{"id":97028,"plugin_id":"plugin_asdk_app_6abd51b0891c81918954286cdd388fa3","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-15T06:36:30.264Z","digest":"30b0dc1090e3af5f430c0a8b1bfe66803bf2c5e42ab6b731a0766d35ea161d4f","against":null,"payload":{"description":"Read a PDF or a scanned page from a link and return its text as Markdown. Use for OCR, tables, forms, invoices and long documents.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":206}],"name":"document-reader","skill_md_contents":"---\nname: document-reader\ndescription: Read a PDF or a scanned page from a link and return its text as Markdown. Use for OCR, tables, forms, invoices and long documents.\n---\n# Read a document\n\n1. Get the document as a public link to a PDF or an image.\n2. Choose a document model: call `list_models` with `endpoint` set to `/v1/ocr`, unless the user names one.\n3. Call `read_document` with the `model` and the link as `document`: a PDF goes in as `document_url` and an image as `image_url`. Set `pages` to read part of it. Pages count from zero, so `\"0,2-4\"` is the first page and the third to the fifth.\n4. A long document returns a job id: call `get_job` with it, and again until the pages are ready.\n5. Answer the user's question from the text, or return the Markdown when they asked for the content itself.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}