← 返回 Skills 市场
Ocr Local Rose
作者
roseknife520
· GitHub ↗
· v1.0.0
· MIT-0
304
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ocr-local-rose
功能描述
Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English.
安全使用建议
This skill appears to do what it says: a local Node script that uses tesseract.js to OCR local images. Before installing, consider: 1) npm install will download tesseract.js and its transitive packages (package-lock references a public mirror); if you want full control, run npm install yourself and/or use the official npm registry. 2) First run will download ~20MB per language model from a CDN (SKILL.md suggests jsdelivr) — if you prefer no runtime network activity, pre-download the .traineddata files into scripts/tessdata/ using the provided curl commands. 3) The script processes only local files (it does not upload images), but verify network egress policies if you are in a sensitive environment. 4) If you want extra assurance, review tesseract.js and its tesseract.js-core package versions listed in package.json/package-lock before installing.
功能分析
Type: OpenClaw Skill
Name: ocr-local-rose
Version: 1.0.0
The skill provides legitimate local OCR functionality using the Tesseract.js library. The code in scripts/ocr.js correctly implements text recognition with configurable language support and local caching, and the instructions in SKILL.md and README.md are consistent with the stated purpose. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
The skill is an OCR wrapper around tesseract.js. Required binary (node) and the dependency (tesseract.js) are exactly what you'd expect for a Node-based local OCR tool. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
The SKILL.md and scripts/ocr.js are consistent: the script reads a single user-supplied local image, performs OCR, and prints results or JSON. It stores downloaded language data under scripts/tessdata/. Runtime behavior includes network downloads of language model files on first run (or manual curl to jsdelivr as documented). This network activity is expected for the stated purpose but is worth noting: images are not uploaded by the script, only language model files are fetched.
Install Mechanism
There is no automated install specification in the registry metadata (instruction-only), but package.json declares tesseract.js as a dependency so npm install is expected. The package-lock shows dependencies resolved via a public npm mirror (registry.npmmirror.com) — a mirror is traceable but not the primary npm registry. Overall the install approach (npm dependency) is proportionate to the task.
Credentials
No environment variables, secrets, or external credentials are requested. The tool only needs filesystem access to the image and to write cached language files under its own scripts/tessdata/ directory.
Persistence & Privilege
The skill is not always-on and is user-invocable. It only creates/uses a tessdata cache directory inside its own script folder and does not modify other skills or global agent settings.
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 ocr-local-rose - 安装完成后，直接呼叫该 Skill 的名称或使用
/ocr-local-rose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
- Initial release of local OCR skill using Tesseract.js.
- Extracts text from images in Chinese (simplified/traditional) and English.
- Runs fully locally; no API key required.
- CLI supports language selection, plain text or JSON output.
- Automated downloading and caching of language model files.
元数据
常见问题
Ocr Local Rose 是什么？
Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 304 次。
如何安装 Ocr Local Rose？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ocr-local-rose」即可一键安装，无需额外配置。
Ocr Local Rose 是免费的吗？
是的，Ocr Local Rose 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Ocr Local Rose 支持哪些平台？
Ocr Local Rose 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 Ocr Local Rose？
由 roseknife520（@roseknife520）开发并维护，当前版本 v1.0.0。
推荐 Skills