Leyang

Midscene Automations Skills for Computer

AIエージェントv1.0.4
作者:Leyang更新日 2026-05-18全 5 バージョン · 最新版の公開日 2026-05-07midscene-computer-automation@clawhub_quanru/midscene-computer-automation
タスク自動化ツール呼び出し#Browser Automation

AlphaMoatによると、2026-10時点でMidscene Automations Skills for Computerのダウンロード数は6,143、スター数は3で、累計ダウンロード数で今回のランキング対象AIスキル10,914件中4,664位、AIエージェントでは1,632件中628位です。

一覧の初期表示は累計ダウンロード数順で、スター数順にも並べ替えできます。詳細ページの順位は累計ダウンロード数で計算しています。

ダウンロード数
6143
スター数
3
累計ダウンロード順位
#4,664
全体の上位 43% · AIエージェントの上位 39%
プラットフォームダウンロード数スター数コメント
ClawHub ↗52623-
SkillHub ↗61433—

プラットフォームごとに集計方法と集計時点が異なります。

このスキルでできること

資料では、デスクトップへの接続、スクリーンショット、マウス・キーボード操作、表示状態のアサート、実行レポートの確認を説明しています。ブラウザーで扱えないネイティブアプリ向けであり、Webアプリには推奨されません。ユーザーの実際のマウスとキーボードを操作するため、クリック、入力、ファイル移動が発生し得ます。対象アプリ、画面状態、各操作の影響を確認し、バックグラウンド実行や無許可のウィンドウ終了・高影響操作を避けてください。 対応する視覚モデルと認証情報を設定します。スクリーンショットやレポートには機密画面情報が含まれる場合があります。

資料公開日 2026-10-29

できること

  • ネイティブデスクトップアプリで制御されたUI操作を行う
  • 画面を確認し、操作後の状態を検証する
  • デスクトップ作業の確認可能なレポートを作成する

使う場面

  • ブラウザーでは扱えないネイティブデスクトップアプリを操作するとき
  • 前面ウィンドウ、操作内容、可逆性を確認し、各結果を段階的に検証できるとき

プロンプト例

スキルのドキュメントをもとに生成した例であり、実際の実行結果ではありません。

まずスクリーンショットを撮り、現在開いているネイティブアプリを確認してから、安全な操作手順を列挙してください。まだクリック、入力、移動はしないでください。

月次の推移

ダウンロード数6143
2094426964432026-03 · ダウンロード数 23942026-05 · ダウンロード数 38202026-06 · ダウンロード数 41342026-07 · ダウンロード数 46262026-08 · ダウンロード数 48952026-09 · ダウンロード数 51302026-10 · ダウンロード数 614326-0326-0926-10
スター数3
2342026-03 · スター数 32026-05 · スター数 32026-06 · スター数 32026-07 · スター数 32026-08 · スター数 32026-09 · スター数 32026-10 · スター数 326-0326-0926-10

2026-09 から集計方法を変更し、同名スキルを作者ごとに分けて集計し、全スキルを対象にしました。破線は変更前の月で、変更後のデータとは直接比較せず、変更をまたぐ増減も計算していません。

月ダウンロード数前月比スター数
2026-106143—3
2026-095130—3
2026-084895+5.8%3
2026-074626+11.9%3
2026-064134+8.2%3
2026-053820—3
2026-032394—3

SKILL.md 原文

作者が公開した元のファイルをテキストのまま表示しています。AlphaMoat による編集や審査はしていません。リンクはクリックできません。コマンドは内容を確認してから実行してください。取得日 2026-10-23。

15 KB・ClawHub v1.0.4
---
name: desktop-computer-automation
description: |
  Vision-driven desktop automation using Midscene. Control your desktop (macOS, Windows, Linux) with natural language commands.
  Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack.

  ⚠️ Takes over the user's real mouse and keyboard. For web apps, prefer "Browser Automation" instead.
  Only use this for desktop-native apps (Electron, Qt, native macOS/Windows/Linux) that cannot run in a browser.

