Agent skill · data analytics · sundial-org
deepread
OCR that never fails silently. Multi-pass document processing API with intelligent quality review flags. Extract text and structured data from PDFs with AI-powered confidence scoring. Free tier - 2,000 pages/month.
Why this skill is useful
Provides a specialized API for document processing with AI-powered confidence scoring that the AI wouldn't reliably generate on its own.
What it needs
Requires deepread account access. About 7k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.
What this skill does
DeepRead - Production OCR API OCR that never fails silently. Process PDFs and extract structured data with AI-powered confidence scoring that tells you exactly which fields need human review. What This Skill Does DeepRead is a production-grade document processing API that reduces human review from 100% to ~10% through intelligent quality assessment. Core Features: Text Extraction: Convert PDFs to clean markdown Structured Data: Extract JSON fields with confidence scores Quality Flags: AI determines which fields need human verification (hilflag) Multi-Pass Processing: Multiple validation passes for maximum accuracy Multi-Model Consensus: Cross-validation between models for reliability Free Tier: 2,000 pages/month (no credit card required) Setup 1. Get Your API Key Sign up and create an API key: Save your API key: 2. Clawdbot Configuration (Optional) Add to your clawdbot.config.json5: 3. Process Your First Document Option A: With Webhook (Recommended) Option B: Poll for Results Usage Examples Basic OCR (Text Only) Extract text as clean markdown: Response when completed: Structured Data Extraction Extract specific fields with confidence scoring: Response includes confidence flags: Complex Schemas (Nested Data) Extract arrays and nested objects: Page-by-Page Breakdown Get per-page OCR results with quality flags: Response: When to Use This Skill ✅ Use DeepRead For: Invoice Processing: Extract vendor, totals, line items Receipt OCR: Parse merchant, items, totals Contract Analysis: Extract parties, dates, terms Form Digitization: Convert paper forms to structured data Document Workflows: Any process requiring OCR + data extraction Quality-Critical Apps: When you need to know which extractions are uncertain ❌ Don't Use For: Real-time Processing: Processing takes 2-5 minutes (async workflow) Batch >2,000 pages/month: Upgrade to PRO or SCALE tier How It Works Multi-Pass Pipeline The pipeline automatically handles: Document rotation and orientation correction Multi-pass valida …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sundial-org/deepread