{"id":11432,"plugin_id":"plugin_asdk_app_6a845baf5fb88191a0ddd23a38550254","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T22:59:28.019Z","digest":"5f459e88f3f5e684d06ee9751cc794ccebd484876a45cf09f1160db64203802e","against":null,"payload":{"name":"ilovepdf-pdf-ocr","description":"Extract and make searchable the text in scanned PDFs using OCR (Optical Character Recognition).\nUse this skill whenever the user wants to make a scanned PDF searchable, extract text\nfrom an image-based PDF, or run OCR on a document.\n","included_files":[],"skill_md_contents":"---\nname: ilovepdf-pdf-ocr\ndescription: |\n  Extract and make searchable the text in scanned PDFs using OCR (Optical Character Recognition).\n  Use this skill whenever the user wants to make a scanned PDF searchable, extract text\n  from an image-based PDF, or run OCR on a document.\n---\n\n# iLovePDF — OCR PDF\n\nRuns Optical Character Recognition (OCR) on a scanned or image-based PDF, producing\na searchable PDF where the text can be selected, copied, and indexed.\n\n## When to Use\n\n- \"Run OCR on this scanned PDF\"\n- \"Make this PDF searchable\"\n- \"Extract text from this scanned document\"\n- \"OCR this PDF in Spanish\"\n- \"Convert this image PDF to a text-selectable PDF\"\n\n## Tool to Call\n\nUse the `ilovepdf` or `ilovepdf_attach` MCP tool with `tool: \"pdf-ocr\"`.\n\nUse `ilovepdf_attach` when the user has attached a file to the chat message.\nUse `ilovepdf` when the user provides a file URL.\n\n## Accepted File Types\n\n`.pdf`\n\n## Options\n\n| Option          | Type            | Description                                     | Default      |\n| --------------- | --------------- | ----------------------------------------------- | ------------ |\n| `ocr_languages` | array of string | Language codes for OCR engine                   | `[\"eng\"]`    |\n\n### Language Codes\n\nPass `ocr_languages` when the user has stated the document language. Default is English.\n\nCommon codes:\n\n| Language   | Code  |\n| ---------- | ----- |\n| English    | `eng` |\n| Spanish    | `spa` |\n| French     | `fra` |\n| German     | `deu` |\n| Italian    | `ita` |\n| Portuguese | `por` |\n| Chinese (Simplified) | `chi_sim` |\n| Chinese (Traditional) | `chi_tra` |\n| Japanese   | `jpn` |\n| Korean     | `kor` |\n| Arabic     | `ara` |\n| Russian    | `rus` |\n\nMultiple languages can be combined: `[\"spa\", \"eng\"]`.\n\nFull list of supported codes: `afr, amh, ara, asm, aze, bel, ben, bod, bos, bul,\ncat, ces, chi_sim, chi_tra, dan, deu, ell, eng, epo, est, eus, fas, fil, fin, fra,\ngla, gle, glg, guj, heb, hin, hrv, hun, hye, ind, isl, ita, jpn, kan, kat, kaz,\nkhm, kor, lao, lat, lav, lit, mal, mar, mkd, mlt, mon, msa, mya, nep, nld, nor,\npan, pol, por, ron, rus, sin, slk, slv, spa, sqi, srp, swa, swe, tam, tel, tgl,\ntha, tur, ukr, urd, vie, yid`\n\n## Example Calls\n\n```json\n// OCR in English (default)\n{ \"tool\": \"pdf-ocr\", \"options\": { \"ocr_languages\": [\"eng\"] } }\n\n// OCR in Spanish + English\n{ \"tool\": \"pdf-ocr\", \"options\": { \"ocr_languages\": [\"spa\", \"eng\"] } }\n\n// OCR in Japanese\n{ \"tool\": \"pdf-ocr\", \"options\": { \"ocr_languages\": [\"jpn\"] } }\n```\n\n## Notes\n\n- The widget handles the upload, processing, and download — do not claim the operation\n  is complete before the widget confirms.\n- If the user does not mention a language, default to `[\"eng\"]` and let the widget\n  provide a language selector as fallback.\n- OCR works on scanned/image PDFs. A PDF that already has a text layer may not benefit\n  from this operation.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}