  Triggers: open app, press key, desktop, computer, click on screen, type text, screenshot desktop,
すべて表示(全 250 行)
  launch application, switch window, desktop automation, control computer, mouse click, keyboard shortcut,
  screen capture, find on screen, read screen, verify window, close app, test Electron app

  Powered by Midscene.js (https://midscenejs.com)
allowed-tools:
  - Bash
---

# Desktop Computer 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.
> 4. **Always report task results before finishing.** After completing the automation task, you MUST proactively summarize the results to the user — including key data found, actions completed, screenshots taken, and any relevant findings. Never silently end after the last automation step; the user expects a complete response in a single interaction.
> 5. **Only minimize windows, never close them unless explicitly asked.** When you need to dismiss or get a window out of the way, minimize it instead of closing it. Do not close any app or window unless the user explicitly asks you to do so.

Control your desktop (macOS, Windows, Linux) using `npx -y @midscene/computer@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.

## What `act` Can Do

Inside a single `act` call on desktop, Midscene can move the mouse, click, double-click, right-click, drag items, type or clear text, scroll, press single keys or keyboard shortcuts, and work through multi-step interactions on whatever is visible on the selected display.

## 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):

```bash
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)

```bash
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

```bash
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

```bash
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](https://midscenejs.com/model-common-config) for supported providers.

## Commands

### Connect to Desktop

```bash
npx -y @midscene/computer@1 connect
npx -y @midscene/computer@1 connect --displayId <id>
```

### List Displays

```bash
npx -y @midscene/computer@1 list_displays
```

### Take Screenshot

```bash
npx -y @midscene/computer@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 computer and get the result. It autonomously handles all UI interactions internally — clicking, typing, scrolling, 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:

```bash
# specific instructions
npx -y @midscene/computer@1 act --prompt "type hello world in the search field and press Enter"
npx -y @midscene/computer@1 act --prompt "drag the file icon to the Trash"

# or target-driven instructions
npx -y @midscene/computer@1 act --prompt "search for the weather in Shanghai using the Chrome browser, tell me the result"
```

### Assert Current Screen State

Use `assert` to verify that the current screen satisfies a natural language condition. It does not perform UI actions; it checks the visible screen state and passes only when the assertion is true. Use this for validation, QA checks, and final state verification after `act`.

```bash
npx -y @midscene/computer@1 assert --prompt "there is a login button visible"
npx -y @midscene/computer@1 assert --prompt "the active window shows a saved confirmation message"
npx -y @midscene/computer@1 assert --displayId 1 --prompt "the file picker is open"
```

### Use a Reference Image for Precise Targeting

When the user provides a screenshot, icon, logo, or reference image and wants an exact visual match, prefer `tap --locate` instead of a generic `act --prompt`. Pass `--locate` as JSON. The `prompt` describes the target, `images` supplies named reference images, and `convertHttpImage2Base64: true` is useful when the image URL may not be directly accessible to the model.

```bash
npx -y @midscene/computer@1 tap --locate '{
  "prompt": "tap the area contains the image",
  "images": [
    {
      "name": "target image",
      "url": "https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png"
    }
  ],
  "convertHttpImage2Base64": true
}'
```

The same `locate` JSON shape also works for other commands that accept a `locate` parameter.

### Disconnect

```bash
npx -y @midscene/computer@1 disconnect
```

### Consume Report Files

The generated HTML report is recommended for human reading first. It includes step-by-step execution details and replay videos for each operation, which makes it much easier to understand what happened and troubleshoot problems.

If another skill or tool needs to consume the report, first convert it with `report-tool` from the same platform CLI package. Prefer Markdown for LLM-based workflows. Use JSON when the report needs to be processed programmatically.

