Requirement already satisfied: python-frontmatter in ./.local/lib/python3.12/site-packages (1.1.0)
Requirement already satisfied: PyYAML in /usr/local/lib/python3.12/site-packages (from python-frontmatter) (6.0.3)

[Skill(name='xlsx', description='Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas', license='Proprietary. LICENSE.txt has complete terms'),
 Skill(name='webapp-testing', description='Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.', license='Complete terms in LICENSE.txt'),
 Skill(name='theme-factory', description='Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.', license='Complete terms in LICENSE.txt'),
 Skill(name='docx', description='Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks', license='Proprietary. LICENSE.txt has complete terms'),
 Skill(name='web-artifacts-builder', description='Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.', license='Complete terms in LICENSE.txt'),
 Skill(name='skill-creator', description="Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.", license='Complete terms in LICENSE.txt'),
 Skill(name='frontend-design', description='Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.', license='Complete terms in LICENSE.txt'),
 Skill(name='pptx', description='Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks', license='Proprietary. LICENSE.txt has complete terms'),
 Skill(name='algorithmic-art', description="Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.", license='Complete terms in LICENSE.txt'),
 Skill(name='internal-comms', description='A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).', license='Complete terms in LICENSE.txt'),
 Skill(name='doc-coauthoring', description='Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.', license=None),
 Skill(name='pdf', description='Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.', license='Proprietary. LICENSE.txt has complete terms'),
 Skill(name='brand-guidelines', description="Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.", license='Complete terms in LICENSE.txt'),
 Skill(name='slack-gif-creator', description='Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."', license='Complete terms in LICENSE.txt'),
 Skill(name='canvas-design', description="Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.", license='Complete terms in LICENSE.txt'),
 Skill(name='mcp-builder', description='Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).', license='Complete terms in LICENSE.txt')]

name: pdf description: Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. license: Proprietary. LICENSE.txt has complete terms

PDF Processing Guide

Overview

This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see reference.md. If you need to fill out a PDF form, read forms.md and follow its instructions.

Quick Start

from pypdf import PdfReader, PdfWriter

# Read a PDF
reader = PdfReader("document.pdf")
print(f"Pages: {len(reader.pages)}")

# Extract text
text = ""
for page in reader.pages:
    text += page.extract_text()

Python Libraries

pypdf - Basic Operations

Merge PDFs

from pypdf import PdfWriter, PdfReader

writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)

with open("merged.pdf", "wb") as output:
    writer.write(output)

Split PDF

reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"page_{i+1}.pdf", "wb") as output:
        writer.write(output)

Extract Metadata

reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Title: {meta.title}")
print(f"Author: {meta.author}")
print(f"Subject: {meta.subject}")
print(f"Creator: {meta.creator}")

Rotate Pages

reader = PdfReader("input.pdf")
writer = PdfWriter()

page = reader.pages[0]
page.rotate(90)  # Rotate 90 degrees clockwise
writer.add_page(page)

with open("rotated.pdf", "wb") as output:
    writer.write(output)

pdfplumber - Text and Table Extraction

Extract Text with Layout

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

Extract Tables

with pdfplumber.open("document.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        tables = page.extract_tables()
        for j, table in enumerate(tables):
            print(f"Table {j+1} on page {i+1}:")
            for row in table:
                print(row)

Advanced Table Extraction

import pandas as pd

with pdfplumber.open("document.pdf") as pdf:
    all_tables = []
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:  # Check if table is not empty
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

# Combine all tables
if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("extracted_tables.xlsx", index=False)

reportlab - Create PDFs

Basic PDF Creation

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

# Add text
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")

# Add a line
c.line(100, height - 140, 400, height - 140)

# Save
c.save()

Create PDF with Multiple Pages

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib.styles import getSampleStyleSheet

doc = SimpleDocTemplate("report.pdf", pagesize=letter)
styles = getSampleStyleSheet()
story = []

# Add content
title = Paragraph("Report Title", styles['Title'])
story.append(title)
story.append(Spacer(1, 12))

body = Paragraph("This is the body of the report. " * 20, styles['Normal'])
story.append(body)
story.append(PageBreak())

# Page 2
story.append(Paragraph("Page 2", styles['Heading1']))
story.append(Paragraph("Content for page 2", styles['Normal']))

# Build PDF
doc.build(story)

Command-Line Tools

pdftotext (poppler-utils)

# Extract text
pdftotext input.pdf output.txt

# Extract text preserving layout
pdftotext -layout input.pdf output.txt

# Extract specific pages
pdftotext -f 1 -l 5 input.pdf output.txt  # Pages 1-5

qpdf

# Merge PDFs
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

# Split pages
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf

# Rotate pages
qpdf input.pdf output.pdf --rotate=+90:1  # Rotate page 1 by 90 degrees

# Remove password
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

pdftk (if available)

# Merge
pdftk file1.pdf file2.pdf cat output merged.pdf

# Split
pdftk input.pdf burst

# Rotate
pdftk input.pdf rotate 1east output rotated.pdf

Common Tasks

Extract Text from Scanned PDFs

# Requires: pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path

# Convert PDF to images
images = convert_from_path('scanned.pdf')

# OCR each page
text = ""
for i, image in enumerate(images):
    text += f"Page {i+1}:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)

