# Send browser-auto-download to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "browser-auto-download",
    "name": "browser-auto-download",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Aaronxx/browser-auto-download",
    "canonicalUrl": "https://clawhub.ai/Aaronxx/browser-auto-download",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/browser-auto-download",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browser-auto-download",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "CHANGELOG.md",
      "CONTRIBUTING.md",
      "package.json",
      "QUICKSTART.md",
      "README.md",
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/browser-auto-download"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/browser-auto-download",
    "downloadUrl": "https://openagent3.xyz/downloads/browser-auto-download",
    "agentUrl": "https://openagent3.xyz/skills/browser-auto-download/agent",
    "manifestUrl": "https://openagent3.xyz/skills/browser-auto-download/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/browser-auto-download/agent.md"
  }
}
```
## Documentation

### Browser Auto Download v4.1.0 (Enhanced)

Download files from dynamic webpages with intelligent detection and multi-step navigation.

### Key Features

Auto-download capture: Detects downloads triggered automatically on page load
Multi-step navigation: Finds and navigates to platform-specific pages (PC/Desktop versions)
Platform auto-detection: Windows x64/ARM64, macOS Intel/Apple Silicon, Linux
Event listening: Captures all download events without requiring button clicks
Smart fallback: Tries multiple strategies (auto-download, navigation, clicking)

### When to Use

Use this skill for:

Auto-download sites: Downloads start automatically when page loads
Multi-step flows: Homepage - click "PC version" - download page
Dynamic content: Download links generated via JavaScript
Interactive downloads: Requires clicking buttons or navigating UI

NOT for: Direct file URLs (use curl/wget instead)

### Option 1: Automatic (Recommended)

python skills/browser-auto-download/scripts/auto_download.py \\
  --url "https://example.com/download"

The script will:

Check for auto-downloads on page load
Look for platform-specific page links (PC/Desktop version)
Navigate if needed
Try clicking download buttons as fallback

### Option 2: Built-in Shortcuts

# WeChat DevTools
python skills/browser-auto-download/scripts/auto_download.py --wechat

# Meitu Xiuxiu
python skills/browser-auto-download/scripts/auto_download.py --meitu

### Option 3: Python Module

from skills.browser-auto-download.scripts.auto_download import auto_download

result = auto_download(
    url="https://example.com/download",
    auto_select=True,   # Platform detection
    auto_navigate=True  # Multi-step navigation
)

if result:
    print(f"Downloaded: {result['path']}")

### Three-Stage Strategy

Stage 1: Auto-Download Detection

Page loads - Check for downloads - Success?
    Yes:                    No:
    Save file               Go to Stage 2

Stage 2: Multi-Step Navigation

Look for "PC/Desktop" link - Navigate - Check downloads - Success?
