skillagent/test/skills/pdf-tools/extract.md

extract.py

Extracts text and metadata from PDF files.

Input:

{
  "file_path": "/path/to/document.pdf",
  "pages": "all" | [1, 2, 3]
}

Output:

{
  "text": "Extracted text content...",
  "metadata": {
    "title": "Document Title",
    "author": "Author Name",
    "pages": 10
  }
}

Usage Example

from skillkit import SkillManager

manager = SkillManager()
result = manager.execute_skill_script(
    skill_name="pdf-extractor",
    script_name="extract",
    arguments={"file_path": "document.pdf", "pages": "all"}
)

if result.success:
    print(result.stdout)