PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.

LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

Claude Code and Codex SKILLs for PDF, Excel, Word, and PowerPoint manipulation — extraction, forms, formulas, tracked changes, adapted from Anthropic skills.