← 返回 Skills 市场
uday390

DeepRead ID Documents

作者 DeepRead.tech · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
34
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install deepread-id-documents
功能描述
Extract structured data from passports, driver's licenses, and national ID cards for KYC/onboarding — name, document number, dates, nationality — as typed JS...
使用说明 (SKILL.md)

DeepRead ID Documents

Read passports, driver's licenses, and national ID cards — scans or phone photos — into clean, typed JSON for KYC and customer onboarding: name, document number, dates of birth/issue/expiry, and nationality. Every field carries a needs_review flag, because in identity verification, a confident-but-wrong character matters.

Use responsibly. Only process identity documents you are authorized to handle, for legitimate KYC/onboarding/verification purposes, with the document holder's knowledge and applicable consent. This skill POSTs the document to https://api.deepread.tech and polls for results. No system files are modified. Review DeepRead's privacy policy for data handling.

What You Get Back

{
  "schema_version": "dp02",
  "status": "completed",
  "extraction": {
    "fields": [
      {"key": "document_type", "value": "Passport", "needs_review": false, "location": {"page": 1}},
      {"key": "full_name", "value": "PRIYA NAIR", "needs_review": false, "location": {"page": 1}},
      {"key": "document_number", "value": "P1234567", "needs_review": true, "review_reason": "Glare on character 3", "location": {"page": 1}},
      {"key": "date_of_birth", "value": "1992-07-14", "needs_review": false, "location": {"page": 1}},
      {"key": "expiry_date", "value": "2031-05-02", "needs_review": false, "location": {"page": 1}},
      {"key": "nationality", "value": "IND", "needs_review": false, "location": {"page": 1}},
      {"key": "issuing_country", "value": "IND", "needs_review": false, "location": {"page": 1}}
    ]
  }
}

Setup

open "https://www.deepread.tech/dashboard/?utm_source=clawhub"
export DEEPREAD_API_KEY="sk_live_your_key_here"

Schema

{
  "type": "object",
  "properties": {
    "document_type":  {"type": "string", "description": "Passport, Driver's License, National ID, etc."},
    "full_name":      {"type": "string", "description": "Full name as printed"},
    "document_number":{"type": "string", "description": "Document / license number"},
    "date_of_birth":  {"type": "string", "description": "Date of birth (YYYY-MM-DD)"},
    "issue_date":     {"type": ["string","null"], "description": "Issue date (YYYY-MM-DD)"},
    "expiry_date":    {"type": ["string","null"], "description": "Expiry date (YYYY-MM-DD)"},
    "nationality":    {"type": ["string","null"], "description": "Nationality (ISO 3-letter if shown)"},
    "issuing_country":{"type": ["string","null"], "description": "Issuing country / authority"},
    "sex":            {"type": ["string","null"], "description": "Sex/gender if printed"}
  }
}

Extract + Expiry Check (Python)

import datetime
fields = {f["key"]: f["value"] for f in result["extraction"]["fields"]}

# Flag expired or soon-to-expire IDs
exp = fields.get("expiry_date")
if exp:
    days = (datetime.date.fromisoformat(exp) - datetime.date.today()).days
    if days \x3C 0:   print("⚠ EXPIRED document — reject")
    elif days \x3C 90: print(f"⚠ expires in {days} days")

# Route low-confidence fields (glare, worn print) to manual review
for f in result["extraction"]["fields"]:
    if f.get("needs_review"):
        print(f"REVIEW {f['key']}: {f.get('review_reason')}")

Use Cases

  • KYC / customer onboarding — auto-fill identity fields from an uploaded ID
  • Age / expiry verification — confirm DOB and that the document is valid
  • Account recovery / fraud ops — structured ID data for verification workflows
  • Travel / hospitality check-in — capture passport details quickly

Store Compliantly — Redact the Image

After extracting the fields you need, redact the raw ID image before archiving or sharing, so you're not storing full identity documents in the clear:

curl -X POST https://api.deepread.tech/v1/pii/redact -H "X-API-Key: $DEEPREAD_API_KEY" -F "[email protected]"

Install: clawhub install uday390/deepread-pii

Tips

  • Photos work — vision AI handles phone captures, but flat, glare-free, well-lit images extract best.
  • Expect needs_review on worn cards/glare — that's the feature; verify those manually.
  • Don't store more than you need — extract the minimum fields and redact the source.

Related DeepRead Skills

  • deepread-form-fill — fill onboarding forms from extracted ID data — clawhub install uday390/deepread-form-fill
  • deepread-pii — redact identity documents — clawhub install uday390/deepread-pii
  • deepread-ocr — general extraction — clawhub install uday390/deepread-ocr

Support


Get started free: https://www.deepread.tech/dashboard/?utm_source=clawhub

安全使用建议
Install only if you are authorized to process identity documents and are comfortable sending those documents to DeepRead's API. Confirm your consent, retention, compliance, and redaction requirements before using it for real KYC or onboarding data.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The purpose is KYC/onboarding extraction from passports, licenses, and national IDs, which inherently involves highly sensitive PII; the described API upload and extracted fields are aligned with that purpose.
Instruction Scope
Instructions are scoped to authorized identity-document processing, review of low-confidence fields, expiry checks, and optional redaction; no prompt override, hidden control flow, or unrelated agent authority was found.
Install Mechanism
The artifact is a single non-executable SKILL.md requiring DEEPREAD_API_KEY and linking to the provider dashboard; there are no install scripts, package hooks, or automatic code execution.
Credentials
Network transfer to https://api.deepread.tech and use of an API key are disclosed and necessary for the stated document-AI workflow, but users should treat uploaded ID documents as sensitive third-party processing.
Persistence & Privilege
No local persistence, background workers, privilege escalation, system-file modification, credential harvesting, or broad filesystem access is present in the artifact.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install deepread-id-documents
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /deepread-id-documents 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Extract name, document number, dates, and nationality from passports, licenses, and national IDs for KYC/onboarding. Expiry checks, per-field confidence flags, PII redaction for compliant storage.
元数据
Slug deepread-id-documents
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

DeepRead ID Documents 是什么?

Extract structured data from passports, driver's licenses, and national ID cards for KYC/onboarding — name, document number, dates, nationality — as typed JS... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 34 次。

如何安装 DeepRead ID Documents?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install deepread-id-documents」即可一键安装,无需额外配置。

DeepRead ID Documents 是免费的吗?

是的,DeepRead ID Documents 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

DeepRead ID Documents 支持哪些平台?

DeepRead ID Documents 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 DeepRead ID Documents?

由 DeepRead.tech(@uday390)开发并维护,当前版本 v1.0.0。

💬 留言讨论