← 返回 Skills 市场
161
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install moark-ocr
功能描述
Perform Optical Character Recognition (OCR) to extract and recognize text from images.
安全使用建议
This package appears to do what it says: it sends the provided image (as a data URI when a local file is used) to Gitee's AI endpoint and returns OCR text. Before installing, confirm the following: (1) The GITEEAI_API_KEY you supply is for a trusted Gitee AI account and you understand its permissions and billing; (2) any images you process may be transmitted to the external service — avoid sending sensitive images unless you accept that risk; (3) you will need the 'openai' Python client installed (pip install openai); (4) review and run the included script locally if you want to inspect its behavior first. If you need the OCR to run strictly offline or without external upload, this skill is not appropriate.
功能分析
Type: OpenClaw Skill
Name: moark-ocr
Version: 1.0.0
The skill is a legitimate OCR tool that uses the Gitee AI Vision API to extract text from images. The Python script (scripts/perform_ocr.py) uses the standard OpenAI library to communicate with the Gitee endpoint (ai.gitee.com) and contains no evidence of malicious execution, data exfiltration beyond the intended image processing, or prompt injection attacks.
能力评估
Purpose & Capability
Name/description state OCR via an external Gitee AI service and the package requires a single GITEEAI_API_KEY. The bundled script calls a Gitee AI endpoint (base_url=https://ai.gitee.com/v1) and uses a PaddleOCR model — these requirements match the declared purpose.
Instruction Scope
SKILL.md instructs the agent to run the included script, extract the line starting with 'OCR_RESULT:' and present it to the user. The script only reads the provided image path and (optionally) GITEEAI_API_KEY; it encodes local files to base64 and sends them to the Gitee AI API — expected for OCR but does transmit image data to an external service. Minor formatting oddity: SKILL.md asks to present output with a camera emoji and bracketed text rather than normal markdown image syntax; this is a display choice, not a security issue.
Install Mechanism
There is no automatic installer; the SKILL.md suggests installing the well-known 'openai' Python client via pip. No downloads from unknown URLs or archive extraction are present. The included script lists 'openai' as the dependency, which is consistent with the instructions.
Credentials
Only one environment variable is required: GITEEAI_API_KEY (declared as primary). The key is directly used to authenticate to the Gitee AI endpoint. No unrelated secrets or additional environment access are requested.
Persistence & Privilege
The skill does not request permanent presence (always: false), does not modify other skill configurations, and has no special system-level privileges. Autonomous invocation is allowed (platform default) but not combined with other concerning factors.
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 moark-ocr - 安装完成后，直接呼叫该 Skill 的名称或使用
/moark-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
v1.0.0
Initial release of moark-ocr
- Enables extraction and recognition of text from images using an external GITEE AI API.
- Provides a workflow to run `perform_ocr.py`, parse its output, extract, and display OCR results.
- Requires GITEEAI_API_KEY; notifies users if the key is missing.
- Presents OCR results and a brief summary based on the user's prompt.
- Output format: displays results in markdown with a camera emoji and label.
元数据
常见问题
Moark Ocr 是什么？
Perform Optical Character Recognition (OCR) to extract and recognize text from images. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 161 次。
如何安装 Moark Ocr？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install moark-ocr」即可一键安装，无需额外配置。
Moark Ocr 是免费的吗？
是的，Moark Ocr 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Moark Ocr 支持哪些平台？
Moark 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 Moark Ocr？
由 fchange（@fchange）开发并维护，当前版本 v1.0.0。
推荐 Skills