← ClaudeAtlas

text-to-handwritten-noteslisted

Turn any content (a PDF, pasted text, a solution, a web page, a photo of a page or whiteboard) into pages that look written by hand, either as a phone photo of a real notebook page (squared, lined or Seyès paper) or as a clean iPad page, exported as PDF or PNG. Writes in a bundled default handwriting, or in the user's own handwriting learned from photos of notes they already wrote. Maths is drawn by hand (fractions, sums, integrals, roots, intervals, Greek). Use when the user asks for handwritten notes, notes "à la main", notebook or iPad-style notes, or something written in their own handwriting.
yahyaraissouni/text-to-handwritten-notes-skill · ★ 8 · AI & Automation · score 68
Install: claude install-skill yahyaraissouni/text-to-handwritten-notes-skill
# Text to handwritten notes You turn content into pages that look handwritten. The renderer is `scripts/handnotes.py`. It only needs Python with Pillow and numpy, which are already present in the ChatGPT and Claude code sandboxes. **Default result:** a phone photo of a notebook page on squared paper, in blue ink, written in the bundled default handwriting. If the user asks for nothing special, give them that. **The paper is squared by default in every case.** The user may send only their handwriting and an assignment, only the text they want written by hand, or nothing but a request. Always use squared paper unless they explicitly name another paper or the iPad look. Do not copy the paper from their handwriting photos or from the assignment's layout: a lined or blank photo is only a source of letters. ## Step 0: whose handwriting? Ask once, briefly: *"Send me as many photos of your own handwriting as you can (any pages you already wrote: notes, homework). Otherwise I'll use the default handwriting."* - **No photos:** use the default handwriting. Do not ask again. - **Photos:** learn them first (see *Learning a handwriting from photos* below), then render with `--hand their-hand`. More pages give more samples per letter and a more natural result. 3 to 6 pages is good. ## Step 1: read the input - **PDF:** extract the text with pypdf, pdftotext or your own reader. For a scanned PDF, look at the page images. - **Photo, screenshot, whiteboard:** read it yourself with visio