Toolverse
All skills
Data Science

markdown-tools

by daymade

Converts documents to markdown with multi-tool orchestration for best quality. Supports Quick Mode (fast, single tool) and Heavy Mode (best quality, multi-tool merge). Use when converting PDF/DOCX/PPTX files to markdown, extracting images from documents, validating conversion

Installation

Pick a client and clone the repository into its skills directory.

Installation

Quick info

Author
daymade
Category
Data Science
Views
35
GitHub repo

About this skill

Converts documents to markdown with multi-tool orchestration for best quality. Supports Quick Mode (fast, single tool) and Heavy Mode (best quality, multi-tool merge). Use when converting PDF/DOCX/PPTX files to markdown, extracting images from documents, validating conversion quality, or needing LLM-optimized document output.

How to use

  1. Zainstaluj wymagane zależności: uruchom uv tool install "markitdown[pdf]", następnie pip install pymupdf4llm i brew install pandoc (lub odpowiednik dla Twojego systemu operacyjnego). Te pakiety umożliwiają obsługę różnych formatów dokumentów.

  2. Przygotuj dokument do konwersji — obsługiwane są pliki PDF, DOCX, PPTX i XLSX. Upewnij się, że masz dostęp do pliku na swoim komputerze.

  3. Aby szybko skonwertować dokument, użyj Trybu Szybkiego (domyślny): uruchom uv run --with pymupdf4llm --with markitdown scripts/convert.py nazwa_pliku.pdf -o output.md. Narzędzie automatycznie wybierze najlepszy konwerter dla Twojego formatu.

  4. Jeśli potrzebujesz najwyższej jakości konwersji złożonych dokumentów, dodaj flagę --heavy: uv run --with pymupdf4llm --with markitdown scripts/convert.py nazwa_pliku.pdf -o output.md --heavy. Tryb Zaawansowany uruchamia wiele narzędzi równolegle i łączy najlepsze fragmenty wyniku.

  5. Aby sprawdzić, które narzędzia są dostępne dla Twojego dokumentu, uruchom uv run scripts/convert.py --list-tools. Wynik markdown znajdziesz w pliku output.md.

Related skills

ml-paper-writing

by davila7

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation

Data Science
2681

threejs

by mrgoonie

Build 3D web apps with Three.js (WebGL/WebGPU). Use for 3D scenes, animations, custom shaders, PBR materials, VR/XR experiences, games, data visualizations, product configurators.

Data Science
1743

web-artifacts-builder

by anthropics

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX

Data Science
37124

market-research-reports

by davila7

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for

Data Science
16115

skill-creator

by anthropics

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Data Science
59147

pptx

by anthropics

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Data Science
134310