Token导航 LogoToken导航

Agent Skill · 开发

didit-id-document-verification(didit id 文件验证)

didit-id-document-verification 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

didit-id-document-verification 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 12,055。

总安装 1,458周安装 62GitHub Stars 12下载 511核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:didit-id-document-verification(didit id 文件验证)
来源仓库:https://github.com/didit-protocol/skills
仓库路径:skills/didit-id-document-verification
安装命令:
npx skills add https://github.com/didit-protocol/skills --skill didit-id-document-verification
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/didit-protocol/skills --skill didit-id-document-verification

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

didit-id-document-verification 验证身份证件正反面的真伪与有效性。支持 OCR 提取、MRZ 解析与防伪特征检测。覆盖 4,000+ 种证件类型与 220+ 国家地区。要求完整四角可见、无反光阴影的原始照片。集成活体检测防止截图与复印件欺骗。

didit-id-document-verification 属于开发类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/didit-id-document-verification

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/didit-protocol/skills --skill didit-id-documen…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

didit-id-document-verification 怎么安装?

在终端执行 npx skills add https://github.com/didit-protocol/skills --skill didit-id-document-verifica…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

didit-id-document-verification 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

didit-id-document-verification 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

didit-id-document-verification 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

didit-id-document-verification 用的人多吗?

公开数据是累计安装 1,458 次,近一周安装 62 次,下载 511 次,GitHub 12 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

didit-id-document-verification 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
didit-id-document-verification

didit id 文件验证 · 本页

1,45812接触敏感数据未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Didit ID Verification API

Overview

Verifies identity documents by submitting images of the front and back sides. Performs OCR extraction, MRZ parsing, authenticity checks, and document liveness detection.

Key constraints:

  • Supported formats: JPEG, PNG, WebP, TIFF
  • Maximum file size: 5MB per image
  • All document corners must be visible, full-color, no glare/shadows
  • Original real-time photos only (no screenshots, scans, or digital copies)

Coverage: 4,000+ document types, 220+ countries, 130+ languages. Supports passports, national ID cards, driver's licenses, and residence permits.

Processing pipeline:

  1. Intelligent capture & document type detection
  2. OCR text extraction + MRZ/barcode parsing
  3. Template matching, security feature validation, tamper detection
  4. Document liveness (detects screen captures, printed copies, portrait manipulation)

API Reference: https://docs.didit.me/standalone-apis/id-verification Feature Guide: https://docs.didit.me/core-technology/id-verification/overview Supported Documents: https://docs.didit.me/core-technology/id-verification/supported-documents-id-verification


Authentication

All requests require x-api-key header. Get your key from Didit Business Console → API & Webhooks, or via programmatic registration (see below).

Getting Started (No Account Yet?)

If you don't have a Didit API key, create one in 2 API calls:

  1. Register: POST https://apx.didit.me/auth/v2/programmatic/register/ with {"email": "you@gmail.com", "password": "MyStr0ng!Pass"}
  2. Check email for a 6-character OTP code
  3. Verify: POST https://apx.didit.me/auth/v2/programmatic/verify-email/ with {"email": "you@gmail.com", "code": "A3K9F2"} → response includes api_key

To add credits: GET /v3/billing/balance/ to check, POST /v3/billing/top-up/ with {"amount_in_dollars": 50} for a Stripe checkout link.

See the didit-verification-management skill for full platform management (workflows, sessions, users, billing).


Endpoint

POST https://verification.didit.me/v3/id-verification/

Headers

HeaderValueRequired
x-api-keyYour API keyYes
Content-Typemultipart/form-dataYes

Request Parameters (multipart/form-data)

ParameterTypeRequiredDefaultConstraintsDescription
front_imagefileYes—JPEG/PNG/WebP/TIFF, max 5MBFront image of ID document
back_imagefileNo—Same as aboveBack image (when applicable)
save_api_requestbooleanNotrue—Save in Business Console Manual Checks
vendor_datastringNo——Your identifier for session tracking

Example

import requests

response = requests.post(
    "https://verification.didit.me/v3/id-verification/",
    headers={"x-api-key": "YOUR_API_KEY"},
    files={
        "front_image": ("front.jpg", open("front.jpg", "rb"), "image/jpeg"),
        "back_image": ("back.jpg", open("back.jpg", "rb"), "image/jpeg"),
    },
    data={"vendor_data": "user-123"},
)
const formData = new FormData();
formData.append("front_image", frontImageFile);
formData.append("back_image", backImageFile);
formData.append("vendor_data", "user-123");

const response = await fetch("https://verification.didit.me/v3/id-verification/", {
  method: "POST",
  headers: { "x-api-key": "YOUR_API_KEY" },
  body: formData,
});

Response (200 OK)

