OpenAgentSkill Registry Manifest
Skill: ExtractPDF4J
Slug: extractpdf4j-extractpdf4j
Category: document-processing
Description: Java PDF table extraction & OCR library. Extract structured tables from text-based and scanned PDFs using stream, lattice (OpenCV-style grid detection), and hybrid parsing.

Agent fit:
- Decision: 68/100 Prototype first
- Primary fit: Document processing
- Role: Fallback candidate

Supply profile:
- Track: Research and knowledge work
- Scenario: Document processing
- Applicable agents: Claude Code, CLI, Codex, Cursor, Java
- Maintenance: 4mo since push
- Risk: Needs review

Trust:
- Trust score: 72/100 Strong shortlist
- Audit: 75/100 Needs review

Attribution:
- Status: Community indexed
- Source: GitHub star discovery
- Creator: ExtractPDF4J
- Claim URL: https://www.openagentskill.com/skills/extractpdf4j-extractpdf4j#claim-this-skill

Install:
npx skills add ExtractPDF4J/ExtractPDF4J

URLs:
- Web: https://www.openagentskill.com/skills/extractpdf4j-extractpdf4j
- API: https://www.openagentskill.com/api/agent/skills/extractpdf4j-extractpdf4j
- Install API: https://www.openagentskill.com/api/skills/extractpdf4j-extractpdf4j/install
- Repository: https://github.com/ExtractPDF4J/ExtractPDF4J