I turned a photo of my handwriting into a real font, then open-sourced the whole pipeline

Short summary

A developer built an open-source pipeline that converts a single photo of handwriting into an installable TTF font using sharp, potrace, and svg2ttf — all running locally via npm with no system dependencies. A Claude Code skill wraps the pipeline, using vision to label letters and critique its own output. The project is MIT-licensed and available on GitHub and npm.

• •Open-source MIT pipeline converts handwriting photos to TTF/WOFF2 fonts with zero system dependencies
• •Claude Code skill automates letter labeling, vectorization, and self-critique of font output
• •Six deterministic steps: adaptive threshold, blob detection, vision labeling, potrace vectorization, metrics, and TTF assembly

Generated with AI, which can make mistakes.