Convert PDF documents into local Markdown and extracted image assets.
npx skills add https://github.com/black-yt/skills --skill pdf-parsing
Please help me install this Agent Skill. Skill: pdf-parsing Source: https://github.com/black-yt/skills/tree/main/pdf-parsing Command: npx skills add https://github.com/black-yt/skills --skill pdf-parsing
This Skill removes the friction of reading PDFs by converting them into local Markdown that is searchable, copyable, and easier to inspect, while also extracting embedded images for later review.
structai.read_pdf to parse a PDF once and reuse the generated local Markdown on subsequent reads.Ask the assistant to parse the attached PDF into local Markdown and extracted images, then review the generated full.md file instead of the original document.
High-intent search queries and answers about installing and using this skill.
To convert a research paper PDF into searchable Markdown, the Skill parses the document using MinerU token authentication and outputs a local full.md file alongside extracted image assets for offline inspection and section navigation.
Yes, you can extract images and figures from a PDF. The Skill captures embedded images and layout resources during parsing, saving them as local assets so you can review figures and tables without reopening the original document.
Yes, you need a MinerU token to parse PDFs into Markdown. The Skill requires structai.read_pdf configured with MinerU token authentication to handle document conversion, proxy-aware retries, and local cache reuse.
Local cache reuse works by storing the generated Markdown and extracted images from the initial parse. When you process the same PDF again, the Skill retrieves the cached output directly, avoiding redundant MinerU parsing and reducing wait time.
The best way to handle proxy-related failures during PDF text extraction is through the Skill's built-in proxy-aware retry handling, which manages MinerU token setup and automatically retries failed parsing requests.
Converting a PDF to Markdown enables searchable, copyable text and quick section navigation. You can inspect extracted figures locally and reuse the Markdown output, removing the friction of navigating bulky original PDF documents.
cat-xierluoConvert PDF, Word, PowerPoint, and images to Markdown via the MinerU API.
u9401066Extract text, figures, and citations from PDFs into Markdown.
black-ytBuild and debug structured LLM workflows with the StructAI Python toolkit.
dz07Convert .docx files to Markdown and extract embedded images.