← 返回 Skills 市场
378
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install scanner
功能描述
Transform document photos into clean scanned-looking pages with automatic edge detection, cropping, and perspective correction. Use when (1) the user wants a...
安全使用建议
This skill is coherent for document-scanning use, but be mindful that the examples load remote JavaScript from CDNs (OpenCV.js and a jscanify GH @master build) and suggest running 'npx serve' to host files locally. Before using in production or on sensitive images: (1) prefer pinned, versioned releases of jscanify (avoid @master), (2) consider hosting the libraries locally or using Subresource Integrity (SRI) if embedding CDN scripts, (3) vet the jscanify package/source (review its code or npm package), and (4) avoid running unreviewed npm packages with npx on machines holding sensitive data. If you need higher assurance, ask the skill author for a specific, versioned install instruction or a packaged implementation.
功能分析
Type: OpenClaw Skill
Name: scanner
Version: 1.0.0
The 'scanner' skill is a legitimate tool designed for document edge detection and perspective correction using the jscanify library and OpenCV.js. The instructions in SKILL.md are well-aligned with the stated purpose, utilizing standard development workflows (npm, npx serve) and reputable external CDNs (jsDelivr, opencv.org) without any signs of data exfiltration, malicious execution, or prompt injection.
能力评估
Purpose & Capability
Name/description match the instructions: the SKILL.md only describes selecting and running a document-scanning workflow (browser-first jscanify/OpenCV.js) and producing corrected images. No unrelated credentials, binaries, or system accesses are requested.
Instruction Scope
Runtime instructions stay within the scanning task: installing jscanify, loading opencv.js, serving a local page, and calling jscanify.extractPaper/highlightPaper. The doc explicitly forbids overwriting originals and does not instruct reading unrelated system files or secrets.
Install Mechanism
There is no packaged install spec (instruction-only), which is low-risk, but the recommended CDN usage points at jsdelivr GH with the @master ref (https://cdn.jsdelivr.net/gh/ColonelParrot/jscanify@master/...). Pulling an unpinned master branch from a CDN increases the risk of unexpected code changes. The plan to use 'npx serve .' will fetch and run a package on demand (transient install). These practices are common for quick dev workflows but worth hardening for production.
Credentials
The skill requires no environment variables, credentials, or config paths. The external endpoints listed (docs.opencv.org and cdn.jsdelivr.net) match the browser-first purpose.
Persistence & Privilege
Skill is not always:true, is user-invocable, and does not request permanent/system-level presence or alter other skills' configs. Autonomous invocation is allowed (platform default) but not combined with other red flags.
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 scanner - 安装完成后，直接呼叫该 Skill 的名称或使用
/scanner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
v1.0.0
Added a focused browser-first document scanning workflow with jscanify defaults, edge detection guidance, and low-friction local preview commands.
元数据
常见问题
Scanner 是什么？
Transform document photos into clean scanned-looking pages with automatic edge detection, cropping, and perspective correction. Use when (1) the user wants a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 378 次。
如何安装 Scanner？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install scanner」即可一键安装，无需额外配置。
Scanner 是免费的吗？
是的，Scanner 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Scanner 支持哪些平台？
Scanner 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（linux, darwin, win32）。
谁开发了 Scanner？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.0。
推荐 Skills