← 返回 Skills 市场
datappt8

一个功能强大的屏幕浏览、OCR识别和屏幕分析技能包,专为AI助手设计

作者 datappt8 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
591
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install screen-capture-hub
功能描述
此技能应被用于任何需要捕获屏幕截图、分析屏幕内容或处理屏幕图像的任务。包括:使用Python PIL库捕获整个屏幕或特定区域的截图;保存截图到指定位置;分析截图中的文字内容(支持中英文OCR识别);对截图进行基本图像处理(裁剪、旋转、调整大小)。当用户提到"屏幕截图"、"截屏"、"查看屏幕"或需要分析屏幕上的内容...
安全使用建议
This package appears to do what it says: take screenshots and run OCR/analysis. Before installing or running it, consider the following: - Screenshots capture all visible data on your screen (including passwords, 2FA codes, private messages). Only run these scripts in a trusted environment and be mindful of privacy of captured images and output files. - The Windows installer script (scripts/install_tesseract.py) downloads a .exe from the network and executes it with silent install flags. Verify the download URLs and, if possible, the file checksum/signature before running. Prefer to install Tesseract manually from the official project or your distribution's package manager if you are uncomfortable with automated installers. - Inspect scripts/install_tesseract.py and scripts/setup.py (and any other scripts) before running them to ensure there is no unwanted network behavior or commands. Consider running the package in a disposable VM/container first. - The package does not request credentials, but it will write files (images, text, JSON) to the working directory. Review where output is stored and ensure sensitive captures are handled securely. - If you plan to allow an agent to invoke this skill autonomously, restrict autonomous execution or monitor runs; automated screenshotting has high privacy impact. Disable or limit autonomous invocation if you cannot review each action. - Good checks to perform: run scripts/dependency_check.py to see what is missing, run the examples in a safe environment, and prefer manual installation of Tesseract (brew/apt or official Windows installer you obtained yourself).
功能分析
Type: OpenClaw Skill Name: screen-capture-hub Version: 1.0.0 The skill bundle provides extensive screen capture, OCR, and analysis capabilities, which are inherently high-risk. Most notably, 'scripts/install_tesseract.py' automatically downloads and executes a binary installer from external sources (digi.bib.uni-mannheim.de and github.com) without hash verification, posing a significant supply chain risk. Additionally, 'scripts/setup.py' uses 'exec()' on a hardcoded string for environment verification, and the overall toolset allows for silent monitoring of user screens and text extraction. While these features align with the stated purpose, the automated execution of remote binaries and the sensitive nature of screen access warrant a suspicious classification.
能力评估
Purpose & Capability
Name/description, SKILL.md, README and included scripts consistently implement screen capture, OCR and basic image analysis. Requested Python libraries (Pillow, pyautogui, pytesseract, OpenCV, numpy) and reference to Tesseract OCR are appropriate and expected for the described functionality.
Instruction Scope
SKILL.md instructs the agent to run local Python scripts to capture the screen, save images, and perform OCR/analysis — these are within scope. However the runtime instructions also call out a one‑click installer (python scripts/setup.py) and an install script that will download and run a Tesseract installer; these steps cause network activity and execution of an external binary beyond simple local script execution.
Install Mechanism
There is no platform install spec in the package manifest, but scripts/install_tesseract.py programmatically downloads a Windows installer EXE (primary URL: digi.bib.uni-mannheim.de, fallback to a GitHub releases download URL) and runs it silently. Downloading and executing an external installer is a high-risk action — even if the URLs appear related to UB‑Mannheim Tesseract builds, it requires the user to trust external binaries and grants the script the ability to run privileged installers on the host.
Credentials
The skill does not request environment variables, credentials, or config paths unrelated to its purpose. Dependency checks inspect common Program Files paths and call tesseract commands; this is proportional to locating a locally installed Tesseract binary. No secrets or unrelated tokens are requested.
Persistence & Privilege
Skill flags show no forced persistence (always: false) and normal autonomous invocation is allowed. The only persistent effect the package may request is installing Tesseract system‑wide (writes to Program Files), which requires administrative privileges on Windows. The skill does not modify other skills or system agent configs.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install screen-capture-hub
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /screen-capture-hub 触发
  4. 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
openclaw-screen-viewer 1.0.0 – Initial release - Adds Python-based screen capture and image processing capabilities (full screen or region). - Supports screenshot saving, text extraction via OCR (Chinese and English), and basic image editing (crop, rotate, resize). - Provides scripts for quick capture, OCR, region selection, and screen content analysis. - Includes detailed usage, installation, and troubleshooting instructions for multiple platforms.
元数据
Slug screen-capture-hub
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

一个功能强大的屏幕浏览、OCR识别和屏幕分析技能包,专为AI助手设计 是什么?

此技能应被用于任何需要捕获屏幕截图、分析屏幕内容或处理屏幕图像的任务。包括:使用Python PIL库捕获整个屏幕或特定区域的截图;保存截图到指定位置;分析截图中的文字内容(支持中英文OCR识别);对截图进行基本图像处理(裁剪、旋转、调整大小)。当用户提到"屏幕截图"、"截屏"、"查看屏幕"或需要分析屏幕上的内容... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 591 次。

如何安装 一个功能强大的屏幕浏览、OCR识别和屏幕分析技能包,专为AI助手设计?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install screen-capture-hub」即可一键安装,无需额外配置。

一个功能强大的屏幕浏览、OCR识别和屏幕分析技能包,专为AI助手设计 是免费的吗?

是的,一个功能强大的屏幕浏览、OCR识别和屏幕分析技能包,专为AI助手设计 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

一个功能强大的屏幕浏览、OCR识别和屏幕分析技能包,专为AI助手设计 支持哪些平台?

一个功能强大的屏幕浏览、OCR识别和屏幕分析技能包,专为AI助手设计 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 一个功能强大的屏幕浏览、OCR识别和屏幕分析技能包,专为AI助手设计?

由 datappt8(@datappt8)开发并维护,当前版本 v1.0.0。

💬 留言讨论