Pdf

Skill valkryhx/google_adk_agent/skills/pdf

a startup but not simple agent demo using google adk.

Install

npx -y skills add valkryhx/google_adk_agent --skill pdf

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

A collection of scripts for PDF operations including content extraction, form filling, and image conversion. Use this skill to process PDF documents, extract text/tables, or automate PDF form handling.

SKILL.md

3.5 KB, 806 tokens by cl100k_base, as published. Nobody here has run it

PDF Skill

Overview

This skill provides a comprehensive set of tools for working with PDF files. It supports extracting text and tables, converting pages to images, and filling out both fillable and non-fillable PDF forms.

Usage

1. Extract PDF Content

Extracts text and tables from a PDF and outputs a formatted Markdown file.

# Windows (Recommended)
cmd /c set PYTHONIOENCODING=utf-8 && python skills/pdf/scripts/extract_pdf_content.py [input_pdf] [output_md]

# Unix/macOS
python skills/pdf/scripts/extract_pdf_content.py [input_pdf] [output_md]

2. Convert PDF to Images

Converts each page of a PDF into a PNG image. Useful for visual analysis or OCR.

# Windows (Recommended)
cmd /c set PYTHONIOENCODING=utf-8 && python skills/pdf/scripts/convert_pdf_to_images.py [input_pdf] [output_directory]

# Unix/macOS
python skills/pdf/scripts/convert_pdf_to_images.py [input_pdf] [output_directory]

3. Handle PDF Forms

Extract Form Field Info

Identifies fillable fields in a PDF and saves their metadata to JSON.

# Windows (Recommended)
cmd /c set PYTHONIOENCODING=utf-8 && python skills/pdf/scripts/extract_form_field_info.py [input_pdf] [output_json]

# Unix/macOS
python skills/pdf/scripts/extract_form_field_info.py [input_pdf] [output_json]

Fill Fillable Fields

Fills standard PDF form fields using values from a JSON file.

# Windows (Recommended)
cmd /c set PYTHONIOENCODING=utf-8 && python skills/pdf/scripts/fill_fillable_fields.py [input_pdf] [field_values_json] [output_pdf]

# Unix/macOS
python skills/pdf/scripts/fill_fillable_fields.py [input_pdf] [field_values_json] [output_pdf]

Fill with Annotations

Fills non-fillable PDFs by adding text annotations at specific coordinates.

# Windows (Recommended)
cmd /c set PYTHONIOENCODING=utf-8 && python skills/pdf/scripts/fill_pdf_form_with_annotations.py [input_pdf] [fields_json] [output_pdf]

# Unix/macOS
python skills/pdf/scripts/fill_pdf_form_with_annotations.py [input_pdf] [fields_json] [output_pdf]

Examples

User: "Extract the text from 'report.pdf' and save it to 'report.md'." Action:

# Windows (Recommended)
cmd /c set PYTHONIOENCODING=utf-8 && python skills/pdf/scripts/extract_pdf_content.py "report.pdf" "report.md"

# Unix/macOS
python skills/pdf/scripts/extract_pdf_content.py "report.pdf" "report.md"

User: "Convert 'presentation.pdf' to images in the 'slides' folder." Action:

# Windows (Recommended)
cmd /c set PYTHONIOENCODING=utf-8 && python skills/pdf/scripts/convert_pdf_to_images.py "presentation.pdf" "slides"

# Unix/macOS
python skills/pdf/scripts/convert_pdf_to_images.py "presentation.pdf" "slides"

Scripts Reference

Script	Description
`extract_pdf_content.py`	Extracts text/tables to Markdown.
`convert_pdf_to_images.py`	Converts PDF pages to PNG.
`extract_form_field_info.py`	Gets fillable field metadata.
`fill_fillable_fields.py`	Fills standard PDF forms.
`fill_pdf_form_with_annotations.py`	Fills forms via annotations.
`check_bounding_boxes.py`	Validates field coordinates.

Gives 0 of the 12 instructions most pdf office docs skills give in 806 tokens

Counted across 635 of the 690 authors here whose files we hold, read 2026-08-06

extract text using pdfplumberin 92 of 635, across 25 files
create PDFs using reportlabin 83 of 635, across 16 files
read FORMS.md to fill out PDF formsin 80 of 635, across 13 files
OCR scanned PDFs using pytesseractin 77 of 635, across 10 files
merge or split PDFs using qpdfin 70 of 635, across 3 files
use Excel formulas instead of hardcoded calculated valuesin 68 of 635, across 12 files
unpack edit xml and repack existing documentsin 63 of 635, across 8 files
document sources for hardcoded valuesin 61 of 635, across 9 files
write minimal python code without unnecessary commentsin 59 of 635, across 7 files
run the recalculation script after adding or modifying formulasin 58 of 635, across 6 files
fix all identified formula errors and recalculatein 58 of 635, across 6 files
format years as text stringsin 57 of 635, across 5 files

Said here and by no other author read

extract fillable form field metadata to JSON
fill standard PDF forms using JSON values
fill non-fillable PDFs via text annotations
set PYTHONIOENCODING to utf-8 on Windows
validate field coordinates

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.