Skill UI

This workflow provides the primary mechanism for converting complex, live websites into clean, LLM-ready markdown content. It supports single-page scraping using `scrapeUrl`, deep multi-page site crawling with `crawlUrl`, and scalable async crawling for large datasets. Ideal for building robust content ingestion pipelines and reliably extracting structured information from the web.

A comprehensive pipeline for processing, validating, and optimizing scraped web content from Firecrawl. This tool handles markdown cleaning, structured data extraction using Zod validation, content deduplication, and chunking tailored for Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems. It ensures crawled data is standardized, clean, and ready for downstream consumption or knowledge base indexing.

Automates detection and deep exploratory analysis across 200+ scientific data formats, assessing quality, extracting metadata, and recommending visualizations while generating markdown reports that guide downstream workflows and highlight structure and distributions.

Conduct rigorous, multi-database literature reviews with systematic workflows, verified citations in styles like APA or Nature, and AI-enhanced schematics for publication-ready markdown and PDF outputs in biomedical and technical domains.

Analyzes Excel and CSV uploads with DuckDB, inspecting schemas, running SQL, summarizing statistics, and exporting results so users can explore structured data efficiently.

This skill provides direct command-line access to the Paperzilla platform, allowing users to manage, summarize, and retrieve academic research data. Users can fetch canonical papers in markdown format, get the latest project recommendations, analyze paper relevance, export data (JSON/Atom), and provide feedback on recommendations. It is an essential tool for researchers managing a large volume of academic literature.

This skill performs comprehensive Exploratory Data Analysis (EDA) on specialized scientific datasets. It supports over 200 file formats across diverse domains, including chemistry (PDB), bioinformatics (FASTA, BAM), microscopy (TIFF), and spectroscopy. The system automatically detects the file type, assesses data quality and integrity, and generates detailed, format-specific markdown reports, providing deep insights and recommending downstream analyses.

MarkItDown is a powerful tool designed to convert a wide array of file types—including PDF, DOCX, images, audio, and structured data (JSON/XML)—into clean, token-efficient Markdown format. It supports advanced features like OCR for scanned documents, transcription for audio, and AI-enhanced descriptions, making diverse content readily consumable and structured for modern Language Models and AI pipelines.

Provides quick, LLM-optimized summaries for a single academic paper using arXiv IDs or URLs. This skill employs a tiered source fallback system, starting with a structured overview, progressing to full markdown, and finally inspecting the source LaTeX files for deep details. It is designed for rapid comprehension of one specific paper, not for broad literature reviews.

This skill guides the systematic process of conducting comprehensive academic literature reviews. It allows users to search multiple biomedical, scientific, and technical databases (e.g., PubMed, arXiv, Semantic Scholar) to synthesize current knowledge. The output generates professionally formatted reports (Markdown/PDF) with verified citations, and mandatorily integrates AI-generated scientific schematics to enhance visualization and depth, suitable for research papers, meta-analyses, and state-of-the-art reports.

This powerful router analyzes complex document types (scanned, medical, table-heavy, etc.) and determines the optimal conversion pipeline (tools, flags, cleanup) to extract data into various formats like Markdown, JSON, or DOCX. It goes beyond simple text extraction by prioritizing the preservation of document structure, relational data, and high fidelity, ensuring the generated output is accurate for downstream machine processing.

A powerful tool for deterministic and reproducible retrieval of evidence from specialized academic and policy corpora. It supports searching arXiv (preprints), PubMed/PMC (biomedical literature), and US policy documents. Users can check corpus freshness, retrieve stable metadata, and fetch full-document Markdown for high-reliability research tasks.