academic-pdf-redaction

Redact identifying information from academic PDFs while preserving references.

Updated Jan 15, 2026
One-click install
npx skills add https://github.com/KaiserWhoLearns/skillsbench --skill academic-pdf-redaction
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: academic-pdf-redaction
Source: https://github.com/KaiserWhoLearns/skillsbench/tree/main/tasks/paper-anonymizer/environment/skills/academic-pdf-redaction
Command: npx skills add https://github.com/KaiserWhoLearns/skillsbench --skill academic-pdf-redaction

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Redact identifying information from PDF documents for blind review anonymization.

Core Features & Use Cases

  • Preserve References while redacting: The tool identifies and redacts author names, affiliations, emails, venue names, arXiv IDs, DOIs, and Acknowledgements, ensuring references remain intact.
  • ONLY redact specific text matches: It redacts exact matches only, avoiding full pages or large regions to preserve document structure and readability.
  • VERIFY output: After redaction, it provides verification steps to ensure content remains readable and the document integrity is preserved.

Quick Start

Run the Python redaction workflow on your PDF to remove identifying information while preserving references.

Frequently Asked Questions about academic-pdf-redaction

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I redact identifying information in academic PDFs for blind review?

To redact identifying information for blind review, this tool selectively removes exact text matches of author names, affiliations, and emails from academic PDFs while preserving the References section and document structure. It uses PyMuPDF to ensure precise redaction of exact matches only.

Can I anonymize an academic paper for double-blind review without removing references?

Yes, you can anonymize an academic paper without losing references. The redaction process specifically preserves the References section and essential content while removing author names, affiliations, emails, DOIs, and Acknowledgements to ensure the manuscript remains readable.

How does PyMuPDF handle text pattern redaction in scholarly manuscripts?

PyMuPDF handles text pattern redaction by selectively targeting and removing exact text matches in scholarly manuscripts. It avoids deleting entire pages or large regions, ensuring the document's structural integrity and readability are preserved during the anonymization workflow.

What specific identifying information is removed during PDF anonymization?

During PDF anonymization, the tool removes author names, affiliations, emails, venue names, arXiv IDs, DOIs, and Acknowledgements. It targets these exact text patterns to thoroughly prepare the document for blind review while leaving references intact.

Does PDF redaction verify that document integrity is preserved after removing text?

Yes, the PDF redaction workflow includes verification steps after removing text. It verifies the redaction output to ensure the content remains readable and the document integrity is fully preserved before finalizing the anonymized manuscript.