Skill UI

Implements a robust caching strategy by using the SHA-256 hash of file content as the primary key, instead of the file path. This pattern is essential for high-cost file processing pipelines (like OCR, PDF parsing) because it ensures cache hits survive file renaming or moving, while still automatically invalidating entries when the content changes. It adheres to the Single Responsibility Principle (SRP) by isolating caching logic into a service layer wrapper.

Fast local parsing of PDFs, Office files, and images with per-token bounding boxes. Extract spatial text, run OCR on scans, produce layout-preserved JSON for RAG, batch-ingest folders, and render pages to PNG for multimodal agents. Fully local, no cloud API.

Implements a robust caching strategy by using the SHA-256 hash of file content as the primary key, instead of the file path. This pattern is essential for high-cost file processing pipelines (like OCR, PDF parsing) because it ensures cache hits survive file renaming or moving, while still automatically invalidating entries when the content changes. It adheres to the Single Responsibility Principle (SRP) by isolating caching logic into a service layer wrapper.

This skill converts Microsoft Word documents (.docx) into Markdown format. It is essential for accurately analyzing, summarizing, or extracting data from proprietary Word files, as direct parsing is unreliable. It supports single files, batch processing of folders, and is designed to coordinate with sibling skills (PDF and Excel) when handling mixed document types to ensure no data is skipped.

Extract structured fields from documents like invoices, payslips, and contracts with page grounding. Each value cites its source page and confidence score. Missing values are reported as not found instead of hallucinated. Supports PDF, PNG, and DOCX files. Ideal for accounting, compliance, and data parsing tasks where accuracy is critical. Uses Stipple API for processing.

This skill enables deep web scraping, screenshots, and PDF parsing using the Firecrawl API. It extracts content from web pages, handles page interactions like clicking and scrolling, and processes multiple URLs in batch. Ideal for automated data collection tasks requiring robust extraction capabilities.