Agent Claude Code
This pipeline converts PDFs with reviewer annotations into clean, structured sections ready for ArangoDB insertion.
not rated 3 27d ago A 0 tokens
GPL-3.0
3Stars on the repository
54Mods indexed here, across every type
27d agoLast push, which is what freshness is scored on
GPL-3.0Licence, which decides whether bodies are shown
Agent Claude Code
Agent "PDF_EXTRACTION_QUICK_REFERENCE" from grahama1970/extractor, covering pdf extraction quick reference, complete pipeline in 10 commands, 1. extract annotations from original pdf, 3. create clean pdf without annotations and 4. check knowledge base for similar extractions.
not rated 3 27d ago A 0 tokens
GPL-3.0
Agent Claude Code
After Stage 6, you have sections like this.
not rated 3 27d ago A 0 tokens
GPL-3.0
extract-docx
04Agent Claude Code
Advanced multi-format document processing with AI accuracy improvements - Enhanced marker-pdf fork.
not rated 3 27d ago not scanned
tokens not measured
GPL-3.0
extract-epub
05Agent Claude Code
Advanced multi-format document processing with AI accuracy improvements - Enhanced marker-pdf fork.
not rated 3 27d ago not scanned
tokens not measured
GPL-3.0
extract-html
06Agent Claude Code
Advanced multi-format document processing with AI accuracy improvements - Enhanced marker-pdf fork.
not rated 3 27d ago not scanned
tokens not measured
GPL-3.0
Agent Claude Code
Advanced multi-format document processing with AI accuracy improvements - Enhanced marker-pdf fork.
not rated 3 27d ago not scanned
tokens not measured
GPL-3.0
extract-pdf
08Agent Claude Code
PDF extraction orchestrator. I coordinate workers who do all execution.
not rated 3 27d ago A 17 tokens
GPL-3.0
extract-ppt
09Agent Claude Code
Advanced multi-format document processing with AI accuracy improvements - Enhanced marker-pdf fork.
not rated 3 27d ago not scanned
tokens not measured
GPL-3.0
extract-rst
10Agent Claude Code
Advanced multi-format document processing with AI accuracy improvements - Enhanced marker-pdf fork.
not rated 3 27d ago not scanned
tokens not measured
GPL-3.0
Agent Claude Code
Advanced multi-format document processing with AI accuracy improvements - Enhanced marker-pdf fork.
not rated 3 27d ago not scanned
tokens not measured
GPL-3.0
extract-xml
12Agent Claude Code
Advanced multi-format document processing with AI accuracy improvements - Enhanced marker-pdf fork.
not rated 3 27d ago not scanned
tokens not measured
GPL-3.0
Agent Claude Code
Extracts and interprets PDF annotations including comments, highlights, and markup.
not rated 3 27d ago A 18 tokens
GPL-3.0
pdf-camelot
14Agent Claude Code
Advanced table extraction using Camelot library for complex table structures.
not rated 3 27d ago A 16 tokens
GPL-3.0
pdf-form
15Agent Claude Code
Extracts and processes PDF form fields, checkboxes, and fillable elements.
not rated 3 27d ago A 18 tokens
GPL-3.0
Agent Claude Code
Identifies and classifies objects in PDF pages including images, diagrams, charts, and special elements.
not rated 3 27d ago A 24 tokens
GPL-3.0
Agent Claude Code
Comprehensively analyzes and cleans PDF sections in batches. Use when: processing extracted PDF sections that need complete analysis including text cleaning, table reconstruction, annotation application, and content validation. When invoking this agent, provide complete section data including all blocks, types, and…
not rated 3 27d ago A 0 tokens
GPL-3.0
pdf-section
18Agent Claude Code
Validates section headers and builds document structure using semantic understanding.
not rated 3 27d ago A 14 tokens
GPL-3.0
Agent Claude Code
Validates suspicious blocks using Claude's semantic understanding to achieve >90% accuracy.
not rated 3 27d ago A 21 tokens
GPL-3.0
Agent Claude Code
Merges split tables across pages and columns into complete structures.
not rated 3 27d ago A 16 tokens
GPL-3.0
pdf-table
21Agent Claude Code
Semantic table analysis using Claude for deep understanding of structure and meaning.
not rated 3 27d ago A 15 tokens
GPL-3.0
Agent Claude Code
Plans optimal PDF extraction workflows based on document characteristics.
not rated 3 27d ago A 15 tokens
GPL-3.0
Agent Claude Code
Cleans and normalizes extracted text, fixing common PDF extraction issues.
not rated 3 27d ago A 18 tokens
GPL-3.0
Agent Claude Code
Plans PDF extraction workflows using DAG-based execution for optimal performance.
not rated 3 27d ago A 17 tokens
GPL-3.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: