Token导航 LogoToken导航

Agent Skill · 研究检索

midscene-harmony-automation(中场和谐自动化)

midscene-harmony-automation 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

midscene-harmony-automation 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 15,449。

总安装 7,845周安装 337GitHub Stars 公开资料未说明下载 2,750核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.3

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:midscene-harmony-automation(中场和谐自动化)
来源仓库:https://github.com/quanru/midscene-harmony-automation
安装命令:
openclaw skills install midscene-harmony-automation
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install midscene-harmony-automation

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

为 HarmonyOS NEXT 设备提供视觉驱动自动化能力。基于屏幕截图识别界面元素并执行触控操作。适用于应用测试与跨平台设备控制场景。midscene-harmony-automation 属于研究检索类 Skill,可作为该场景下的辅助能力补充。需确保设备处于开发者模式并授权辅助功能。

建议核实系统版本与技能兼容性后再行使用。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install midscene-harmony-automation;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

midscene-harmony-automation 怎么安装?

在终端执行 openclaw skills install midscene-harmony-automation。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

midscene-harmony-automation 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

midscene-harmony-automation 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

midscene-harmony-automation 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

midscene-harmony-automation 用的人多吗?

公开数据是累计安装 7,845 次,近一周安装 337 次,下载 2,750 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

midscene-harmony-automation 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
midscene-harmony-automation

中场和谐自动化 · 本页

7,845—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
harmonyos-device-automation
description
>
allowed-tools

HarmonyOS Device Automation

CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW: 1. Never run midscene commands in the background. Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop. 2. Run only one midscene command at a time. Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together. 3. Allow enough time for each command to complete. Midscene commands involve AI inference and screen interaction, which can take longer than typical shell commands. A typical command needs about 1 minute; complex act commands may need even longer.

Automate HarmonyOS NEXT devices using npx @midscene/harmony@1. Each CLI command maps directly to an MCP tool — you (the AI agent) act as the brain, deciding which actions to take based on screenshots.

Prerequisites

Midscene requires models with strong visual grounding capabilities. The following environment variables must be configured — either as system environment variables or in a .env file in the current working directory (Midscene loads .env automatically):

MIDSCENE_MODEL_API_KEY="your-api-key"
MIDSCENE_MODEL_NAME="model-name"
MIDSCENE_MODEL_BASE_URL="https://..."
MIDSCENE_MODEL_FAMILY="family-identifier"

Example: Gemini (Gemini-3-Flash)

MIDSCENE_MODEL_API_KEY="your-google-api-key"
MIDSCENE_MODEL_NAME="gemini-3-flash"
MIDSCENE_MODEL_BASE_URL="https://generativelanguage.googleapis.com/v1beta/openai/"
MIDSCENE_MODEL_FAMILY="gemini"

Example: Qwen 3.5

MIDSCENE_MODEL_API_KEY="your-aliyun-api-key"
MIDSCENE_MODEL_NAME="qwen3.5-plus"
MIDSCENE_MODEL_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
MIDSCENE_MODEL_FAMILY="qwen3.5"
MIDSCENE_MODEL_REASONING_ENABLED="false"
# If using OpenRouter, set:
# MIDSCENE_MODEL_API_KEY="your-openrouter-api-key"
# MIDSCENE_MODEL_NAME="qwen/qwen3.5-plus"
# MIDSCENE_MODEL_BASE_URL="https://openrouter.ai/api/v1"

Example: Doubao Seed 2.0 Lite

MIDSCENE_MODEL_API_KEY="your-doubao-api-key"
MIDSCENE_MODEL_NAME="doubao-seed-2-0-lite"
MIDSCENE_MODEL_BASE_URL="https://ark.cn-beijing.volces.com/api/v3"
MIDSCENE_MODEL_FAMILY="doubao-seed"

Commonly used models: Doubao Seed 2.0 Lite, Qwen 3.5, Zhipu GLM-4.6V, Gemini-3-Pro, Gemini-3-Flash.

If the model is not configured, ask the user to set it up. See Model Configuration for supported providers.

HDC Setup

HDC (HarmonyOS Device Connector) must be installed and accessible. Common setup:

  • Install via DevEco Studio
  • Or set HDC_HOME environment variable to point to the HDC directory

Verify HDC is working:

hdc version
hdc list targets

Commands

Connect to Device

npx @midscene/harmony@1 connect
npx @midscene/harmony@1 connect --deviceId 0123456789ABCDEF

Take Screenshot

npx @midscene/harmony@1 take_screenshot

After taking a screenshot, read the saved image file to understand the current screen state before deciding the next action.

