← Back to Skills Marketplace
641
Downloads
0
Stars
3
Active Installs
3
Versions
Install in OpenClaw
/install pyautogui
Description
Cross-platform mouse/keyboard automation skill. Supports mouse control (move/click/drag/scroll), keyboard control (key press/hotkeys/type text), screen opera...
Usage Guidance
This package appears to be a straightforward PyAutoGUI-based automation toolkit and is internally consistent. Before installing/running it: 1) review and run the scripts in a safe environment (they can move the mouse, type, and delete files); use the cleanup script in preview mode first (--execute required to actually delete). 2) Be aware RapidOCR/onnxruntime may download or require large model files on first use and may use network/disk resources. 3) Granting accessibility/input permissions (macOS) or running with elevated rights (Windows) may be required for full functionality — avoid running with higher privileges than necessary. 4) If you plan to allow autonomous agent invocation, remember the skill can operate the UI—only enable autonomous use if you trust the skill and its source.
Capability Analysis
Type: OpenClaw Skill
Name: pyautogui
Version: 1.2.0
The skill bundle provides extensive UI automation and image processing tools using PyAutoGUI, OpenCV, and RapidOCR. While the functionality is consistent with the documentation, the bundle is classified as suspicious due to the inherent high-risk nature of providing an AI agent with full mouse, keyboard, and screen capture capabilities. Additionally, several scripts (e.g., scripts/keyboard_mouse.py, scripts/image_utils.py, and scripts/cleanup.py) lack input sanitization for file paths, which could potentially be leveraged for unauthorized file writes or deletions of specific file patterns. No evidence of intentional malicious behavior or data exfiltration was observed.
Capability Assessment
Purpose & Capability
Name/description (mouse/keyboard automation, screenshots, image locating, cleanup) match the included scripts (keyboard_mouse.py, image_finder.py, draw_overlay.py, draw_on_image.py, cleanup.py). The packaged code implements the advertised features; no unrelated secrets or cloud credentials are requested.
Instruction Scope
SKILL.md gives concrete CLI commands that map to the included scripts. The instructions only reference installing Python packages and running the scripts; they do not instruct the agent to read unrelated system configuration or exfiltrate data. The cleanup script deletes files matching expected temporary-image patterns (subject to dry-run unless --execute is used).
Install Mechanism
There is no formal install spec in the registry (instruction-only), but the skill bundle contains multiple executable scripts. SKILL.md instructs installing Python packages via pip (pyautogui, Pillow, optionally opencv/rapidocr). This is consistent but worth noting: dependencies (especially RapidOCR/onnxruntime models) may download model data on first run and require additional disk/network usage; no arbitrary remote download URLs are embedded in the package itself.
Credentials
No environment variables, credentials, or config paths are requested. The skill's functionality (taking screenshots, controlling input, removing temporary image files) justifies the lack of declared secrets. There are no requests for unrelated tokens, keys, or system-wide config access.
Persistence & Privilege
always is false and the skill is user-invocable; it does not ask to run always or to modify other skills. The scripts perform local actions only (UI control, image processing, file deletion) and do not persistently modify agent/global settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pyautogui - After installation, invoke the skill by name or use
/pyautogui - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
PyAutoGUI skill 1.2.0 adds region screenshot and copy/paste automation:
- Added commands to take screenshots of specific screen regions (screenshot_region).
- Introduced clipboard automation: copy, paste, and combined copy_paste commands for fast text input.
- Documented use cases and command syntax for region screenshot and clipboard utilities.
- No changes to existing mouse, keyboard, or image utility functions.
v1.1.0
**Summary: Adds image locating (template matching & OCR) and multi-language docs**
- Added `scripts/image_finder.py` for image locating (template matching + OCR-based screen/text locating).
- Updated description to include image locating and OCR features.
- Added Chinese documentation files (`README_zh.md`, `SKILL_zh.md`).
- Improved multi-language support in the skill description.
- No breaking changes to existing automation, image, or cleanup operations.
v1.0.0
openclaw-pyautogui 1.0.0
- 首次发布跨平台键鼠自动化控制技能，支持 Windows、Linux、macOS。
- 支持鼠标控制（移动、点击、拖拽、滚动）、键盘控制（按键、组合键、输入文本）。
- 提供屏幕操作（截图、获取鼠标位置、屏幕尺寸）及图片处理（获取图片参数、裁剪图片）。
- 支持屏幕和图片绘图标记、文件清理与磁盘空间释放功能。
- 提供详细命令行用法、常用场景及依赖说明。
Metadata
Frequently Asked Questions
What is pyautogui?
Cross-platform mouse/keyboard automation skill. Supports mouse control (move/click/drag/scroll), keyboard control (key press/hotkeys/type text), screen opera... It is an AI Agent Skill for Claude Code / OpenClaw, with 641 downloads so far.
How do I install pyautogui?
Run "/install pyautogui" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is pyautogui free?
Yes, pyautogui is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does pyautogui support?
pyautogui is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created pyautogui?
It is built and maintained by Ikaros (@ikaros-521); the current version is v1.2.0.
More Skills