```bash
npx -y @midscene/computer@1 report-tool --action to-markdown --htmlPath ./midscene_run/report/.../index.html --outputDir ./output-markdown
npx -y @midscene/computer@1 report-tool --action split --htmlPath ./midscene_run/report/.../index.html --outputDir ./output-data
```

## Workflow Pattern

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

1. **Connect** to establish a session
2. **Health check** — observe the output of the `connect` command. If `connect` already performed a health check (screenshot and mouse movement test), no additional check is needed. If `connect` did not perform a health check, do one manually: take a screenshot and verify it succeeds, then move the mouse to a random position (`act --prompt "move the mouse to a random position"`) and verify it succeeds. If either step fails, stop and troubleshoot before continuing. Only proceed to the next steps after both checks pass without errors.
3. **Launch the target app and take screenshot** to see the current state, make sure the app is launched and visible on the screen.
4. **Execute action** using `act` to perform the desired action or target-driven instructions, and use `assert` when you need to verify the resulting screen state.
5. **Disconnect** when done
6. **Report results** — summarize what was accomplished, present key findings and data extracted during the task, and list any generated files (screenshots, logs, etc.) with their paths

## Best Practices

1. **Always run a health check first**: After connecting, observe the output of the `connect` command. If `connect` already performed a health check (screenshot and mouse movement test), no additional check is needed. If it did not, do one manually: take a screenshot and move the mouse to a random position. Both must succeed (no errors) before proceeding with any further operations. This catches environment issues early.
2. **Bring the target app to the foreground before using this skill**: For best efficiency, bring the app to the foreground using other means (e.g., `open -a <AppName>` on macOS, `start <AppName>` on Windows) **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. Avoid using Spotlight, Start menu search, or other launcher-based approaches through midscene — they involve transient UI, multiple AI inference steps, and are significantly slower.
3. **Be specific about UI elements**: Instead of vague descriptions, provide clear, specific details. Say `"the yellow minimize button in the top-left corner of the Safari window"` instead of `"the button"`.
4. **Describe locations when possible**: Help target elements by describing their position (e.g., `"the icon in the top-right corner of the menu bar"`, `"the third item in the left sidebar"`).
5. **Never run in background**: Every midscene command must run synchronously — background execution breaks the screenshot-analyze-act loop.
6. **Check for multiple displays**: If you launched an app but cannot see it on the screenshot, the app window may have opened on a different display. Use `list_displays` to check available displays. You have two options: either move the app window to the current display, or use `connect --displayId <id>` to switch to the display where the app is.
7. **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, "search for X, click the first result, and scroll down to see more details" should be a single `act` call, not three. This reduces round-trips, avoids unnecessary screenshot-analyze cycles, and is significantly faster.
8. **Set up `PATH` before running (macOS)**: On macOS, some commands (e.g., `system_profiler`) may not be found if the `PATH` is incomplete. Before running any midscene commands, ensure the `PATH` includes the standard system directories:
   ```bash
   export PATH="/usr/sbin:/usr/bin:/bin:/sbin:$PATH"
   ```
   This prevents screenshot failures caused by missing system utilities.
9. **Use `assert` for verification**: When the goal is to confirm that a screen state is true, use `assert --prompt "..."` instead of an `act` prompt. Keep assertions observable and specific, such as `"the Save dialog is open"` or `"the export completed message is visible"`.
10. **Always report results after completion**: After finishing the automation task, you MUST proactively present the results to the user without waiting for them to ask. This includes: (1) the answer to the user's original question or the outcome of the requested task, (2) key data extracted or observed during execution, (3) screenshots and other generated files with their paths, (4) a brief summary of steps taken. Do NOT silently finish after the last automation command — the user expects complete results in a single interaction.
11. **Prefer `tap --locate` when a reference image is provided**: If the user shares a screenshot, icon, or logo and wants that exact visual target, use `tap --locate` with a multimodal `locate` JSON object such as `{ "prompt": "...", "images": [...] }` instead of relying only on `act --prompt`.

**Example — Context menu interaction:**

```bash
npx -y @midscene/computer@1 act --prompt "right-click the file icon and select Delete from the context menu"
npx -y @midscene/computer@1 take_screenshot
```

**Example — Dropdown menu:**

