Transcribe handwritten or scanned documents into Markdown text.
npx skills add https://github.com/jeff-hamm/ai-tools --skill ocr-scan
Please help me install this Agent Skill. Skill: ocr-scan Source: https://github.com/jeff-hamm/ai-tools/tree/main/src/skills/ocr-scan Command: npx skills add https://github.com/jeff-hamm/ai-tools --skill ocr-scan
OCR is a practical solution for turning handwritten or scanned documents into searchable, editable Markdown text. This skill streamlines archival, note-taking, and information sharing by producing consistent Markdown output from image-based sources.
Provide an image file path or directory to OCR and generate per-image Markdown transcripts.
High-intent search queries and answers about installing and using this skill.
To convert handwritten notes to Markdown, you provide an image file path to trigger multi-backend OCR transcription. The system processes the image and generates a per-image .ocr.md file containing the transcribed text and metadata.
Yes, you can batch process a directory of scanned images for OCR transcription. The system recursively scans directories for image files and processes them in batch, writing a separate .ocr.md file next to each source image.
Yes, OCR transcription works with multiple AI backends including easyocr, openai, anthropic, gemini, and others. A centralized model registry automatically selects the best available backend to maximize transcription accuracy.
The best way to OCR handwritten forms and receipts into editable text is using multi-backend OCR with quality-based model selection. This approach automatically chooses the optimal backend to transcribe image-based sources into consistent Markdown transcripts.
The model registry selects the best OCR backend for your images by evaluating quality-based criteria across supported backends. It automatically identifies and utilizes the best available model to maximize transcription accuracy for your handwritten or scanned documents.
OCR scanning generates a per-image .ocr.md output file placed alongside the source image. This Markdown file contains the transcribed text along with provenance and source references for archival and information sharing.
Estrella-231Convert PDFs, DOCX, PPTX, XLSX, HTML, JSON, and XML files into Markdown.
thieungExport Claude Code sessions into structured Markdown with frontmatter metadata.
hmzainjamilExtract text from images and scanned PDFs using PaddleOCR with bounding boxes.
AIDotNetExtract text from images and scanned documents into plain text.
