📦

pdf

Name: pdf
Author: sickn33

Riesgo bajo ⚙️ Comandos externos🌐 Acceso a red📁 Acceso al sistema de archivos

Process and manipulate PDF documents

También disponible en: AutumnsGrove,Azeem-2,92Bilal26,Cam10001110101,92Bilal26,davila7,ArtemisAI,anthropics,DYAI2025,ZhanlinCui,ComposioHQ,K-Dense-AI

Handle PDF forms, extract text and tables, merge or split documents, and create new PDFs programmatically. This skill eliminates manual PDF editing by automating form filling, data extraction, and document assembly tasks.

Soporta: Claude Codex Code(CC)

🥈 77 Plata

Descargar el ZIP de la skill

Subir en Claude

Ve a Configuración → Capacidades → Skills → Subir skill

Activa y empieza a usar

Pruébalo

Usando "pdf". Extract form fields from application.pdf

Resultado esperado:

Read 12 fields from application.pdf
Wrote field information to fields.json:
- name (text field, page 1)
- email (text field, page 1)
- age (text field, page 1)
- citizen_checkbox (checkbox, page 2)
- signature (text field, page 3)

Usando "pdf". Fill form with field_values.json

Resultado esperado:

Loaded 12 field values from field_values.json
Validating field IDs against PDF form...
All fields validated successfully
Writing filled form to output.pdf
Completed: 12 fields filled

Auditoría de seguridad

Riesgo bajo

v1 • 2/24/2026

Static analysis detected 219 patterns across 12 files, but all are false positives. The 'external_commands' are markdown documentation code blocks, not executable code. 'Weak cryptographic algorithm' warnings are from test files using MD5 for non-security test data generation. 'C2 keywords' and 'system reconnaissance' are CLI argument parsing and legitimate system calls. The skill performs legitimate PDF processing using Python libraries (pypdf, pdfplumber, reportlab). Low risk due to filesystem operations and external tool dependencies (poppler-utils, qpdf) that require user-provided file paths.

Archivos escaneados

1,909

Líneas analizadas

hallazgos

Auditorías totales

Problemas de riesgo bajo (2)

scripts/extract_form_field_info.py:141-144 scripts/fill_fillable_fields.py:55 scripts/fill_pdf_form_with_annotations.py:93

Filesystem Write Operations

Scripts write output PDF and JSON files to disk. User controls file paths via CLI arguments, minimizing risk.

SKILL.md:172-196 forms.md:87

External Tool Dependencies

Documentation references external CLI tools (qpdf, pdftotext, pdfimages) that execute shell commands. These are documented usage patterns, not embedded malicious code.

Factores de riesgo

⚙️ Comandos externos (4)

forms.md:87 forms.md:180 SKILL.md:172-196 reference.md:11-590

🌐 Acceso a red (1)

LICENSE.txt:8-9

📁 Acceso al sistema de archivos (4)

scripts/extract_form_field_info.py:141-144 scripts/fill_fillable_fields.py:55 scripts/fill_pdf_form_with_annotations.py:93 SKILL.md:42-75

Auditado por: claude

Puntuación de calidad

Arquitectura

100

Mantenibilidad

Contenido

Comunidad

Seguridad

Cumplimiento de la especificación

Lo que puedes crear

Automated Form Processing

Extract field definitions from fillable PDF forms, map user data to fields, and generate completed forms without manual entry.

Document Data Extraction

Extract structured text and tables from PDF reports, invoices, or documents for analysis and conversion to other formats.

PDF Assembly and Generation

Merge multiple PDFs, split large documents, add watermarks, or create new PDFs from templates programmatically.

Prueba estos prompts

Extract PDF Form Fields

I have a fillable PDF form at [path]. Extract all form field information including field names, types, and locations. Save the output to a JSON file so I can map values to each field.

Fill PDF Form with Data

Fill the PDF form at [input.pdf] using the values in [field_values.json]. The form has fields for name, address, and checkboxes. Validate that all fields are mapped correctly before generating the output.

Extract Tables from PDF Report

Extract all tables from this financial report PDF. Convert each table to a pandas DataFrame and save them to an Excel file with separate sheets. Preserve column headers and data types where possible.

Add Text Annotations to Non-Fillable Form

This PDF form has no fillable fields. Analyze each page to identify where text should be entered. Create bounding boxes for labels and entry areas, generate validation images, and add text annotations at the correct positions.

Mejores prácticas

Always validate bounding boxes visually before adding annotations to non-fillable forms
Test PDF operations on a copy before processing original documents
Specify explicit font sizes when adding text annotations to ensure proper rendering

Evitar

Do not skip validation steps when working with non-fillable forms
Avoid using default file paths; always specify explicit input and output locations
Do not assume all PDFs have fillable fields; check before attempting form filling

Preguntas frecuentes

What Python libraries does this skill require?

The skill uses pypdf for basic PDF operations, pdfplumber for text and table extraction, and reportlab for PDF creation. Install with: pip install pypdf pdfplumber reportlab

Can this skill fill out scanned PDF forms?

Yes, but it requires a visual analysis step. The skill converts PDF pages to images, identifies field locations with bounding boxes, validates positions, then adds text annotations at the correct coordinates.

How do I handle PDFs with no fillable fields?

Follow the non-fillable form workflow: convert to images, create a fields.json with label and entry bounding boxes, generate validation images to verify positions, then add annotations using the fill script.

What external tools are needed for command-line operations?

For CLI operations, install poppler-utils (provides pdftotext, pdfimages) and qpdf. On Ubuntu: apt install poppler-utils qpdf. On macOS: brew install poppler qpdf

Can this skill extract tables from PDFs?

Yes, using pdfplumber. The skill can extract tables as structured data and convert them to pandas DataFrames or Excel files for further analysis.

How are checkbox and radio button values handled?

For fillable forms, the skill extracts the checked/unchecked values from the PDF. For checkboxes, use the checked_value to mark them. For radio groups, select one of the radio_options values.