Extract raw text from local PDF files or remote URLs into Obsidian inbox notes.
npx skills add https://github.com/ethan-rio/skills --skill ingest-pdf-ethan-rio
Please help me install this Agent Skill. Skill: ingest-pdf Source: https://github.com/ethan-rio/skills/tree/main/skills/personal_agent/ingest-pdf Command: npx skills add https://github.com/ethan-rio/skills --skill ingest-pdf-ethan-rio
Manually copying and formatting text from PDFs (academic papers, books, reports) into Obsidian is time-consuming and prone to formatting errors, slowing down personal knowledge capture and research workflows.
Use the ingest-pdf skill to extract text from the attached research paper PDF and save it as a new Obsidian inbox note.
High-intent search queries and answers about installing and using this skill.
To convert a PDF to an Obsidian note, this Skill extracts raw text from local files or remote URLs and generates a metadata-tagged inbox note. It automatically includes source attribution, word count, and truncated full text for quick review.
Yes, you can extract text directly from a remote PDF URL. The Skill processes remote .pdf links via curl, eliminating the need to manually download files before converting them into Obsidian notes.
Yes, this PDF text extraction tool works with local chat attachments. It supports inputs from chat attachments, slash commands, and direct .pdf URLs to capture research papers or reports into your Obsidian vault.
The best way to extract text from academic papers for knowledge management is using this Skill to bypass manual copy-pasting. It formats extracted content into searchable Obsidian notes with proper source attribution and word counts.
Yes, you need pdftotext, pypdf, and curl installed. These dependencies handle PDF text extraction and remote file retrieval to successfully generate formatted Obsidian inbox notes from your documents.
Generated Obsidian notes contain truncated full text to prevent overwhelming your vault with large documents. This design supports quick review and downstream processing by second-brain and note synthesis workflows.
breakcafeExtract text from local PDFs, URLs, and WhatsApp attachments to stdout.
ethan-rioExtract entity-relation triples from Obsidian notes into graph memory stores.
ai-in-pmAutomate note creation, management, and search in Obsidian vaults.
anilcan-karaExtract text from PDFs and scanned documents using pymupdf or marker-pdf.