{
  "request_id": "a1b2c3d4-...",
  "id_verification": {
    "status": "Approved",
    "document_type": "Identity Card",
    "document_number": "YZA123456",
    "personal_number": "X9876543L",
    "first_name": "Elena",
    "last_name": "Martínez Sánchez",
    "full_name": "Elena Martínez Sánchez",
    "date_of_birth": "1985-03-15",
    "age": 40,
    "gender": "F",
    "nationality": "ESP",
    "issuing_state": "ESP",
    "issuing_state_name": "Spain",
    "expiration_date": "2030-08-21",
    "date_of_issue": "2020-08-21",
    "address": "Calle Mayor 10, Madrid",
    "formatted_address": "Calle Mayor 10, 28013 Madrid, Spain",
    "place_of_birth": "Valencia",
    "portrait_image": "<base64>",
    "front_document_image": "<base64>",
    "back_document_image": "<base64>",
    "mrz": {
      "surname": "MARTINEZ SANCHEZ",
      "given_name": "ELENA",
      "document_type": "I",
      "document_number": "YZA123456",
      "country": "ESP",
      "nationality": "ESP",
      "birth_date": "850315",
      "expiry_date": "300821",
      "sex": "F"
    },
    "parsed_address": {"city": "Madrid", "region": "...", "postal_code": "28013", "country": "ES"},
    "warnings": []
  },
  "created_at": "2025-05-01T13:11:07.977806Z"
}

Status Values

StatusMeaning
"Approved"Document verified successfully
"Declined"Verification failed (see warnings)
"In Review"Requires manual review

Error Responses

CodeMeaningAction
400Invalid requestCheck file format, size, parameters
401Invalid API keyVerify x-api-key header
403Insufficient creditsTop up at business.didit.me

Response Field Reference

FieldTypeDescription
statusstring"Approved", "Declined", "In Review"
document_typestring"Passport", "Identity Card", "Driver's License", "Residence Permit"
document_numberstringDocument ID number
personal_numberstringPersonal/national ID number
first_name, last_name, full_namestringExtracted name fields
date_of_birthstringYYYY-MM-DD
ageintegerCalculated age
genderstring"M", "F", "U"
nationality, issuing_statestringISO 3166-1 alpha-3
expiration_date, date_of_issuestringYYYY-MM-DD
portrait_imagestringBase64-encoded portrait from document
mrzobjectMachine Readable Zone data
parsed_addressobjectGeocoded address: {city, region, postal_code, country, street_1}
warningsarray{risk, log_type, short_description, long_description}

Warning Tags

Auto-Decline (always)

TagDescription
ID_DOCUMENT_IN_BLOCKLISTDocument in blocklist (previously flagged)
PORTRAIT_IMAGE_NOT_DETECTEDNo portrait found on document
DOCUMENT_EXPIREDDocument expiration date has passed
DOCUMENT_NOT_SUPPORTED_FOR_APPLICATIONDocument type not accepted

Configurable (Decline / Review / Approve)

CategoryTags
Document livenessSCREEN_CAPTURE_DETECTED, PRINTED_COPY_DETECTED, PORTRAIT_MANIPULATION_DETECTED
MRZ issuesMRZ_NOT_DETECTED, MRZ_VALIDATION_FAILED, MRZ_AND_DATA_EXTRACTED_FROM_OCR_NOT_SAME
Data issuesNAME_NOT_DETECTED, DATE_OF_BIRTH_NOT_DETECTED, DOCUMENT_NUMBER_NOT_DETECTED, DATA_INCONSISTENT
DuplicatesPOSSIBLE_DUPLICATED_USER
Expected mismatchFULL_NAME_MISMATCH_WITH_PROVIDED, DOB_MISMATCH_WITH_PROVIDED, GENDER_MISMATCH_WITH_PROVIDED
GeolocationDOCUMENT_COUNTRY_MISMATCH

Common Workflows

Basic ID Verification

1. POST /v3/id-verification/ → front_image (+ back_image if applicable)
2. If "Approved" → extract first_name, last_name, date_of_birth, document_number
   If "Declined" → check warnings:
     DOCUMENT_EXPIRED → ask for valid document
     SCREEN_CAPTURE_DETECTED → ask for real photo of physical document
     MRZ_VALIDATION_FAILED → ask for clearer image

Full Identity Verification Pipeline

1. POST /v3/id-verification/ → verify document
2. POST /v3/passive-liveness/ → verify real person
3. POST /v3/face-match/ → compare selfie to document portrait
4. POST /v3/aml/ → screen extracted name/DOB/nationality
5. All Approved → fully verified identity

Utility Scripts

export DIDIT_API_KEY="your_api_key"

python scripts/verify_id.py front.jpg
python scripts/verify_id.py front.jpg back.jpg --vendor-data user-123

平台分布

Codex

35.24%
按下载量换算180

Claude

30.38%
按下载量换算155

Cursor

18.47%
按下载量换算94

Gemini CLI

9.47%
按下载量换算48

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills