Stats
Actions
Tags
From dstoic
Convert PDF files to LLM-ready markdown, DocTags, or JSON using Docling. Handles analysis, summarization, OCR, and batch processing with token savings estimates.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dstoic:convert-pdfhaikuThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Convert PDF files using IBM's Docling toolkit.
Convert PDF files using IBM's Docling toolkit.
dstoic:install-dependency skill to ensure docling is installed$1 (required), format (default: markdown), OCR flag./converted/ if missingsource .venv/bin/activate
docling --to markdown --image-export-mode placeholder input.pdf -o converted/
./converted/See reference.md for format selection guide, batch processing, VLM pipeline, and OCR options.
npx claudepluginhub digital-stoic-org/agent-skills --plugin dstoicConverts heavy document formats (PDF, Word, Excel, PowerPoint, and others) to token-efficient Markdown/CSV with structurally-aware digest compression. Use when Claude needs to read documents without excessive context budget.
Converts Word (.docx) files to clean markdown using markitdown for LLM context. Useful for document analysis, summarization, or Q&A without sending content to LLMs.
Parses PDFs, DOCX, PPTX, HTML, images (20+ formats) to Markdown/HTML/JSON/text with layout/tables/OCR. Chunks for RAG pipelines; batch converts via DocumentConverter.