跳到主要内容
Supermarket
返回能力市场
Claude Skill
programming
MIT

draw-your-font

Turn a photo of your handwriting into a real font (TTF/WOFF/WOFF2) - free, open source, no uploads. Node CLI + Claude Code skill.

danilo-znamerovszkijdanilo-znamerovszkij
87/ 100

公开评测 · 综合采用结论

证据充分,整体质量与安全表现优秀

查看评测依据 评测我的项目基于公开项目证据,非安全认证或安装推荐
795stars
74forks
最近更新 1个月前
评测生成时间(北京时间)
本报告引擎
v3.10.0
当前引擎
v3.16.0

本报告与当前引擎使用不同规则;原分数不会自动更新,不同版本的分数不宜直接对比。

重新评测此项目

进入后确认来源与额度,提交才会创建任务。

Evaluation report

综合采用结论

87
A
满分 100
值得推荐低风险
决策摘要

证据充分,整体质量与安全表现优秀

76%
中置信度
88
文档
100
安全
86
质量
90
活跃
51
采用
  • 基础评测完成+25/25确定性评分与静态安全扫描已完成
  • README 有效证据+9/253,515 个去重后的有效字符
  • 独立证据来源+12/203 类非重复证据,重复文件不叠加
  • 仓库元数据+10/10已取得仓库状态与采用数据
  • 活跃记录+5/5已取得最近提交时间
  • AI 复核+15/15已完成结构化 AI 证据复核
How it works · 流程图

手写照片转字体流程

README描述了从照片到字体的连续处理步骤,适合用流程图表示。

AI 提取 · 证据约束

左右滑动查看完整图示

手写照片转字体流程README描述了从照片到字体的连续处理步骤,适合用流程图表示。输入照片生成裁剪图标注后矢量轮廓生成字体照片输入输入分割与识别处理标注字母处理矢量化处理度量调整处理字体输出输出
图示依据
  • • README中'How it works'部分列出流程
  • • CLI命令segment和build对应步骤
  • • 描述'potrace vectorize'和'shared em-square metrics'
五维表现
将手写照片转为字体的工具,价值明确且示例具体。文档清晰,CLI与Skill双路径。主要缺口是限制与错误处理说明不足,设计证据有限。
质量证据
  • README描述'Turn a photo of your handwriting into a real font'
  • CLI参考表列出template、segment、build、make、preview命令
  • 示例命令'npx draw-your-font make photo.jpg --chars "ABCabc" --name "My Hand"'
  • 工作原理部分说明'adaptive threshold...potrace vectorize...shared em-square metrics'
  • FAQ提及'Kerning, ligatures, letter randomization? v2'
采用建议
优势
  • 问题与用途描述
  • 有效 README
  • 安装或接入步骤
  • 可执行示例
  • 未发现已知高风险模式
关注点
  • 缺少限制、权限或边界
  • 缺少限制、权限或边界说明
  • 错误处理或排障信息缺失
  • 设计细节如安全默认值未展示
  • 文档未提及具体版本或依赖约束
适合

希望将手写体转为字体的个人用户、需要本地处理、注重隐私的用户、使用Claude Code的开发者、需要TTF/WOFF/WOFF2格式的网页开发者

不建议直接用于

需要高级字体功能如连字、随机化的用户、需要图形界面编辑器的用户

也有自己的公开项目?先看完证据,再用当前规则生成独立报告。

评测我的项目 →
文档证据
88/100
问题与用途描述10 分
有效 README12 分
安装或接入步骤14 分
可执行示例16 分
输入、参数或工具说明11 分
输出或结果说明9 分
限制、权限或边界12 分
错误处理或排障8 分
许可证信息5 分
结构化章节3 分
安全证据
低风险
未发现已知高风险模式

静态扫描不是安全保证,生产接入前仍应人工复核权限和数据边界。

优先改进清单
  1. 01补充限制、权限或边界
方法、证据与局限展开
数据来源

GitHub Repository API

扫描范围

3 个文件 · 11,495 字符

评测引擎

v3.10.0 · AI 复核已启用(deepseek-chat)

局限
  • 静态评测不会安装或执行项目代码
  • 安全扫描基于高信号文件与已知模式,不能替代人工审计
  • 流行度只反映采用程度,不代表安全或工程质量

30 天热度趋势

README

draw-your-font

Turn a photo of your handwriting into a real font (TTF/WOFF/WOFF2) - free, open source, no uploads, no credits.

Draw your alphabet on paper. Take a photo. Get your font.

A photo of a handwritten alphabet in a spiral notebook becoming an installable font

This is a real one-shot result: dim light, spiral binding, page shadow. One photo in, installable font out.

Use it as a Claude Code skill (the fun way)

npx skills add danilo-znamerovszkij/draw-your-font

Then in Claude Code, invoke the skill and hand it your photo:

/draw-your-font "here's a photo of my handwriting - make my font" (drag the photo into the terminal)

Claude finds your letters in the photo, labels them with vision, builds the font, shows you a preview, and critiques its own work. Iterate by talking:

  • "make it rounder" / "a bit bolder"
  • "the g looks bad" - it shows you the crop and fixes or asks for a re-shoot
  • "give me woff2 + css for my website"
  • "how readable is it?" - a legibility score and the two worst letter pairs

No photo yet? Say "give me a font template" and you get a printable PDF grid: write your alphabet with a dark pen, photograph the pages, and hand them back. Messy freeform photos work too. Napkins, notebooks, spiral binding, bad lighting: that's what the vision step is for.

Everything runs locally on your machine. Your handwriting never leaves it.

Use it as a CLI (no AI at all)

The skill is a thin layer over a deterministic npm CLI. It works on its own when you can tell it what you wrote:

# freeform photo, you know the order you wrote in:
npx draw-your-font make photo.jpg --chars "ABCabc" --name "My Hand"
# → MyHand.ttf - double-click, install, done.

# best quality: print a template, fill it, photograph:
npx draw-your-font template -o template.pdf --charset minimal   # or: spanish
npx draw-your-font make page1.jpg page2.jpg --charset minimal --name "My Hand"

Pure npm, zero system dependencies: no FontForge, no ImageMagick, no potrace binary. Works on macOS / Linux / Windows wherever Node ≥ 18 runs.

CLI reference

CommandWhat it does
templateprintable A4 PDF grid (--charset minimal|spanish)
segment <photos…>find letters → crops + numbered contact sheet + blobs.json
buildlabeled crops → font (--labels / --chars / --charset)
make <photos…>segment + build in one shot
previewrender any text with the built font

Refinement flags: --smooth 0..2 (rounder curves), --weight=-2..2 (thinner/bolder), --formats ttf,woff,woff2,css (web-ready + @font-face snippet). Run draw-your-font --help for everything.

How it works

photo ──► adaptive threshold ──► blob detection ──► label (Claude / you / template order)
      ──► potrace vectorize ──► shared em-square metrics ──► TTF/WOFF/WOFF2 + preview

The craft is in the metrics step: every character has a vertical band in a shared 1000-unit em square (cap height, x-height, descender depth), so your g hangs below the line and your o stays small. That's what makes it feel like a font instead of a ransom note. Vectorization is potrace, the same engine inside FontForge and Inkscape. AI never draws your letters; it only finds, labels, and judges them.

FAQ

Who owns the font? You. 100%, commercial use included. It's your handwriting.

Why is this free when Calligraphr charges $8/month? Their cost is servers and a browser editor. Here your machine does the work and the agent is the editor.

Kerning, ligatures, letter randomization? v2. The pipeline (fonttools calt) is planned; the current output is a clean single-variant font.

License

MIT. Draw something.