upstage-ocrExtract plain text with word-level bounding box coordinates from images and scanned documents using Upstage OCR API. Use when user asks to OCR a document, ex...
Install via ClawdBot CLI:
clawdbot install upstage-deployment/upstage-ocrGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://api.upstage.ai/v1/document-digitizationCalls external URL not in known-safe list
https://console.upstage.ai/api/document-digitization/ocrAI Analysis
The skill sends user documents to Upstage's official OCR API endpoint, which is consistent with its stated purpose of extracting text from images. The API key usage follows standard environment variable practices, and there is no evidence of hidden instructions, credential harvesting, or obfuscation. The external endpoint is documented and legitimate, though not in a known-safe list, hence the low risk.
Audited May 10, 2026 · audit v1.0
Generated May 13, 2026
Automatically extract invoice numbers, dates, and line items from scanned invoices. This reduces manual data entry errors and speeds up accounts payable workflows.
Convert scanned legal documents, contracts, and court filings into searchable text with bounding box coordinates for easy reference and archiving.
Extract text from patient intake forms, lab reports, and prescription notes to build searchable electronic health records (EHR).
Extract merchant names, dates, and totals from receipts to automate expense report generation and reimbursement workflows.
Digitize scanned academic papers and books to make them searchable, extract citations, and enable text reuse detection.
Charge per API call or per page processed. Ideal for startups and enterprises with variable OCR volumes.
Offer a web-based platform where users upload documents and receive OCR results. Charge monthly subscription based on page quotas.
Integrate the OCR API into expense management, document management, or workflow automation tools. Charge per integration or per document processed.
💬 Integration Tip
Wrap the API calls in a function that takes a file path and returns structured JSON. Use the sync endpoint for quick demos and async for large batches.
Scored May 13, 2026
Use when building UI with shadcn/ui components, Tailwind CSS layouts, form patterns with react-hook-form and zod, theming, dark mode, sidebar layouts, mobile navigation, or any shadcn component question.
Tailwind reference tool. Use when working with tailwind in frontend contexts.
A product creation skill based on the "Bee Website Builder" Open API. It is used to create a new product under a specified site language and product group, w...
A product update skill based on the "Bee Website Builder" Open API. It is used to update an existing product under a specified site language and supports upd...
Build WCAG 2.1 AA compliant websites with semantic HTML, proper ARIA, focus management, and screen reader support. Includes color contrast (4.5:1 text), keyboard navigation, form labels, and live regions. Use when implementing accessible interfaces, fixing screen reader issues, keyboard navigation, or troubleshooting "focus outline missing", "aria-label required", "insufficient contrast".
Use when building Vue 3 applications with Composition API, Nuxt 3, or Quasar. Invoke for Pinia, TypeScript, PWA, Capacitor mobile apps, Vite configuration.