webapp-testing

name	webapp-testing
description	Toolkit for testing local web applications and browser workflows with MCP browser tools. Use this whenever the user asks to inspect a web UI, verify frontend behavior, debug a local app, capture screenshots, trace browser errors, or exercise forms and interactions in a browser.

Webapp Testing

Use the MCP browser tools for browser work. Use Playwright for both read-only inspection and interaction. Prefer the Guardian wrapper tools when available.

Use browser-session-defense as the companion skill when the question is about browser security boundaries, risky browser actions, or the distinction between Guardian-managed browsing and the user's own browser activity.

Tool Selection

• Use Guardian wrapper tools first: browser_navigate, browser_read, browser_links, browser_extract, browser_state, browser_act.
• Use raw mcp-playwright-* tools only when the wrapper surface cannot answer the question.
• Do not use mcp-playwright-browser_run_code; it is blocked by policy.
• Avoid evaluate unless the existing browser tools cannot answer the question and the action is worth approval.

Workflow

1. Confirm how the app is started if it is not already running.
2. Open the page with the lowest-power Guardian wrapper tool that can answer the question.
3. Inspect before acting:
   • page text or markdown
   • semantic structure
   • interactive elements
   • screenshots or snapshots when visual state matters
4. Identify selectors or target elements from observed state.
5. Perform the minimum interaction needed to verify behavior.
6. Capture evidence: screenshot, relevant console output, network details, or structured findings.

Read-Only Recon First

When the user asks "what is on this page?" or "why is this screen wrong?", prefer:

• browser_read
• browser_links
• browser_extract
• browser_state when interactive refs matter

Interactive Testing

For user journeys and bug reproduction:

• navigate first
• wait for the page to settle
• inspect the current state before clicking blindly
• use descriptive selectors or the browser snapshot output
• capture a screenshot before and after important interactions

Common Pitfalls

• Do not guess selectors before inspecting the current page state.
• Do not jump straight to raw MCP tools when the wrapper surface already covers the task.
• Do not stop at "it failed"; collect the screenshot, console messages, and any obvious network errors.

Read references/browser-tool-selection.md when you need a quick tool-selection checklist.