From oh-my-claudeagent
MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.
npx claudepluginhub utsavbalar1231/oh-my-claudeagent --plugin oh-my-claudeagentThis skill uses the workspace's default tool permissions.
**Task**: $ARGUMENTS
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
Task: $ARGUMENTS
No task specified → ask user what browser task to perform.
Browser automation via Playwright MCP — testing, scraping, verification, interaction.
The Playwright MCP server must be configured. Add to your project's .mcp.json:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["@playwright/mcp@latest"]
}
}
}
Or for headed mode (visible browser):
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["@playwright/mcp@latest", "--headless=false"]
}
}
}
When the Playwright MCP server is running, these tools become available:
browser_navigate — Go to a URLbrowser_go_back / browser_go_forward — Browser history navigationbrowser_wait — Wait for page load or conditionbrowser_click — Click an element (uses accessibility snapshot selectors)browser_type — Type text into focused elementbrowser_fill — Fill form field (clears existing value first)browser_select_option — Select dropdown optionbrowser_hover — Hover over elementbrowser_drag — Drag from one element to anotherbrowser_press_key — Press keyboard key (Enter, Tab, Escape, etc.)browser_snapshot — Get accessibility tree snapshot (preferred over screenshot)browser_screenshot — Take a PNG screenshotbrowser_get_text — Extract text content from pagebrowser_execute_javascript — Run JavaScript in page contextbrowser_tab_list — List open tabsbrowser_tab_new — Open new tabbrowser_tab_select — Switch to tabbrowser_tab_close — Close tabbrowser_navigate to the URLbrowser_snapshot to get page structurebrowser_screenshot for visual evidencebrowser_navigate to form pagebrowser_fill each form fieldbrowser_click submit buttonbrowser_snapshot to verify resultbrowser_navigate to target pagebrowser_snapshot for structured contentbrowser_execute_javascript for complex extractionbrowser_snapshot after each navigation to understand new pageIf Playwright MCP server is not configured (no mcp__playwright__* tools available), fall back to /oh-my-claudeagent:dev-browser.
Primary interaction is via Playwright MCP tools (mcp__playwright__*), not via Bash. Use the MCP tools directly for all browser operations.
browser_snapshot over browser_screenshot — structured accessibility databrowser_snapshot output