MCP App StoreMCP App Store
from pdf2md-by-mineru-api-skill19
Converts complex PDFs into high-quality Markdown with images and tables using the MinerU API for superior AI analysis.
This skill solves the problem of poor PDF parsing by converting documents into high-fidelity Markdown. It leverages the MinerU (TextIn) API to preserve complex layouts, tables, and images, allowing the agent to perform visual and structural analysis on the content.
Use this skill whenever the user provides a PDF file that requires precise reading, especially if the document contains complex formatting, mathematical formulas, or embedded images.
convert_pdf.py for handling the API conversion process.Compatible with any agent capable of running Python scripts and reading local files (Claude Code, Cursor, Codex, Gemini CLI, etc.)
This skill has not been reviewed by our automated audit pipeline yet.
Doc Cleaner
Convert PDF, DOCX, XLSX and text files into clean, structured Markdown with CJK and table support; supports offline or AI-enhanced modes.
Filtrix Video Gen (MCP)
Submit and manage text- or image-to-video generation jobs via Filtrix's Remote MCP API, including polling and downloading completed videos.
MUAPI Photo Pack Generator (Identity-Lock)
Generate themed photo packs from a single reference image while preserving the exact facial identity and enforcing identity-lock guardrails.
QwenCloud Model Selector
Advisory skill that recommends the best QwenCloud model and parameters for a task, balancing quality, speed, and cost.
Invoice Entity Bounding Box Mapping (Duplicate Handling)
Patches OCR invoice entity-to-bounding-box mapping to avoid shared boxes for duplicate values, reverse-search amounts sections, and ensure coordinate uniqueness
PPTX to HTML (MinerU)
Convert PowerPoint (.pptx) slides into web-ready HTML using the MinerU extractor; supports local files and URLs and preserves text and basic structure (requires
vLLM-Omni Video Generation
Generate videos (text→video, image→video, text+image→video) using vLLM-Omni and Wan2.2-style diffusion models, with guidance on parameters and performance trade
PhD Deep Read Workflow
A guided CLI workflow that extracts text from academic PDFs (PyMuPDF + Tesseract), generates structured Obsidian notes, and creates JSON Canvas critical-thinkin