Convert PDFs and documents into structured Markdown with metadata.
npx skills add https://github.com/Gami19/rd-strands-agents --skill pdf-convert
Please help me install this Agent Skill. Skill: pdf-convert Source: https://github.com/Gami19/rd-strands-agents/tree/main/strands-py/backend/agent/skills/pr/pdf-convert Command: npx skills add https://github.com/Gami19/rd-strands-agents --skill pdf-convert
PDFs and other document formats often block quick review, archiving, and collaboration. This Skill converts PDFs, DOCX, PPTX, and related formats into high-quality Markdown, preserving structure, tables, figures, and metadata to feed downstream distillation and review workflows.
Use the batch workflow to convert documents to Markdown for a given project.
High-intent search queries and answers about installing and using this skill.
You can convert PDFs to Markdown with tables and figures preserved by using a deterministic DocLing pipeline. It retains structural elements and figure captions to ensure faithful downstream processing of client materials.
Yes, you can batch convert invoices, proposals, and reports into structured Markdown. The workflow applies OCR and table recognition to transform multiple client deliverables into publish-ready text.
DocLing supports configurable OCR and VLM pipelines for document conversion. These options enable high-quality extraction from PDFs and other formats, ensuring accurate metadata and structure retention.
The best way to extract metadata from PDFs for reproducible processing is using a deterministic conversion pipeline. It outputs frontmatter metadata alongside Markdown, supporting downstream distillation and review workflows.
You can transform DOCX and PPTX files into Markdown for collaboration by running them through the DocLing conversion workflow. This unblocks quick archiving and review by converting blocked formats into structured text.
While VLM enhances PDF table recognition, the pipeline is strictly local and deterministic. Users should configure OCR and VLM options appropriately to handle complex tables and ensure reproducible Markdown output.
smilebank7Extract text, tables, and equations from PDFs, PPTX, DOCX, and images into Markdown.
makramabExtract text, tables, metadata, and images from PDF, Office, image, HTML, and archive documents.
tassiovaleExtract text and bounding boxes from PDFs, Office files, and images.
KanakMalpaniA tagline describing your app.
