PowerSkills — Browser
SkillWeb & browsingThis skill gives your AI control over the Edge browser on your computer. Once added, your AI can open and read web pages, fill in forms, and take screenshots, so routine browsing tasks get handled for you.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then ask your AI to do something in Edge, like open a website, pull information from a page, or complete a form for you.
Then ask your AI: use the PowerSkills — Browser skill
What your AI can do with it
- List open Edge tabs and move between them
- Navigate to web pages and scroll through them
- Extract page text or HTML so the AI can read web content
- Click elements, type text, and fill in web forms
- Take screenshots of any page
- Run JavaScript on a page for custom actions
What this skill tells your AI
The instructions your AI receives, as published by aloth/powerskills in skills/browser/SKILL.md and read by ahel’s review.
Edge browser automation via CDP (Chrome DevTools Protocol).
Requirements
- Microsoft Edge running with remote debugging:
Start-Process "msedge" -ArgumentList "--remote-debugging-port=9222" - Default port configurable in
config.json(edge_debug_port)
Actions
.\powerskills.ps1 browser <action> [--params]
| Action | Params | Description |
|---|---|---|
tabs | List open browser tabs | |
navigate | --url URL | Navigate to URL |
screenshot | --out-file path.png [--target-id id] | Capture page as PNG |
content | [--target-id id] | Get page text content |
html | [--target-id id] | Get full page HTML |
evaluate | --expression "js" | Execute JavaScript expression |
click | --selector "#btn" | Click element by CSS selector |
type | --selector "#input" --text "hello" | Type into element |
new-tab | --url URL | Open new tab |
close-tab | --target-id id | Close tab by ID |
scroll | --scroll-target top|bottom|selector | Scroll page |
fill | --fields-json '[{"selector":"#a","value":"b"}]' | Fill multiple form fields |
wait | --seconds N | Wait N seconds (default: 3) |
Examples
# List open tabs
.\powerskills.ps1 browser tabs
# Navigate and screenshot
.\powerskills.ps1 browser navigate --url "https://example.com"
.\powerskills.ps1 browser screenshot --out-file page.png
# Extract page text
.\powerskills.ps1 browser content
# Run JavaScript
.\powerskills.ps1 browser evaluate --expression "document.title"
# Fill a login form
.\powerskills.ps1 browser fill --fields-json '[{"selector":"#user","value":"alex"},{"selector":"#pass","value":"secret","submit":"#login"}]'
Multi-Tab Support
Pass --target-id (from tabs output) to operate on a specific tab. Without it, actions target the first page.
Fill Fields Format
JSON array of objects with selector, value, and optional submit:
[
{"selector": "#search-input", "value": "PowerShell automation"},
{"selector": "#filter-type", "value": "recent", "submit": "#apply-btn"}
]
Supports text inputs, selects, and checkboxes. Last field can include submit to click a button.
Signals
- GitHub stars
- 36
- Forks
- 9
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
powerskills-browser- Source
- github.com/aloth/powerskills