Detect PDF form fields, fill them, and extract text and tables.
npx skills add https://github.com/Wide-Moat/open-computer-use --skill pdf-wide-moat
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/pdf Command: npx skills add https://github.com/Wide-Moat/open-computer-use --skill pdf-wide-moat
This Skill removes the manual effort required to understand PDFs (including forms), extract their content, and generate or transform new PDF outputs with consistent results.
Ask the Assistant to fill the form in the attached PDF by following the Skill’s form-handling workflow, including field detection and safe population of the output PDF.
High-intent search queries and answers about installing and using this skill.
PDF form filling for scanned documents is handled by detecting fillable fields and adding text annotations to non-fillable areas using layout-safe coordinate handling. This approach applies visual bounding-box annotations directly onto non-fillable form areas.
PDF text and table extraction uses dedicated readers to pull readable content and identify tables from documents. This process yields structured text and table data ready for immediate downstream processing and analysis.
Yes, pypdf supports PDF creation and transformation workflows including merging, splitting, and generating documents. These operations include specific safeguards designed to handle larger files reliably during processing.
Yes, you can convert PDF pages to images for visual annotation. The workflow transforms pages into images to apply visual bounding-box annotations, utilizing PIL and pdf2image for rendering and overlaying.
Detecting real form fields in a PDF requires identifying whether the document contains actual fillable fields. The workflow checks for fill-field identification to determine whether to fill fields or add text annotations.
OpenCoworkAIExtract text, tables, and form fields from PDFs using pypdf and pdf2image.
alibabaExtract text, tables, and metadata from PDF documents into JSON.
Komi-san-kugiExtract text and tables from PDF documents and fill forms.
juliuss1907Extract text from PDFs, scanned documents, and images using OCR.
