mcpbeat

PDF Extractor

guia-matthieu/pdf-extractor

Extract text, tables, and images from PDFs. Use when: extracting data from reports; converting PDF tables to CSV; pulling images from presentations; processing research papers; batch converting PDFs to text

3k tokens
context cost
the whole folder, loaded on every use
3
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
145
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill pdf-extractor

What comes with it

10 356 bytes besides the instruction
scripts/main.py
scripts/requirements.txt

The instruction itself

19 sections, as written by the author

PDF Extractor

> Extract text, tables, and images from PDF files using pdfplumber - turn static PDFs into usable data.

When to Use This Skill

  • Report processing - Extract data from PDF reports
  • Table extraction - Convert PDF tables to CSV
  • Image collection - Pull images from presentations
  • Text mining - Bulk convert PDFs to searchable text
  • Research - Process academic papers and whitepapers

What Claude Does vs What You Decide

| Claude Does | You Decide |

|-------------|------------|

| Structures analysis frameworks | Metric definitions |

| Identifies patterns in data | Business interpretation |

| Creates visualization templates | Dashboard design |

| Suggests optimization areas | Action priorities |

| Calculates statistical measures | Decision thresholds |

Dependencies

pip install pdfplumber pypdf click pandas
# For image extraction:
pip install Pillow

Commands

Extract Text

python scripts/main.py text document.pdf
python scripts/main.py text document.pdf --pages 1-5

Extract Tables

python scripts/main.py tables report.pdf --output tables.csv
python scripts/main.py tables financial.pdf --page 3

Extract Images

python scripts/main.py images presentation.pdf --output ./images/

Merge PDFs

python scripts/main.py merge doc1.pdf doc2.pdf --output combined.pdf

PDF Info

python scripts/main.py info document.pdf

Examples

Example 1: Extract Financial Tables

python scripts/main.py tables annual-report.pdf --output financials.csv

# Output: financials.csv with all tables found
# Also creates individual CSVs: table_page3_1.csv, table_page5_1.csv

Example 2: Batch Convert to Text

python scripts/main.py batch ./pdfs/ --output ./text/

# Converts all PDFs in folder to .txt files

Example 3: Extract Specific Pages

python scripts/main.py text whitepaper.pdf --pages 1,5-10,15

# Extracts only pages 1, 5-10, and 15

Skill Boundaries

What This Skill Does Well

  • Structuring data analysis
  • Identifying patterns and trends
  • Creating visualization frameworks
  • Calculating statistical measures

What This Skill Cannot Do

  • Access your actual data
  • Replace statistical expertise
  • Make business decisions
  • Guarantee prediction accuracy

Related Skills

  • web-scraper - Scrape web content
  • content-repurposer - Repurpose extracted content

Skill Metadata

  • Mode: centaur
category: automation
subcategory: document-processing
dependencies: [pdfplumber, pypdf, pandas]
difficulty: beginner
time_saved: 4+ hours/week

How to use it

Copy the folder

Take guia-matthieu/pdf-extractor from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

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.

Install what it needs

The instructions reference pip. Without those the skill loads but fails at the first command.