The Document Importer skill simplifies the process of ingesting legacy or external documentation into a codebase by automatically converting formats such as PDF, DOCX, PPTX, XLSX, and HTML into editable Markdown. It goes beyond simple conversion by applying rigorous structural cleanup—fixing table alignments, normalizing headings, and removing artifacts like page numbers or watermarks—ensuring that the imported content meets professional documentation standards and is ready for version control or further AI-assisted refinement.
주요 기능
01Supports multi-format conversion for PDF, Word, Excel, PowerPoint, and HTML
02291 GitHub stars
03Content sanitization to manage size constraints and strip unnecessary system tags
04Automatic structural cleanup including ATX heading normalization and 80-character line wrapping
05Optional hand-off to document generation skills for automated rewriting and polishing
06Artifact removal to strip page numbers, headers, footers, and watermarks
사용 사례
01Migrating legacy PDF project specifications into a repository's internal documentation
02Converting requirement spreadsheets into editable Markdown tables for better version control
03Transforming a PowerPoint slide deck into a structured technical README