robotgo-flow

robotgo-flow is a skill for Claude Code, Codex from znlgis/opengis-skills. It costs 50 tokens per session (3,142 once invoked), scanned A, original, MIT.

A Windows desktop automation framework that runs step-by-step workflows described in YAML, a plain-text configuration format. It can find screen elements from images and control the mouse, keyboard, and browser.

In plain words
What is it for?
It helps build, record, run, and debug Windows RPA workflows, such as filling forms, operating desktop software, and handling browser steps.
Why use it?
It removes repetitive manual clicking and typing from Windows tasks while allowing workflows to pause for human input or recover from errors.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is go test ./internal/config/ -v.

Good fit It helps build, record, run, and debug Windows RPA workflows, such as filling forms, operating desktop software, and handling browser steps.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/znlgis/opengis-skills
agentmods
npx agentmods add skills/znlgis/opengis-skills/robotgo-flow

Made for: Claude Code, Codex.

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 robotgo-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/znlgis/opengis-skills/robotgo-flow/github.svg)](https://agentmods.dev/skills/znlgis/opengis-skills/robotgo-flow)
Your own site
<a href="https://agentmods.dev/skills/znlgis/opengis-skills/robotgo-flow"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/robotgo-flow/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 robotgo-flow

Your own site · 80×15
<a href="https://agentmods.dev/skills/znlgis/opengis-skills/robotgo-flow"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/robotgo-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,142 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00050 $0.03142
Opus 5 $0.00025 $0.01571
Sonnet 5 $0.00010 $0.00628
Haiku 4.5 $0.00005 $0.00314

Measured 7d ago against content hash 6587cea3fc79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

robotgo-flow scanned grade A with 0 findings 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 7d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

others/robotgo-flow/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

项目地址: https://github.com/znlgis/robotgo-flow 官方文档: https://github.com/znlgis/robotgo-flow#readme

底层库: go-vgo/robotgo

上游中文教程: https://znlgis.github.io/others/robotgo-flow/(共 19 章)

许可证: MIT License

概述

robotgo-flow 是一款基于 robotgo 实现的 Windows 桌面 RPA 自动化框架。通过 YAML 声明式描述自动化流程,用图像模板匹配定位屏幕 UI 元素,自动执行鼠标、键盘、浏览器等操作,无需编写 Go 代码

  • Go CLI:纯命令行工具(run / record / capture / serve),专注自动化逻辑。
  • WPF 托盘应用:基于 .NET 10 WPF 的 Windows 托盘应用,实时进度监控与任务栏通知(可选组件)。
  • 图像模板匹配:预截取 UI 元素截图定位目标,适应窗口位置变化;窗口内优先搜索、全屏回退。
  • 交互式动作:运行时输入框(支持密码隐藏)、确认对话框、系统通知,可实现人工决策节点。
  • 运行时变量注入$input.<name> 占位符,运行时动态替换文本。
  • 人类行为模拟:贝塞尔曲线鼠标轨迹、打字错误与修正、可变延迟、空闲抖动,降低被检测风险。
  • 交互式录制器与截图工具:CLI 逐步引导录制工作流、框选截图。
  • 容错与调试:每步自动截图、从指定步骤恢复、abort/skip/retry 三种错误策略、context 安全取消。
  • GBK/UTF-8 自动编码:Windows 中文环境下自动处理路径与 YAML 编码。

当前仅支持 Windows 平台。命令与字段以仓库最新代码为准。


环境与构建

组件 版本要求 说明
Go 1.26+ https://go.dev/dl/
GCC (MinGW-w64) x86_64 通过 MSYS2 安装
.NET 10.0+ 仅 WPF 托盘应用需要
Windows 10 / 11 当前仅支持 Windows
# 安装 MSYS2 与编译工具链
winget install MSYS2.MSYS2
# 在 MSYS2 终端中:
pacman -S mingw-w64-x86_64-gcc mingw-w64-x86_64-zlib
# 将 C:\msys64\mingw64\bin 加入系统 PATH

首次编译约 4 分钟(需编译 GLFW C 源码),后续增量编译约 1 秒。

# 构建 Go CLI(必需)
.\scripts\build.ps1            # 优化输出(strip 调试信息)
.\scripts\build.ps1 -NoStrip   # 调试版本

# 构建 WPF 托盘应用(可选)
cd src\csharp
dotnet build RobotgoFlow.Wpf.sln -c Release

# 构建供 Tray 调用的 Go c-shared DLL
.\scripts\build.ps1 -Dll

CLI 命令

robotgo-flow                       # 无参数 → 显示帮助
robotgo-flow run <工作流文件>      # 执行工作流
robotgo-flow record                # 交互式录制工作流
robotgo-flow capture [元素名]      # 交互式截取模板
robotgo-flow serve <工作流文件>    # JSON-Line 协议服务(供 WPF GUI 调用)

run 参数:

参数 默认值 说明
--from N 1(从头) 从第 N 步开始执行(1-indexed)
--debug false 每步自动保存截图到输出目录
--out dir 工作流所在目录 截图输出目录(默认 screenshots/

Read the full file on GitHub · 265 lines

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. 7d ago First seen · 265 lines · 50 tokens per session scan A 6587cea3fc79

Subscribe to this mod's changes

robotgo-flow is a skill published in the GitHub repository znlgis/opengis-skills (60 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 3,142 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.