evo-pdf-content-extraction
SkillDocs & knowledgeExtracts and analyzes text content from PDF pages to identify author-revealing information including names, affiliations, emails, arXiv IDs, venue/conference mentions, and other identity-leaking content.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the evo-pdf-content-extraction skill
What this skill tells your AI
The instructions your AI receives, as published by openlair/openskill in tasks-evolved/paper-anonymizer/environment/skills/evo-pdf-content-extraction/SKILL.md and read by ahel’s review.
Extracts text from academic PDFs and identifies all content that could reveal authorship for anonymization purposes.
Key Functions
extract_page_text(page)- Get plain text from a pageextract_words_with_positions(page)- Get words with bounding box coordinatesidentify_author_block_region(page)- Find the author block area on first pagedetect_arxiv_identifiers(text)- Find arXiv IDs in textdetect_email_addresses(text)- Find email addressesdetect_affiliations(text)- Find institutional affiliationsdetect_venue_statements(text)- Find venue/conference acceptance statementsget_all_redaction_targets(pdf_path)- Main function: analyze a PDF and return all strings to redact
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-pdf-content-extraction/scripts')
from extraction import get_all_redaction_targets
targets = get_all_redaction_targets('/root/paper1.pdf')
print(targets['exact_strings']) # List of exact strings to redact
print(targets['regex_patterns']) # List of regex patterns to apply
print(targets['link_patterns']) # URL patterns to scrub
Signals
- GitHub stars
- 89
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
evo-pdf-content-extraction- Source
- github.com/openlair/openskill