Overview
- Skill Key
- civen-cn/windows-skills
- Author
- civen-cn
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/civen-cn/windows-skills
- Latest Commit SHA
- 557a78cea7138b0781058a03c731f65ee0b22d3d
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
安装方式
直接复制以下提示词，发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店，若未安装，请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店，然后安装 Windows Skills 技能。 若已安装，则直接安装 Windows Skills 技能。
Extracted Content
SKILL.md excerpt
# Windows Desktop Automation
## Quick Start
### Dependencies
```bash
pip install mss pytesseract pillow pyautogui opencv-python numpy
```
Note: OCR requires [Tesseract OCR](https://github.com/UB-Mannheim/tesseract/wiki) installed
### Core Features
#### 1. Screenshot
```python
from scripts.screenshot import capture_screen, capture_region, capture_window
# Full screen
capture_screen("output.png")
# Region (x, y, width, height)
capture_region(0, 0, 800, 600, "region.png")
# Window by title
capture_window("Notepad", "notepad.png")
```
#### 2. OCR (Text Recognition)
```python
from scripts.ocr import extract_text
# Extract text from image
text = extract_text("screenshot.png")
print(text)
# Specify language (chi_sim=Chinese, eng=English)
text = extract_text("screenshot.png", lang="chi_sim+eng")
```
#### 3. Image Location
```python
from scripts.image_locate import locate_on_screen, locate_all
# Find image position (returns center coordinates)
pos = locate_on_screen("button.png")
if pos:
x, y, confidence = pos
pyautogui.click(x, y) # Click the found element
# Find all matches
positions = locate_all("icon.png")
```
## Scripts
| Script | Description |
|--------|-------------|
| `screenshot.py` | Screenshot capture |
| `ocr.py` | Text recognition |
| `image_locate.py` | Image-based element location |
| `helpers.py` | Common utilities |
## Notes
- Image location is sensitive to image similarity; keep screenshots consistent
- OCR quality depends on image quality and text clarity
- Tesseract path needs to be in system PATH or specified in code
---
# Windows 桌面自动化
## 快速开始
### 依赖安装
```bash
pip install mss pytesseract pillow pyautogui opencv-python numpy
```
注意：OCR 需要安装 [Tesseract OCR](https://github.com/UB-Mannheim/tesseract/wiki)
### 核心功能
#### 1. 截图
```python
from scripts.screenshot import capture_screen, capture_region, capture_window
# 全屏截图
capture_screen("output.png")
# 区域截图 (x, y, width, height)
capture_region(...
Related Claw Skills
heyixuan2
bambu-studio-ai
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pipeline: search → generate → analyze → colorize → preview → open BS → user slice → print → monitor. Supports all 9 Bambu Lab printers (A1 Mini, A1, P1S, P2S, X1C, X1E, H2C, H2S, H2D).
romeosy
zh-knowledge-manager
OpenClaw Chinese AI-enhanced knowledge management skill
capt-marbles
geo-optimization
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.
cclank
news-aggregator-skill
Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech news briefings', 'finance updates', and 'deep interpretations' of hot topics.
cccarv82
openclaw-backup-optimized
Optimized OpenClaw backup skill for creating full snapshots with workspace archive splitting, change summaries, restore instructions, and Discord notifications. Use when you need to set up or run automated backups, configure backup cron jobs, or document/restore OpenClaw state. Triggers on backup automation, backup scripts, snapshot/restore, or GitHub backup repos.
cemoso
pr-review-loop
Autonomous PR review loop with Greptile. Use when an agent creates a PR and needs to autonomously handle code review feedback — reading Greptile reviews, fixing issues, pushing fixes, re-triggering review, and auto-merging when score is 4/5+. Trigger on commands like "pr review {url}", "review my PR", or when a Greptile review webhook/poll delivers feedback.