docstrange
por shhdwi
Personal DevelopmentResumo
Document extraction API by Nanonets.
Descrição
O que esta skill faz
DocStrange is a document extraction API by Nanonets. It converts PDFs and images to markdown, JSON, or CSV, returning per-field confidence scores for each extracted value.
Per-field confidence scores (0-100) let you automatically flag uncertain extractions for manual review rather than trusting all output blindly.
Quando usá-la
- Extracting invoice fields from supplier PDFs
- Parsing receipts for expense reports
- Converting scanned bank statements to structured data
- Digitizing paper forms into JSON
- OCR-ing printed documents for search indexing
Exemplo de fluxo de trabalho
User asks: Extract the invoice number, date, vendor, and total from this invoice PDF
- 1
Receives the PDF file path from the user
- 2
Sends a POST request to /api/v1/extract/sync with output_format=json and field list ["invoice_number", "date", "vendor", "total"]
- 3
Adds include_metadata=confidence_score to the request
- 4
Parses the response and flags any field with a confidence score below 80 for manual review
JSON object with invoice_number, date, vendor, and total values, each annotated with a 0-100 confidence score
Requisitos
- Nanonets DocStrange account
- DOCSTRANGE_API_KEY environment variable
Instalação
clawhub install shhdwi/docstrangeExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.