```bash
npx -y @midscene/computer@1 act --prompt "open the File menu and click New Window"
npx -y @midscene/computer@1 take_screenshot
```


## Troubleshooting

### macOS: Accessibility Permission Denied
Your terminal app does not have Accessibility access:
1. Open **System Settings > Privacy & Security > Accessibility**
2. Add your terminal app and enable it
3. Restart your terminal app after granting permission

### macOS: Xcode Command Line Tools Not Found
```bash
xcode-select --install
```

### API Key Not Set
Check `.env` file contains `MIDSCENE_MODEL_API_KEY=<your-key>`.

### macOS: Screenshot Fails with `system_profiler` Not Found
If `take_screenshot` fails with an error like `system_profiler: command not found`, the `PATH` environment variable is likely incomplete. Fix it by running:
```bash
export PATH="/usr/sbin:/usr/bin:/bin:/sbin:$PATH"
```
Then retry the screenshot command.

### macOS: Screenshot Returns a Black Screen
If `take_screenshot` returns a completely black image, the Mac is likely **locked** (e.g. screen is at the login/lock window). This is a system-level restriction — macOS prohibits capturing the screen contents while the session is locked, so there is no workaround at the application level.

**Recommended fix:** Use a **screensaver** instead of locking the screen. A screensaver keeps the user session active and unlocked, allowing screenshots to capture normally.

1. Open **System Settings > Lock Screen**
2. Set "Require password after screen saver begins or display is turned off" to a longer delay (or turn it off during automation)
3. Optionally configure a screensaver under **System Settings > Screen Saver** so the display still dims after inactivity without locking

### AI Cannot Find the Element
1. Take a screenshot to verify the element is actually visible
2. Use more specific descriptions (include color, position, surrounding text)
3. Ensure the element is not hidden behind another window


### `@midscene/*` Dependency Version Outdated
- Check local versions: `npm ls @midscene/computer @midscene/core @midscene/shared` (or `pnpm why @midscene/computer`).
- Check latest versions: `npm view @midscene/computer version`, `npm view @midscene/core version`, `npm view @midscene/shared version`.
- Upgrade dependencies: `npm i @midscene/computer@latest @midscene/core@latest @midscene/shared@latest`.

AIエージェントの人気スキル

self-improving agentAIエージェント

開発中の学び、エラー、訂正を Markdown ファイルに記録し、再利用やワークスペースの記憶への昇格に備えます。

↓ 160.3万★ 4544pskoett
技能发现·Find SkillsAIエージェント

やりたいことを自然文で伝えると、ローカルとリモートのカタログからスキルを探して推薦するスキルです。

↓ 157.4万★ 1810桂皮
Agent BrowserAIエージェント

AI エージェント向けのブラウザ自動化コマンドラインスキルです。

↓ 122.3万★ 1001Nicolas Kleiber
Self-Improving + Proactive AgentAIエージェント

利用者の訂正と自己点検を層構造の記憶に蓄え、使われ方に応じて昇格や保管を行うスキルです。

↓ 69.6万★ 1622Iván
Proactive AgentAIエージェント

AI エージェントの先回り、作業記憶、振り返りの手順を計画するためのワークスペース設定ガイドです。

↓ 57.9万★ 916halthelobster
Skill CreatorAIエージェント

効果的な Claude スキルの作成・更新ガイドです。

↓ 47.7万★ 485chindden
Skill VetterAIエージェント

第三者のスキルを入れる前に、出所と権限と危険な作りを手順に沿って調べるスキルです。

↓ 44.5万★ 1328spclaudehome
唐朝诗仙李白 · Ai Agent SkillAIエージェント

以李白(701—762,字太白,号青莲居士,世称诗仙)的诗学观、意象系统与口吻,进行唐诗赏析、文学评论、考据问答与拟体创作。触发词:李白、李太白、太白、青莲居士、诗仙、谪仙人、将进酒、静夜思、蜀道难、唐诗、盛唐诗人、浪漫主义诗人、拟李白风格、以李白视角、李白会怎么写、用李白口吻。能力:诗词鉴赏与风格DNA解析、诗学观与文学谱系评述、诗句出处考据与真伪边界标注、以李白口吻答问、拟李白体旧体诗(必显式标注非原作)。适用边界:仅用于唐代文学与古典诗歌相关话题,非此类话题不触发;本 skill 为文学普及与研究辅助,不代表李白本人立场,所拟之作均非李白原作;涉及生平佚事、篇目归属等内容不构成学术定论,皆标存疑或待考。

↓ 43.6万★ 4user_ff4d9420

データ月:2026-10 · ダウンロード数とスター数は公開スキルレジストリ(ClawHub、SkillHub)から月単位で集計しています。詳しくはデータの方法論をご覧ください。