Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →dokhacgiakhoa/testing-automation-mcp
Autonomous E2E testing using Playwright Model Context Protocol (MCP).
Passed 20 of 23 test cases with the skill, and 12 of 23 without it.
and 15 more in the full report
10 fixed11 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
For a search interface on `https://docs.dev/search`, we want to type 'MCP tools' into `input#search-input` and then click `button#search-submit`. What sequence of tool calls handles this two-step operation?
| Checked | Without skill | With skill |
|---|---|---|
| Executes playwright_fill with input#search-input and value 'MCP tools'. | Missed | Passed |
| Executes playwright_click with selector 'button#search-submit'. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill empowers AI Agents to autonomously write, execute, and debug E2E tests using the official Playwright MCP Server. It transforms passive testing into an active, agentic workflow.
| Tool | Description | Usage |
|---|---|---|
playwright_navigate | Go to a specific URL. | {"url": "http://localhost:3000"} |
playwright_click | Click an element by selector. | {"selector": "button[type='submit']"} |
playwright_fill | Fill input fields. | {"selector": "#email", "value": "[email protected]"} |
playwright_screenshot | Take a screenshot of the viewport. | {"path": "debug/error.png"} |
playwright_evaluate | Run custom JS in the browser. | {"script": "return document.title"} |
test cases passed, vs 12 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.