yousufkidiya17/hermes-mobile-modified/handwriting-reader

Claude Code and agent skill by yousufkidiya17/hermes-mobile-modified

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Read handwritten text from images using vision + OCR.

Install

npx vskill@latest install yousufkidiya17/hermes-mobile-modified/handwriting-reader

SKILL.md

The same SKILL.md was published earlier as yousufkidiya17/hermes-mobile-modified/handwriting-reader.

Handwriting Reader

Read and transcribe handwritten text from images. Works with Hindi (Devanagari), English, numbers, and calculations.

When to Use

  • User provides an image with handwritten text
  • User wants to read a note, receipt, or paper from a photo
  • OCR or handwriting transcription needed

Steps

Step 1: Vision Analysis (Primary)

Use vision_analyze with a detailed prompt:

vision_analyze(
image_url="<path>",
question="This is a handwritten note. Read EVERY word carefully, character by character. Transcribe all text exactly as written. Include all numbers, dates, and calculations. Describe handwriting style and any unclear words."
)
Step 2: Install OCR Tools (if needed)
bash
pip install pytesseract Pillow
# Windows: also install Tesseract from https://github.com/UB-Mannheim/tesseract/wiki
# Linux: sudo apt install tesseract-ocr tesseract-ocr-hin
# Mac: brew install tesseract
Step 3: Tesseract OCR (Backup/Detail)
bash
python3 -c "
from PIL import Image
import pytesseract
# For Hindi + English
text = pytesseract.image_to_string(Image.open('image.png'), lang='hin+eng')
print(text)
"
Step 4: Present Results
  • Show full transcription in code block
  • Explain each line/number
  • Translate if needed (Hindi → English)
  • Note handwriting style and clarity

Pitfalls

  • Poor lighting/blurry images reduce accuracy
  • Vision model may misread similar Hindi characters
  • Signatures are usually unreadable (intentional scribble)
  • Always try vision first, Tesseract as backup

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/yousufkidiya17/hermes-mobile-modified/handwriting-reader/badge)](https://verified-skill.com/skills/yousufkidiya17/hermes-mobile-modified/handwriting-reader)

Something wrong with this skill or its page? Tell us.