
import pdfplumber
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/dirnbauer/webconsulting-skills
- First seen
- Jun 3, 2026
More from dirnbauer/webconsulting-skills
All 2Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs