powerskills-browser
Automates Microsoft Edge tasks using Chrome DevTools Protocol commands.
Install
mkdir -p .claude/skills/powerskills-browser && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16180" && unzip -o skill.zip -d .claude/skills/powerskills-browser && rm skill.zipInstalls to .claude/skills/powerskills-browser
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Edge browser automation via Chrome DevTools Protocol (CDP). List tabs, navigate, take screenshots, extract page content/HTML, execute JavaScript, click elements, type text, fill forms, scroll. Use when needing to control Edge browser, scrape web content, automate web forms, or take browser screenshots on Windows. Requires Edge with --remote-debugging-port=9222.Key capabilities
- →List open browser tabs in Microsoft Edge.
- →Navigate to a specified URL.
- →Capture a screenshot of a web page.
- →Extract the text content or full HTML of a page.
- →Execute JavaScript expressions within the browser.
- →Fill multiple form fields using a JSON array.
How it works
The skill automates Microsoft Edge via the Chrome DevTools Protocol (CDP) to perform actions like navigation, content extraction, and form filling.
Inputs & outputs
When to use powerskills-browser
- →Automate web form filling
- →Take browser screenshots
- →Extract web page HTML content
About this skill
PowerSkills — Browser
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.
When not to use it
- →When the user wants to automate a browser other than Microsoft Edge.
- →When the user does not have Microsoft Edge running with remote debugging enabled.
- →When the task does not involve web content interaction or extraction.
Prerequisites
Limitations
- →The skill only supports Microsoft Edge.
- →It requires Microsoft Edge to be running with remote debugging enabled.
- →Actions target the first page if no specific target-id is provided.
How it compares
This skill provides direct programmatic control over Microsoft Edge for web automation, unlike manual browser interaction.
Compared to similar skills
powerskills-browser side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| powerskills-browser (this skill) | 0 | 1mo | No flags | Intermediate |
| browser-automation | 39 | 1mo | Review | Intermediate |
| browser-use | 64 | 3mo | Review | Intermediate |
| web-browser | 2 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
browser-automation
browserbase
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Triggers include "browse", "navigate to", "go to website", "extract data from webpage", "screenshot", "web scraping", "fill out form", "click on", "search for on the web". When taking actions be as specific as possible.
browser-use
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
web-browser
mitsuhiko
Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.
gui-task
bivex
>
telegrab-fetch
saturov
Use when the user needs to download one Telegram video from a post link through this repository's telegrab CLI with deterministic preflight checks and machine-readable result fields.
mcporter
consuelohq
--- name: mcporter description: Call MCP servers via MCPorter - browser automation, vision, and other MCP tools homepage: https://github.com/steipete/mcporter metadata: { "openclaw": { "emoji": "🧳", "requires": { "bins": ["npx"] } } }