Perform Action

Use act to interact with the device and get the result. It autonomously handles all UI interactions internally — tapping, typing, scrolling, swiping, waiting, and navigating — so you should give it complex, high-level tasks as a whole rather than breaking them into small steps. Describe what you want to do and the desired effect in natural language:

# specific instructions
npx @midscene/harmony@1 act --prompt "type hello world in the search field and press Enter"
npx @midscene/harmony@1 act --prompt "long press the message bubble and tap Delete in the popup menu"

# or target-driven instructions
npx @midscene/harmony@1 act --prompt "open Settings and navigate to Wi-Fi settings, tell me the connected network name"

Disconnect

npx @midscene/harmony@1 disconnect

Workflow Pattern

Since CLI commands are stateless between invocations, follow this pattern:

  1. Connect to establish a session
  2. Launch the target app and take screenshot to see the current state, make sure the app is launched and visible on the screen.
  3. Execute action using act to perform the desired action or target-driven instructions.
  4. Disconnect when done

Best Practices

  1. Bring the target app to the foreground before using this skill: For best efficiency, launch the app using HDC (e.g., hdc shell aa start -a EntryAbility -b <bundleName>) before invoking any midscene commands. Then take a screenshot to confirm the app is actually in the foreground. Only after visual confirmation should you proceed with UI automation using this skill. HDC commands are significantly faster than using midscene to navigate to and open apps.
  2. Be specific about UI elements: Instead of vague descriptions, provide clear, specific details. Say "the Wi-Fi toggle switch on the right side" instead of "the toggle".
  3. Describe locations when possible: Help target elements by describing their position (e.g., "the search icon at the top right", "the third item in the list").
  4. Never run in background: Every midscene command must run synchronously — background execution breaks the screenshot-analyze-act loop.
  5. Batch related operations into a single act command: When performing consecutive operations within the same app, combine them into one act prompt instead of splitting them into separate commands. For example, "open Settings, tap Wi-Fi, and toggle it on" should be a single act call, not three. This reduces round-trips, avoids unnecessary screenshot-analyze cycles, and is significantly faster.
  6. Summarize report files after completion: After finishing the automation task, collect and summarize all report files (screenshots, logs, output files, etc.) for the user. Present a clear summary of what was accomplished, what files were generated, and where they are located, making it easy for the user to review the results.

Example — App launch and interaction:

hdc shell aa start -a EntryAbility -b com.huawei.hmos.settings
npx @midscene/harmony@1 connect
npx @midscene/harmony@1 take_screenshot
npx @midscene/harmony@1 act --prompt "scroll down the settings list and tap About device"
npx @midscene/harmony@1 take_screenshot
npx @midscene/harmony@1 disconnect

Example — Form interaction:

npx @midscene/harmony@1 act --prompt "fill in the username field with 'testuser' and the password field with 'pass123', then tap the Login button"
npx @midscene/harmony@1 take_screenshot

Common HarmonyOS Bundle Names

AppBundle Name
Settingscom.huawei.hmos.settings
Cameracom.huawei.hmos.camera
Gallerycom.huawei.hmos.photos
Calendarcom.huawei.hmos.calendar
Clockcom.huawei.hmos.clock
Calculatorcom.huawei.hmos.calculator
Browsercom.huawei.hmos.browser
Weathercom.huawei.hmos.weather

Troubleshooting

ProblemSolution
HDC not foundInstall via DevEco Studio or set HDC_HOME environment variable.
Device not listedCheck USB connection, ensure USB debugging is enabled in Developer Options, and run hdc list targets.
Command timeoutThe device screen may be off or locked. Wake the device and unlock it.
API key errorCheck .env file contains MIDSCENE_MODEL_API_KEY=<your-key>. See Model Configuration.
Wrong device targetedIf multiple devices are connected, use --deviceId <id> flag with the connect command.

适合场景

01

调用多模型

02

代码和文本生成

03

Agent 推理流程

04

OpenRouter 模型接入

能力概览

能力 1

统一调用多种 LLM

能力 2

支持 Claude、Gemini、Kimi 等模型

能力 3

适合聊天、代码和推理任务

能力 4

可作为 Agent 模型调用入口

平台分布

OpenClaw

92.51%
按下载量换算2,544

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills