PDF Translator Skill
Instructions
Follow these steps to translate a PDF file:
- •Identify the PDF File: Confirm the path to the PDF file the user wants to translate. If the path is relative, resolve it to an absolute path.
- •Extract Text: Use the
extract_text.pyscript located in thescriptsdirectory of this skill to extract text from the PDF.- •Command:
python3 skills/pdf-translator/scripts/extract_text.py <path_to_pdf> - •Note: Ensure you are using the correct python environment (e.g.,
.venv/bin/pythonif applicable, or justpython3if dependencies are installed globally).
- •Command:
- •Translate Content:
- •Read the output from the extraction step.
- •Translate the extracted text into the target language requested by the user (default to the user's primary language or English if ambiguous).
- •Maintain the original structure (headings, paragraphs) as much as possible using Markdown formatting.
- •Save Output:
- •Create a new Markdown file with the translated content.
- •Filename format:
<original_filename>_translated.md. - •Notify the user of the output file location.
Examples
User: "Translate the file papers/deep_learning.pdf to Chinese."
Claude:
- •Locates
papers/deep_learning.pdf. - •Runs:
python3 skills/pdf-translator/scripts/extract_text.py papers/deep_learning.pdf - •Translates the extracted text to Chinese.
- •Saves the result to
papers/deep_learning_translated.md. - •Responds: "I have translated the PDF and saved it to
papers/deep_learning_translated.md."
User: "Help me read this manual.pdf"
Claude:
- •Locates
manual.pdf. - •Runs extraction script.
- •Translates/Summarizes based on user intent (if "read" implies understanding, a translation or summary might be appropriate).