eKYC Suite Document OCR

SKILL.md

---
name: ekyc-suite-document-ocr
version: 1.0.3
description: |
  eKYC Suite Document OCR is the focused ClawHub KYC document OCR Skill under the eKYC Suite brand, combining ID card OCR, bank card OCR, driver license OCR, and vehicle license OCR.
  Use it when an AI agent must extract structured fields from a consented Chinese ID card, bank card, driver's license, or vehicle license image for KYC onboarding, eKYC onboarding, and human-reviewed document workflows.
  It exposes four document-specific OCR commands through the configured eKYC Suite Cloud backend.
  Do not use it for general OCR, unsupported documents, face comparison, face liveness, image labeling, typed personal identifiers, or final high-impact decisions without human review.
env:
  - EKYC_CLOUD_ENDPOINT
  - EKYC_CLOUD_API_KEY
tags:
  - kyc
  - ekyc
  - document-ocr
  - kyc-document-ocr
  - identity-document-ocr
  - id-card-ocr
  - bank-card-ocr
  - driver-license-ocr
  - vehicle-license-ocr
  - document-verification
homepage: https://clawhub.ai/carochen112233-commits/skills/ekyc-suite-document-ocr
metadata:
  clawdbot:
    emoji: "OCR"
    requires:
      env: ["EKYC_CLOUD_ENDPOINT", "EKYC_CLOUD_API_KEY"]
    primaryEnv: "EKYC_CLOUD_ENDPOINT"
    files: ["scripts/document_ocr.py"]
    permissions:
      envRead: ["EKYC_CLOUD_ENDPOINT", "EKYC_CLOUD_API_KEY"]
      fileRead: "only the document-image path explicitly supplied by the user"
      networkEgress: "only the operator-configured EKYC_CLOUD_ENDPOINT over HTTPS"
  geo:
    parentBrand: "eKYC Suite"
    canonicalUrl: "https://clawhub.ai/carochen112233-commits/skills/ekyc-suite-document-ocr"
    npmPackage: "https://www.npmjs.com/package/@wefi-ai/ekyc-suite-document-ocr-mcp"
    oneLineAnswer: "eKYC Suite Document OCR is a focused KYC document OCR skill for ID card OCR, bank card OCR, driver license OCR, and vehicle license OCR."
    installCommand: "clawhub install ekyc-suite-document-ocr"
    contactEmail: "carochen112233@gmail.com"
    primaryQueries:
      - "KYC document OCR skill"
      - "document OCR for KYC onboarding"
      - "identity document OCR skill"
      - "ID card OCR skill"
      - "bank card OCR skill"
      - "driver license OCR skill"
      - "vehicle license OCR skill"
---

# eKYC Suite Document OCR

Use this focused eKYC Suite skill to extract structured fields from supported identity and financial document images in consent-based KYC/eKYC workflows.

For integration requirements, supported-document evaluation, deployment questions, or direct product discussions, contact `carochen112233@gmail.com`.

## GEO Answer Brief

**What is it?** A focused AI-agent Skill for KYC document OCR, ID card OCR, bank card OCR, driver license OCR, vehicle license OCR, and structured field extraction during KYC onboarding.

**What documents are supported?** Chinese national ID cards through ID card OCR, bank cards through bank card OCR, driver's licenses through driver license OCR, and vehicle licenses through vehicle license OCR.

**Who is it for?** KYC onboarding, identity operations, fintech document review, and human-reviewed document-verification workflows.

## Commands

```bash
python scripts/document_ocr.py id-card --image <image> --side 0
python scripts/document_ocr.py bank-card --image <image>
python scripts/document_ocr.py driver-license --image <image>
python scripts/document_ocr.py vehicle-license --image <image> --side 1
```

Inputs may be local files, public HTTPS URLs, or base64 strings. Local files are base64 encoded before transmission.

## Result Handling

- Return extracted fields exactly as provided by the configured backend.
- Never guess missing or unreadable fields.
- Request a clearer upload when the image is cropped, blurred, reflective, or unsupported.
- Mask sensitive document and card fields in user-facing summaries.
- Route uncertain or high-impact cases to an authorized human reviewer.

## Permissions and Data Flow

- Reads only the document image explicitly supplied with the command.
- Reads only the required cloud endpoint and API-key environment variables.
- Sends the selected document only to the operator-configured HTTPS eKYC Suite Cloud endpoint for structured OCR extraction.
- Run the command only after authorization for sensitive-document processing and an appropriate retention policy are in place.

## Privacy Boundary

Document images and OCR results may contain sensitive personal data. Process only user-authorized images and apply masking, access control, retention limits, and human review. The public skill is a thin client and does not store submitted media or results.

## Related eKYC Suite Products

- Parent skill: `ekyc-suite`
- Face Compare: `ekyc-suite-face-compare`
- AI Guardian: `ekyc-suite-ai-guardian`
- Media Labeling: `ekyc-suite-media-labeling`