skills-store: Skill for Claude Code

.claude/skills/pyautogui-helper/SKILL.md

pyautogui-helper is a skill for Claude Code from Mineru98/skills-store. It costs 65 tokens per session (1,721 once invoked), scanned B, original, MIT.

A set of guidance and utilities for automating desktop interfaces with PyAutoGUI, a Python library for controlling the mouse and keyboard, and OpenCV, a computer-vision library for analyzing images.

In plain words
What is it for?
Use it to capture and inspect screens, find buttons or other images, detect repeated objects, run recognition alongside mouse and keyboard control, add fail-safe behavior, and enter Korean text through the clipboard.
Why use it?
It addresses common GUI automation problems such as waiting for screens, small image differences, multiple matching elements, slow recognition, and non-English text input.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Mineru98/skills-store's own configuration. It tells Claude Code how to work on skills-store itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skills-store configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Mineru98/skills-store. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Mineru98/skills-store/main/.claude/skills/pyautogui-helper/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Mineru98/skills-store

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pyautogui-helper

README.md
[![agentmods](https://agentmods.dev/badge/skills/mineru98/skills-store/pyautogui-helper/github.svg)](https://agentmods.dev/skills/mineru98/skills-store/pyautogui-helper)
Your own site
<a href="https://agentmods.dev/skills/mineru98/skills-store/pyautogui-helper"><img src="https://agentmods.dev/badge/skills/mineru98/skills-store/pyautogui-helper/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pyautogui-helper

Your own site · 80×15
<a href="https://agentmods.dev/skills/mineru98/skills-store/pyautogui-helper"><img src="https://agentmods.dev/badge/skills/mineru98/skills-store/pyautogui-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,721 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.01721
Opus 5 $0.00032 $0.00860
Sonnet 5 $0.00013 $0.00344
Haiku 4.5 $0.00006 $0.00172

Measured 11d ago against content hash 60dbfc1a570e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

pyautogui-helper scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/pyautogui_utils.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo pip3 install pyautogui opencv-python pyperclip pillow numpy
.claude/skills/pyautogui-helper/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PyAutoGUI & OpenCV Helper

PyAutoGUI는 운영체제의 마우스와 키보드를 제어하고 화면 이미지를 분석하여 다양한 GUI 환경을 자동화할 수 있는 직관적인 라이브러리입니다 [1]. 하지만 단순한 API 호출만으로는 화면 로딩 지연, 이미지 해상도 미세 오차, 다국어 입력 오류, 그리고 실시간 화면 인식 시의 연산 병목 현상에 직면하게 됩니다 [3] [8].

이 스킬은 PyAutoGUI의 강력한 제어 기능OpenCV의 초고속·고정밀 이미지 분석 기술을 융합하여, 오작동 없이 안정적으로 구동되는 고품질 자동화 파이프라인을 구축하기 위한 최적의 개발 지침과 검증된 유틸리티를 제공합니다 [1] [2].

1. 핵심 사용 시나리오

이 스킬은 다음과 같은 고급 GUI 자동화가 필요한 프로젝트에서 필수적으로 사용됩니다:

  • 고속 화면 분석 및 실시간 반응: 프레임 변화가 빠른 게임이나 실시간 대시보드 화면을 캡처하고 대상을 지연 없이 검출해야 할 때 [8].
  • 고정밀 이미지 검색 (Template Matching): 미세한 픽셀 오차나 압축 손실이 있는 이미지 환경에서 정확도 임계값(threshold)을 점진적으로 완화하며 대상을 검출할 때 [2].
  • 다중 객체 동시 검출: 화면 내 동일한 아이콘이나 체크박스가 여러 개 존재할 때 이를 모두 식별하고 중복 매칭 좌표를 정교하게 필터링할 때 [1].
  • 멀티스레딩 기반 제어: 화면 인식 연산과 마우스/키보드 제어 동작이 서로를 방해하지 않도록 병렬 처리 아키텍처를 설계할 때 [8].
  • 안전장치 및 한글 입력 우회: 제어권 상실을 방지하는 Fail-Safe 안전장치 설계 및 클립보드를 활용한 한글 타이핑이 필요할 때 [1] [3].

2. 권장 개발 워크플로우

PyAutoGUI와 OpenCV를 결합한 고성능 자동화 스크립트를 작성할 때는 다음 4단계 표준 프로세스를 준수하십시오.

+------------------------+      +------------------------+
| 1. 환경 구성 및 패키지  | ---> | 2. 안전 설정 및 초기화  |
+------------------------+      +------------------------+
                                             |
                                             v
+------------------------+      +------------------------+
| 4. 멀티스레딩 및 복구  | <--- | 3. 고속 캡처 및 매칭   |
+------------------------+      +------------------------+

1단계: 환경 구성 및 패키지 설치

  • 필수 종속성: 고성능 템플릿 매칭과 클립보드 제어를 위해 다음 패키지들을 사전에 설치하십시오.
    sudo pip3 install pyautogui opencv-python pyperclip pillow numpy
    
  • OS별 권한: macOS 환경에서는 반드시 시스템 설정 > 화면 기록 권한을 부여하고 실행 앱을 재시작해야 캡처가 정상 작동합니다 [3].

2단계: 안전 설정 및 초기화

스크립트 오작동 시 시스템 제어권을 완전히 상실하는 무한 루프 사고를 방지하기 위해, 시작부에 전역 안전장치와 지연 시간을 명시적으로 설정하십시오 [1].

import pyautogui
pyautogui.FAILSAFE = True  # 마우스를 모서리로 가져가면 강제 종료
pyautogui.PAUSE = 0.1       # 모든 제어 명령 사이에 0.1초 미세 지연 부여

3단계: 고속 화면 캡처 및 점진적 매칭 (LOCATE-INTERACT)

순수 PyAutoGUI 이미지 매칭 대신, Pillow ImageGrab 메모리 캡처와 OpenCV matchTemplate을 조합하여 성능을 극대화하십시오 [2].

from scripts.pyautogui_utils import wait_and_click_opencv

# 'button.png' 이미지가 화면에 로드될 때까지 최대 10초 대기 후 정밀 클릭
# 매칭 감도(threshold)를 자동으로 완화하며 유연하게 검색합니다.
success = wait_and_click_opencv('button.png', timeout=10, initial_threshold=0.95)

Read the full file on GitHub · 88 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 88 lines · 65 tokens per session scan B 60dbfc1a570e

Subscribe to this mod's changes

pyautogui-helper is a skill published in the GitHub repository Mineru98/skills-store (13 stars, last pushed 12d ago), licensed MIT. It adds 65 tokens to every session and 1,721 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

dingtalk_channel_connect

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.

agentscope-ai/QwenPaw · 69 tokens

browser_cdp

Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.

agentscope-ai/QwenPaw · 70 tokens

browser_cdp

Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.

agentscope-ai/QwenPaw · 85 tokens

browser_visible

Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.

agentscope-ai/QwenPaw · 108 tokens

browser_visible

Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…

agentscope-ai/QwenPaw · 75 tokens

browser-testing-with-devtools

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…

addyosmani/agent-skills · 68 tokens