    Yes:                        No:
    Save file                  Go to Stage 3

Stage 3: Button Clicking

Try multiple selectors - Click - Wait for download - Save

### Platform-Specific Page Detection

Automatically finds links like:

"meitu for PC" - pc.meitu.com
"Desktop version" - desktop.example.com
"Windows Download" - windows.example.com

Keywords: pc, desktop, windows, mac, download, 电脑, 桌面, 客户端

### Auto-Download Sites (Best Case)

# Sites that trigger download on page load
python skills/browser-auto-download/scripts/auto_download.py \\
  --url "https://pc.meitu.com/en/pc?download=pc"

### Multi-Step Navigation

# Homepage - PC version - Download
python skills/browser-auto-download/scripts/auto_download.py \\
  --url "https://xiuxiu.meitu.com/" \\
  --auto-navigate  # Enable (default: True)

### Manual Selector (Fallback)

# If auto-detection fails
python skills/browser-auto-download/scripts/auto_download.py \\
  --url "https://example.com/download" \\
  --selector "button:has-text('Download for free')"

### Disable Features

# Don't navigate to platform pages
python skills/browser-auto-download/scripts/auto_download.py \\
  --url "https://example.com" \\
  --no-auto-navigate

# Don't detect platform
python skills/browser-auto-download/scripts/auto_download.py \\
  --url "https://example.com" \\
  --no-auto-select

### Platform Detection

SystemArchitectureKeywords UsedWindowsAMD64/x86_64windows, win64, x64, 64-bit, pcWindowsx86/i686windows, win32, x86, 32-bit, pcmacOSARM64 (M1/M2/M3)macos, arm64, apple siliconmacOSx86_64 (Intel)macos, x64, intelLinuxx86_64linux, x64, amd64

### Troubleshooting

Download not starting:

Use --headless (default: False) to observe the process
Check stderr for auto-download messages
Try --no-auto-navigate if navigation is causing issues
Use --selector to manually specify button

Wrong version downloaded:

Check platform detection in stderr output
Use --no-auto-select and manually specify --selector
Verify the site offers multiple versions

Navigation going to wrong page:

Disable with --no-auto-navigate
The site may not have platform-specific pages

File not saved:

Check write permissions in output directory
Ensure sufficient disk space
Wait for large files (up to 3 minutes)

### stderr (Progress)

Starting browser (visible)...
Opening: https://example.com
Checking for auto-downloads...
Checking for platform-specific page link...
Found platform page: https://pc.example.com
Navigating to platform page...
Download detected: software_v2.1.0_win64.exe
Saving: software_v2.1.0_win64.exe

SUCCESS!
File: C:\\Users\\User\\Downloads\\software_v2.1.0_win64.exe
Size: 231.9 MB

### stdout (JSON result)

{
  "path": "C:\\\\Users\\\\User\\\\Downloads\\\\software_v2.1.0_win64.exe",
  "filename": "software_v2.1.0_win64.exe",
  "size_bytes": 243209941,
  "size_mb": 231.9,
  "platform": "Windows AMD64"
}

### Meitu Xiuxiu (Multi-step + Auto-download)

from auto_download import quick_download_meitu

result = quick_download_meitu()
# Flow: Homepage - PC page link - Navigate - Auto-download

### WeChat DevTools (Button click)

from auto_download import quick_download_wechat_devtools

result = quick_download_wechat_devtools()
# Flow: Homepage - Click "Stable Windows 64" - Download

### Generic Software (Mixed)

result = auto_download(
    url="https://example.com/downloads",
    auto_select=True,    # Detect Windows 64-bit
    auto_navigate=True   # Find "Desktop version" link
)

### Requirements

pip install playwright
playwright install chromium

### Custom Platform Keywords

Modify get_system_preference() in the script to add custom keywords.

### Integration with Scripts

import subprocess
import json

result = subprocess.run([
    'python', 'skills/browser-auto-download/scripts/auto_download.py',
    '--url', 'https://example.com/download'
], capture_output=True, text=True)

if result.returncode == 0:
    data = json.loads(result.stdout)
    print(f"Downloaded: {data['path']}")  # Use the file

### Batch Downloads

urls = [
    "https://example1.com/download",
    "https://example2.com/download",
    "https://example3.com/download"
]

for url in urls:
    result = auto_download(url)
    if result:
        print(f"Success: {result['filename']}")
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: Aaronxx
- Version: 1.0.1
## Source health
- Status: healthy
- Source download looks usable.
- Yavira can redirect you to the upstream package for this source.
- Health scope: source
- Reason: direct_download_ok
- Checked at: 2026-05-07T17:22:31.273Z
- Expires at: 2026-05-14T17:22:31.273Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/browser-auto-download)
- [Send to Agent page](https://openagent3.xyz/skills/browser-auto-download/agent)
- [JSON manifest](https://openagent3.xyz/skills/browser-auto-download/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/browser-auto-download/agent.md)
- [Download page](https://openagent3.xyz/downloads/browser-auto-download)