pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

1.31x

Quality

82%

Does it follow best practices?

Impact

95%

1.31x

Average score across 8 eval scenarios

Securityby

Passed

No known issues

Evaluation results

100%

90%

Task: Fill Out a Tax Form PDF

Fillable PDF form detection and multi-step form filling workflow

Criteria

Without context

With context

Checks for fillable fields first

100%

Extracts field info with script

100%

Converts PDF to images for visual analysis

100%

Creates field_values.json with correct format

100%

Fills using fill_fillable_fields.py

100%

Uses pypdf not PyPDF2

100%

62%

53%

Task: Fill Out a Scanned Application Form

Non-fillable PDF form filling with bounding box annotation and validation workflow

Criteria

Without context

With context

Checks for fillable fields first

100%

Converts PDF to PNG images

50%

Creates fields.json with correct structure

85%

Creates validation images

Runs bounding box check script

100%

Visually inspects validation images

Fills using fill_pdf_form_with_annotations.py

26%

100%

20%

Task: Extract Financial Data from a PDF Report

PDF text and table extraction using pdfplumber and pypdf for structured data processing

Criteria

Without context

With context

Uses pdfplumber for table extraction

100%

Uses pypdf for PDF reading and metadata

100%

Converts tables to structured format

100%

Handles multi-page extraction

100%

Uses pdfplumber for text extraction

100%

20%

Task: PDF Thumbnail Generator and Summary Report

Using pypdf for reading PDFs and reportlab Platypus for creating structured PDF reports

Criteria

Without context

With context

Uses pypdf for reading PDFs and metadata

100%

Uses reportlab for PDF creation

100%

Uses Platypus for structured report

100%

Uses getSampleStyleSheet for styling

100%

Includes reportlab Table for document listing

100%

Renders PDF pages to PNG images

100%

Task: PDF Document Assembly Pipeline

PDF merge, split, watermark, and password protection using pypdf

Criteria

Without context

With context

Uses pypdf PdfWriter for merging

100%

Uses pypdf for splitting

100%

Uses pypdf merge_page for watermark

100%

Uses pypdf for password protection

100%

Proper file handling pattern

100%

Chemistry Reference Sheet PDF

ReportLab subscript and superscript rendering

Criteria

Without context

With context

Uses <sub> tag for subscripts

100%

Uses <super> tag for superscripts

100%

No Unicode subscript chars

100%

No Unicode superscript chars

100%

Uses Paragraph for subscript/superscript content

100%

Uses reportlab for PDF creation

100%

Extract Sales Data from PDF Report

pdfplumber table extraction with pandas and Excel export

Criteria

Without context

With context

Uses pdfplumber for tables

100%

Converts to pandas DataFrame

100%

Handles empty tables

100%

Combines with pd.concat

100%

Exports to Excel with to_excel

100%

Multi-page iteration

100%

Extract Text from Scanned Archive Documents

OCR text extraction from scanned PDFs

Criteria

Without context

With context

Uses pdf2image for conversion

100%

Uses pytesseract for OCR

100%

Iterates over all pages

100%

Per-page labeling in output

100%

Does NOT use pdfplumber/pypdf text extraction

100%

Repository: douglasvought/wiggle-skills
Commit: b27906e

Evaluated: 2 months ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Task: Fill Out a Tax Form PDF Task: Fill Out a Scanned Application Form Task: Extract Financial Data from a PDF Report Task: PDF Thumbnail Generator and Summary Report Task: PDF Document Assembly Pipeline Chemistry Reference Sheet PDF Extract Sales Data from PDF Report Extract Text from Scanned Archive Documents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.