This is a wrapper around MinerU's open API for extracting text from PDFs, images, and Office files into Markdown or other formats. It has two modes: flash-extract for quick jobs under 10MB with no auth required, and extract for bigger files that need full-fidelity table/formula/image preservation. The skill handles OCR in 80+ languages and works with URLs or local files. The instructions are thorough about a specific gotcha: when using page ranges with directory output, you need to specify explicit filenames or extracts will overwrite each other. If you're doing document Q&A or conversion work, this gives you a clean pipeline from binary blob to structured text without managing API keys yourself for basic use.

skills.sh installs
9.7K
GitHub stars
54
last updated
Aug 21, 2026

Install

$ npx -y skills add tanis90/pdf-converter-mineru --skill pdf-converter --agent claude-code

Installs into .claude/skills of the current project.

Files

Document to Markdown

Convert PDF, images, Office docs, and more to clean Markdown using the MinerU Open API CLI. No API key needed for basic use.

Language Rule

Reply to the user in the SAME language they use. This is non-negotiable.

Core Workflow

Extraction is often just the first step. The typical flow is:

  1. Extract — Use mineru-open-api to convert the document to Markdown
  2. Read & Process — Help the user with what they actually need

MinerU outputs raw Markdown — it doesn't interpret or restructure the content. If the user asks to "extract the tables", "summarize the paper", or "find the key findings", you need to read the output and do that work yourself. MinerU handles the OCR and layout; you handle the understanding.

Use -o to save to a file when the user wants persistent output (conversion, batch processing). Skip -o and read stdout directly when the content is consumed immediately (summarization, Q&A).

Sponsors

Details

Repository
github.com/tanis90/pdf-converter-mineru
Categories
Frontend Development, Documentation, Office & Documents
First seen
May 16, 2026
1cypress-io avatarcypress-authorcypress-io/ai-toolkitCreates, updates, and fixes Cypress tests (E2E/end-to-end and component tests). Use when the user asks to create tests, add tests, write tests, update tests, te9.5Kskills.sh installs
2grafana avatardashboardinggrafana/skillsBuild, modify, and ship Grafana dashboards as JSON via the HTTP API — panel types (timeseries / stat / gauge / table / heatmap / logs / traces / node-graph), `g9.5Kskills.sh installs
3github avatarpower-bi-report-design-consultationgithub/awesome-copilotPower BI report visualization design prompt for creating effective, user-friendly, and accessible reports with optimal chart selection and layout design.9.5Kskills.sh installs
4nomadamas avatardaishin-report-searchnomadamas/k-skill대신증권 리포트 GitHub Pages 미러에서 최신 HTML 리포트 목록과 원문/설명 페이지를 조회한다.9.4Kskills.sh installs
5github avatarproject-workflow-analysis-blueprint-generatorgithub/awesome-copilotComprehensive technology-agnostic prompt generator for documenting end-to-end application workflows. Automatically detects project architecture patterns, techno9.4Kskills.sh installs
6cloudflare avatarmigrate-to-vinextcloudflare/vinextMigrates Next.js projects to vinext (Vite-based Next.js reimplementation). Load when asked to migrate, convert, or switch from Next.js to vinext. Handles compat9.3Kskills.sh installs