← 返回 Skills 市场
Personal Id Ocr
作者
SCNet-sugon
· GitHub ↗
· v1.0.3
· MIT-0
186
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install personal-id-ocr
功能描述
支持身份证正反两面全自动检测与识别,提取姓名、性别、民族、出生日期、住址、公民身份号码及签发机关等关键字段。
安全使用建议
This package appears internally coherent, but you should still exercise caution: 1) The skill sends images (often containing highly sensitive PII) to a third‑party OCR service — verify you trust Scnet and review their privacy policy before sending real ID images. 2) Keep SCNET_API_KEY secret (store in a file with restrictive permissions or use environment variables); never paste it into chat. 3) Confirm network traffic is going only to the expected domain (api.scnet.cn or your configured SCNET_API_BASE). 4) The repository/source is listed inconsistently in registry metadata — if provenance matters, verify the publisher and upstream source (the package includes a placeholder GitHub URL). 5) If you test, try with non-sensitive images first and be prepared to revoke the API key if anything looks wrong.
功能分析
Type: OpenClaw Skill
Name: personal-id-ocr
Version: 1.0.3
The skill is a legitimate wrapper for the Sugon-Scnet OCR API, designed to extract information from ID cards. The core logic in `scripts/main.py` correctly handles file uploads to the official API endpoint (api.scnet.cn), implements standard authentication via API keys, and includes robust error handling and retry logic for rate limiting. No evidence of data exfiltration to unauthorized endpoints, credential theft, or malicious prompt injection was found.
能力标签
能力评估
Purpose & Capability
Name/description match the implementation: the Python script posts image files to https://api.scnet.cn/api/llm/v1/ocr/recognize and extracts ID fields. Required env var (SCNET_API_KEY) and optional SCNET_API_BASE are appropriate for a remote OCR API.
Instruction Scope
SKILL.md limits runtime behavior to reading a local image file and a local config/.env (or env var) and calling the Scnet OCR endpoint. It does not instruct reading unrelated system files or exfiltrating data to unknown endpoints.
Install Mechanism
No install spec; code is instruction-only with a small Python script that uses requests. No external archive downloads or unusual installers are present.
Credentials
Only SCNET_API_KEY (and optional SCNET_API_BASE) are required. That is proportionate for a third‑party OCR service. The code reads only the declared config file or environment variable.
Persistence & Privilege
Skill is not always-enabled and does not modify other skills or system-wide config. It runs on-demand and only requires normal network access to the declared API endpoint.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install personal-id-ocr - 安装完成后,直接呼叫该 Skill 的名称或使用
/personal-id-ocr触发 - 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
v1.0.3
- Added skill.yaml file for improved metadata and configuration.
- Updated SKILL.md with clearer environment variable requirements and explicit dependency information.
- Enhanced installation and security instructions, including safer API Key handling.
- Added notes and guidance on API rate limits (10 QPS) and recommended serial execution to prevent excessive requests.
- Included troubleshooting advice for handling 429 (Too Many Requests) errors.
v1.0.1
- Removed config.json file from the skill package.
- No changes to functionality or user interface.
- Configuration details should now be managed via other documented methods (e.g., config/.env).
v0.1.0
- 首次发布,实现身份证图片正反两面全自动检测与识别
- 支持提取姓名、性别、民族、出生日期、住址、公民身份号码及签发机关等字段
- 输入支持选择识别类型和本地图片路径
- 输出结构化 JSON,包括字段识别结果及置信度
- 提供详细的环境配置和 API Token 设置说明
- 包含命令行和对话式调用示例
元数据
常见问题
Personal Id Ocr 是什么?
支持身份证正反两面全自动检测与识别,提取姓名、性别、民族、出生日期、住址、公民身份号码及签发机关等关键字段。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 186 次。
如何安装 Personal Id Ocr?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install personal-id-ocr」即可一键安装,无需额外配置。
Personal Id Ocr 是免费的吗?
是的,Personal Id Ocr 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Personal Id Ocr 支持哪些平台?
Personal Id Ocr 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 Personal Id Ocr?
由 SCNet-sugon(@scnet-sugon)开发并维护,当前版本 v1.0.3。
推荐 Skills