Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
npx claudepluginhub neuromechanist/research-skills --plugin projectHow this command is triggered — by the user, by Claude, or both
Slash command
/project:doc-process <file-or-directory> [--format markdown|json|text]This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# Document Processing Extract, convert, and structure content from documents. Load the `project:document-processing` skill for reference. ## Process ### 1. Identify Input !echo "Input: $ARGUMENTS" Parse arguments: - First argument: file path or directory - `--format`: output format (markdown, json, text). Default: markdown ### 2. Detect Document Type For each input file, determine processing approach: - Check if PDF has native text layer - Check if input is image (PNG, JPG, TIFF) - Check if input is a directory (batch mode) ### 3. Process Based on document type, use appropriate extrac...
/extractExtracts text from PDF files or directories to Markdown (or TXT) using a multi-backend system with CLI options like --backends and --format.
/convert-to-pdfConverts markdown files to professionally formatted PDFs using pandoc and wkhtmltopdf. Accepts optional custom output path.
Share bugs, ideas, or general feedback.
Extract, convert, and structure content from documents. Load the project:document-processing skill for reference.
!echo "Input: $ARGUMENTS"
Parse arguments:
--format: output format (markdown, json, text). Default: markdownFor each input file, determine processing approach:
Based on document type, use appropriate extraction method:
pymupdf or pdftotextpython-docx or pandocClean up extracted text:
Write output to file(s) in requested format alongside the input.