document-processor-api

Part of the Nutrient skills collection, this skill enables AI agents to extract text from PDFs as structured, semantic Markdown using Nutrient's document processing APIs, working with Claude Code, Codex, Cursor, and other agents.

Generate finished PDFs from Markdown or HTML — accessible PDF/UA, archival PDF/A, watermarks, batch — with built-in conformance verification.

Find the most relevant passages in an already-extracted document (the text or Markdown output of pdf-to-markdown / pdf-to-text) with ranked (BM-25) search.

Extract layout-preserving plain text from a PDF.

Remediate existing PDFs: auto-tag with PDF/UA semantic structure via the Nutrient DWS Accessibility API, then check the result with the bundled verifier.

Extract text as structured, semantic Markdown from a PDF.

Skills for developing with Nutrient SDKs: Web Viewer, Document Authoring, Mobile (iOS/Android/React Native/Flutter/MAUI), Server (Python/Java/Node.js/.NET), self-hosted Nutrient Document Engine, and Nutrient AI Assistant.

AI agent skills for Nutrient APIs and SDKs — works with Claude Code, Codex, Gemini CLI, Cursor, and 35+ more agents

Document processing skills powered by the Nutrient Document Web Services API. Includes the document-processor-api skill (convert, merge, OCR, watermark, redact, sign, optimize) and the document-extraction-api skill (structural parse / Markdown via /extraction/parse).