← Back to Skills Marketplace
110
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install batch-id-ocr-to-txt
Description
批量识别最多50张身份证图片，提取姓名性别身份证号，生成格式规范的文本文件供下载查看。
README (SKILL.md)
batch-id-ocr-to-txt\r
\r
这是一个基于腾讯云 OCR 技术的 OpenClaw Skill。它能够自动识别图片中的身份证信息，并生成一份整齐的 .txt 文件发送给用户，非常适合需要批量处理证件信息的场景。\r
\r
🌟 功能特点\r
\r
- 批量处理：单次最高支持 50 张 身份证图片识别。\r
- 格式规范：自动提取
姓名、性别、身份证号。\r - 排版整洁：每张证件信息占用三行，证件之间自动空行分隔，方便直接复制或打印。\r
- 文件输出：直接生成
.txt附件，避免对话框长文本刷屏。\r - 隐私安全：采用 OpenClaw 环境变量配置，不硬编码 API 密钥，确保您的腾讯云账号安全。\r \r
🛠️ 安装预要求\r
\r 在发布或使用此 Skill 之前，您需要：\r
- 拥有一个腾讯云账号。\r
- 在 腾讯云访问管理 (CAM) 获取您的
SecretId和SecretKey。\r建议：为安全起见，请创建一个仅拥有
QcloudOCRFullAccess权限的子账号。\r - 确保您的 OpenClaw 部署环境可以访问
ocr.tencentcloudapi.com。\r \r
🚀 配置说明 (关键)\r
\r
安装此 Skill 后，请在 OpenClaw 的 Skill 配置面板 中填入以下信息：\r
\r
| 配置项 | 说明 | 示例值 |\r
| :--- | :--- | :--- |\r
| TENCENT_SECRET_ID | 腾讯云 API 密钥 ID | AKIDxxxxxxxxxxxxxx |\r
| TENCENT_SECRET_KEY | 腾讯云 API 密钥 Key | xxxxxxxxxxxxxxxxxxxx |\r
| REGION | 识别接口地域 | ap-guangzhou (默认) |\r
\r
📖 使用方法\r
\r
- 在对话框中发送一张或多张（最多50张）身份证正面照片。\r
- 触发本 Skill。\r
- 稍等片刻（程序内设有 0.5s/张 的频率保护），机器人将发送识别完成的消息。\r
- 下载并查看机器人发送的
身份证提取结果.txt文件。\r \r
📝 输出格式示例\r
\r
姓名：张三\r
性别：男\r
身份证号：44010619900101xxxx\r
\r
姓名：李四\r
性别：女\r
身份证号：44010619950520xxxx
Usage Guidance
This skill appears to do what it says: send user-supplied ID photos to Tencent Cloud OCR and return a .txt of extracted name/sex/ID. Before installing, verify: 1) the OpenClaw Skill config keys you must fill match the skill.yaml names (tencent-secret-id and tencent-secret-key) — SKILL.md's ENV name examples are slightly different; 2) the platform will install the tencentcloud-sdk-python dependency; 3) the code currently hardcodes region to 'ap-guangzhou' (so if you need a different region the code must be updated); 4) the skill will transmit images and sensitive extracted PII to Tencent Cloud—create a limited-permission subaccount (only OCR access) and avoid using high-privilege credentials; and 5) there is an entry-name mismatch in skill.yaml (entry: 'main.handler') vs. the provided file (batch_id.py exports handler) which may cause the skill not to run until corrected. If you need stronger privacy guarantees, do not send real IDs to the service until you confirm compliance with local laws and organizational policies.
Capability Assessment
Purpose & Capability
The skill's purpose (extract name/sex/ID number from up to 50 ID images using Tencent OCR) aligns with the required Tencent credentials in skill.yaml and the code which calls Tencent's IDCardOCR. No unrelated credentials, binaries, or config paths are requested. Minor incoherences: SKILL.md mentions environment variable names like TENCENT_SECRET_ID/TENCENT_SECRET_KEY and REGION, while skill.yaml uses 'tencent-secret-id'/'tencent-secret-key' config keys and the code reads event.config values; the code hardcodes region to 'ap-guangzhou' instead of honoring a configurable REGION.
Instruction Scope
SKILL.md instructs users to provide images and Tencent credentials and to expect a .txt file. The runtime code only reads provided image URLs, calls Tencent OCR, formats results, writes a temp file, and returns it. It does not access unrelated files, system secrets, or external endpoints beyond the Tencent OCR endpoint and the image URLs supplied.
Install Mechanism
No install spec is provided (instruction-only install), but a requirements.txt lists tencentcloud-sdk-python. The platform must install that dependency at runtime; there is no arbitrary URL download or installer. This is a moderate operational note (dependency install required) rather than a security red flag.
Credentials
Only Tencent credentials are required (SecretId/SecretKey), which is proportional. However, SKILL.md uses uppercase ENV names and mentions REGION while the skill.yaml and code use different config key names and the code ignores REGION. Also note that images and extracted PII are sent to Tencent's OCR service—this is expected but has privacy implications.
Persistence & Privilege
The skill does not request persistent or elevated platform privileges (always:false). It writes only to /tmp and returns that file path. Nothing in the skill attempts to modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install batch-id-ocr-to-txt - After installation, invoke the skill by name or use
/batch-id-ocr-to-txt - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
batch-id-ocr-to-txt 1.0.1
- 支持批量识别最多 50 张身份证图片，并自动提取姓名、性别、身份证号。
- 统一输出格式为每张证件三行，证件间自动空行分隔，便于复制和打印。
- 识别结果生成为 .txt 附件，避免对话框刷屏。
- API 密钥从 OpenClaw 环境变量读取，提升账号安全性。
Metadata
Frequently Asked Questions
What is batch-id?
批量识别最多50张身份证图片，提取姓名性别身份证号，生成格式规范的文本文件供下载查看。 It is an AI Agent Skill for Claude Code / OpenClaw, with 110 downloads so far.
How do I install batch-id?
Run "/install batch-id-ocr-to-txt" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is batch-id free?
Yes, batch-id is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does batch-id support?
batch-id is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created batch-id?
It is built and maintained by linyao58 (@linyao58); the current version is v1.0.1.
More Skills