Add Watermark

from pypdf import PdfReader, PdfWriter

# Create watermark (or load existing)
watermark = PdfReader("watermark.pdf").pages[0]

# Apply to all pages
reader = PdfReader("document.pdf")
writer = PdfWriter()

for page in reader.pages:
    page.merge_page(watermark)
    writer.add_page(page)

with open("watermarked.pdf", "wb") as output:
    writer.write(output)

Extract Images

# Using pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix

# This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc.

Password Protection

from pypdf import PdfReader, PdfWriter

reader = PdfReader("input.pdf")
writer = PdfWriter()

for page in reader.pages:
    writer.add_page(page)

# Add password
writer.encrypt("userpassword", "ownerpassword")

with open("encrypted.pdf", "wb") as output:
    writer.write(output)

Quick Reference

Next Steps

• For advanced pypdfium2 usage, see reference.md
• For JavaScript libraries (pdf-lib), see reference.md
• If you need to fill out a PDF form, follow the instructions in forms.md
• For troubleshooting guides, see reference.md

'**CRITICAL: You MUST complete these steps in order. Do not skip ahead to writing code.**\n\nIf you need to fill out a PDF form, first check to see if the PDF has fillable form fields. Run this script from this file\'s directory:\n `python scripts/check_fillable_fields <file.pdf>`, and depending on the result go to either the "Fillable fields" or "Non-fillable fields" and follow those instructions.\n\n# Fillable fields\nIf the PDF has fillable form fields:\n- Run this script from this file\'s directory: `python scripts/extract_form_field_info.py <input.pdf> <field_info.json>`. It will create a JSON file with a list of fields in this format:\n```\n[\n  {\n    "field_id": (unique ID for the field),\n    "page": (page number, 1-based),\n    "rect": ([left, bottom, right, top] bounding box in PDF coordinates, y=0 is the bottom of the page),\n    "type": ("text", "checkbox", "radio_group", or "choice"),\n  },\n  // Checkboxes have "checked_value" and "unchecked_value" properties:\n  {\n    "field_id": (unique ID for the field),\n    "page": (page number, 1-based),\n    "type": "checkbox",\n    "checked_value": (Set the field to this value to check the checkbox),\n    "unchecked_value": (Set the field to this value to uncheck the checkbox),\n  },\n  // Radio groups have a "radio_options" list with the possible choices.\n  {\n    "field_id": (unique ID for the field),\n    "page": (page number, 1-based),\n    "type": "radio_group",\n    "radio_options": [\n      {\n        "value": (set the field to this value to select this radio option),\n        "rect": (bounding box for the radio button for this option)\n      },\n      // Other radio options\n    ]\n  },\n  // Multiple choice fields have a "choice_options" list with the possible choices:\n  {\n    "field_id": (unique ID for the field),\n    "page": (page number, 1-based),\n    "type": "choice",\n    "choice_options": [\n      {\n        "value": (set the field to this value to select this option),\n        "text": (display text of the option)\n      },\n      // Other choice options\n    ],\n  }\n]\n```\n- Convert the PDF to PNGs (one image for each page) with this script (run from this file\'s directory):\n`python scripts/convert_pdf_to_images.py <file.pdf> <output_directory>`\nThen analyze the images to determine the purpose of each form field (make sure to convert the bounding box PDF coordinates to image coordinates).\n- Create a `field_values.json` file in this format with the values to be entered for each field:\n```\n[\n  {\n    "field_id": "last_name", // Must match the field_id from `extract_form_field_info.py`\n    "description": "The user\'s last name",\n    "page": 1, // Must match the "page" value in field_info.json\n    "value": "Simpson"\n  },\n  {\n    "field_id": "Checkbox12",\n    "description": "Checkbox to be checked if the user is 18 or over",\n    "page": 1,\n    "value": "/On" // If this is a checkbox, use its "checked_value" value to check it. If it\'s a radio button group, use one of the "value" values in "radio_options".\n  },\n  // more fields\n]\n```\n- Run the `fill_fillable_fields.py` script from this file\'s directory to create a filled-in PDF:\n`python scripts/fill_fillable_fields.py <input pdf> <field_values.json> <output pdf>`\nThis script will verify that the field IDs and values you provide are valid; if it prints error messages, correct the appropriate fields and try again.\n\n# Non-fillable fields\nIf the PDF doesn\'t have fillable form fields, you\'ll need to visually determine where the data should be added and create text annotations. Follow the below steps *exactly*. You MUST perform all of these steps to ensure that the the form is accurately completed. Details for each step are below.\n- Convert the PDF to PNG images and determine field bounding boxes.\n- Create a JSON file with field information and validation images showing the bounding boxes.\n- Validate the the bounding boxes.\n- Use the bounding boxes to fill in the form.\n\n## Step 1: Visual Analysis (REQUIRED)\n- Convert the PDF to PNG images. Run this script from this file\'s directory:\n`python scripts/convert_pdf_to_images.py <file.pdf> <output_directory>`\nThe script will create a PNG image for each page in the PDF.