Draw Your Font

draw-your-font

Photo of handwritten letters in → installable font out. You do the seeing (find and label letters, judge quality); the CLI does all geometry (trace, metrics, font assembly). Never edit SVG paths or coordinates yourself.

Setup in Hermes (once per session)

The CLI is the pinned npm package draw-your-font@0.1.0 — run it via npx (Node ≥ 18 required, no global install needed):

npx -y draw-your-font@0.1.0 --help

Wherever the examples below show $DYF, use npx -y draw-your-font@0.1.0. Shell variables do not persist between tool calls, so paste the full command each time. Everything runs locally; the user's handwriting never leaves the machine.

Photos arrive in Hermes either as a file path in the message or via the gateway image cache — use the actual file path with the CLI. When a photo lands in the conversation with no path, ask the user for the file (the CLI needs a real file, not your memory of the image).

Do the visual steps (contact sheets, previews, glyph sheets) by loading the PNGs with vision_analyze.

Decide the flow

• User has no photo yet → offer the template: print, write, photograph.
• User shares photo(s) of handwriting → main flow below.
• User pasted an image but there is no file path → you can see it, but the CLI needs a file. Ask them to drag the image file into the terminal (that inserts its path) or give the path directly. Do not proceed from memory.
• User wants changes to a font built this session → Refine section.

Template flow (best quality)

$DYF template -o template.pdf --charset minimal   # or: spanish

Tell the user: print it, write one character per box with a dark pen (0.5 mm+), keep the letter sitting on the solid line, then photograph each page from above in good light and share the file paths. The grid prints in light grey and vanishes during processing - only their ink survives.

Main flow: photo(s) → font

1. Segment. Works for template pages and freeform photos alike:

$DYF segment photo1.jpg photo2.jpg -d work

2. Look, then label. Load work/contact-1.png with vision_analyze (one per photo): every detected blob is numbered. This is the step where your eyes matter - check:

• Did every written character get exactly one box? A letter drawn with separate strokes may appear as two boxes (relabel handles it: give the main box the character and mark the fragment ""), and two touching letters may share one box (ask the user to re-shoot just those, or accept the gap).
• Junk boxes (shadows, ruled lines, smudges, page edges) → label them "".

Then write work/labels.json mapping blob id → character, e.g. {"0": "A", "1": "B", "7": "", "8": "a"}:

• Template page: order is the charset order printed on the template - verify against the sheet instead of trusting it blindly. minimal order: A–Z, a–z, 0–9, then .,;:!?'"-()@#&+/$; spanish appends ÑñÁÉÍÓÚáéíóúü¿¡.
• Freeform: identify each letter from the contact sheet. Uppercase vs lowercase for shape-twins (S/s, O/o, C/c, X/x…) is decided by relative size and position - compare against neighbors you're sure of.
• The user told you what they wrote (e.g. "ABC then abc")? Trust it, map in reading order (top row first, left to right), and verify visually.
• Same letter appears twice → label the better-drawn one, "" the other.

3. Build.

$DYF build -d work --labels work/labels.json --name "Dan's Hand"

Name the font after the user (ask if unclear - one short question max).

4. Judge before delivering. Load work/preview.png and work/glyphs.png with vision_analyze and critique like an art director:

• Broken or blotchy letters (bad trace) → often a faint pen stroke; try --weight 1, or ask for a re-shoot of just that letter.
• Everything too thin/thick → rebuild with --weight 1 / --weight -1.
• Jagged edges → rebuild with --smooth 1.5 (up to 2).
• A letter placed wrong (e.g. a g not descending) → usually a mislabel; fix labels.json and rebuild.
• Filled-in bowls (b, o, g look solid): should never happen - if it does, the crop is smudged; ask for a re-shoot.