\n- Carefully examine each PNG image and identify all form fields and areas where the user should enter data. For each form field where the user should enter text, determine bounding boxes for both the form field label, and the area where the user should enter text. The label and entry bounding boxes MUST NOT INTERSECT; the text entry box should only include the area where data should be entered. Usually this area will be immediately to the side, above, or below its label. Entry bounding boxes must be tall and wide enough to contain their text.\n\nThese are some examples of form structures that you might see:\n\n*Label inside box*\n```\n┌────────────────────────┐\n│ Name:                  │\n└────────────────────────┘\n```\nThe input area should be to the right of the "Name" label and extend to the edge of the box.\n\n*Label before line*\n```\nEmail: _______________________\n```\nThe input area should be above the line and include its entire width.\n\n*Label under line*\n```\n_________________________\nName\n```\nThe input area should be above the line and include the entire width of the line. This is common for signature and date fields.\n\n*Label above line*\n```\nPlease enter any special requests:\n________________________________________________\n```\nThe input area should extend from the bottom of the label to the line, and should include the entire width of the line.\n\n*Checkboxes*\n```\nAre you a US citizen? Yes □  No □\n```\nFor checkboxes:\n- Look for small square boxes (□) - these are the actual checkboxes to target. They may be to the left or right of their labels.\n- Distinguish between label text ("Yes", "No") and the clickable checkbox squares.\n- The entry bounding box should cover ONLY the small square, not the text label.\n\n### Step 2: Create fields.json and validation images (REQUIRED)\n- Create a file named `fields.json` with information for the form fields and bounding boxes in this format:\n```\n{\n  "pages": [\n    {\n      "page_number": 1,\n      "image_width": (first page image width in pixels),\n      "image_height": (first page image height in pixels),\n    },\n    {\n      "page_number": 2,\n      "image_width": (second page image width in pixels),\n      "image_height": (second page image height in pixels),\n    }\n    // additional pages\n  ],\n  "form_fields": [\n    // Example for a text field.\n    {\n      "page_number": 1,\n      "description": "The user\'s last name should be entered here",\n      // Bounding boxes are [left, top, right, bottom]. The bounding boxes for the label and text entry should not overlap.\n      "field_label": "Last name",\n      "label_bounding_box": [30, 125, 95, 142],\n      "entry_bounding_box": [100, 125, 280, 142],\n      "entry_text": {\n        "text": "Johnson", // This text will be added as an annotation at the entry_bounding_box location\n        "font_size": 14, // optional, defaults to 14\n        "font_color": "000000", // optional, RRGGBB format, defaults to 000000 (black)\n      }\n    },\n    // Example for a checkbox. TARGET THE SQUARE for the entry bounding box, NOT THE TEXT\n    {\n      "page_number": 2,\n      "description": "Checkbox that should be checked if the user is over 18",\n      "entry_bounding_box": [140, 525, 155, 540],  // Small box over checkbox square\n      "field_label": "Yes",\n      "label_bounding_box": [100, 525, 132, 540],  // Box containing "Yes" text\n      // Use "X" to check a checkbox.\n      "entry_text": {\n        "text": "X",\n      }\n    }\n    // additional form field entries\n  ]\n}\n```\n\nCreate validation images by running this script from this file\'s directory for each page:\n`python scripts/create_validation_image.py <page_number> <path_to_fields.json> <input_image_path> <output_image_path>\n\nThe validation images will have red rectangles where text should be entered, and blue rectangles covering label text.\n\n### Step 3: Validate Bounding Boxes (REQUIRED)\n#### Automated intersection check\n- Verify that none of bounding boxes intersect and that the entry bounding boxes are tall enough by checking the fields.json file with the `check_bounding_boxes.py` script (run from this file\'s directory):\n`python scripts/check_bounding_boxes.py <JSON file>`\n\nIf there are errors, reanalyze the relevant fields, adjust the bounding boxes, and iterate until there are no remaining errors. Remember: label (blue) bounding boxes should contain text labels, entry (red) boxes should not.\n\n#### Manual image inspection\n**CRITICAL: Do not proceed without visually inspecting validation images**\n- Red rectangles must ONLY cover input areas\n- Red rectangles MUST NOT contain any text\n- Blue rectangles should contain label text\n- For checkboxes:\n  - Red rectangle MUST be centered on the checkbox square\n  - Blue rectangle should cover the text label for the checkbox\n\n- If any rectangles look wrong, fix fields.json, regenerate the validation images, and verify again. Repeat this process until the bounding boxes are fully accurate.\n\n\n### Step 4: Add annotations to the PDF\nRun this script from this file\'s directory to create a filled-out PDF using the information in fields.json:\n`python scripts/fill_pdf_form_with_annotations.py <input_pdf_path> <path_to_fields.json> <output_pdf_path>\n'