UI Test — Plain English E2E Testing (🧪)
Describe your UI tests in plain English. The agent figures out how to find buttons, navigate the app flow, and execute each step — no selectors or code needed. It screenshots every major step, stitches them into a walkthrough video, and DMs you the result with a pass/fail report.
*Made in 🤠 Texas ❤️ PlebLab*
UI Test — Describe it. I'll test it.
Workflow
- Create — User names a test and describes steps in plain English
- Run — Agent opens the clawd browser, executes each step, screenshots each action
- Export — Agent generates a Playwright
.spec.tsfrom the verified steps - CI/CD — User drops the script into their test suite, runs with
npx playwright test
Agent Execution Flow
When running a test:
- Load test definition:
node scripts/ui-test.js get "<name>" - Start clawd browser:
browser action=start profile=clawd - Navigate to the test URL
- For each plain English step: a. Interpret what the user means (click, type, assert, wait, etc.) b. Use
browser action=snapshotto see the page c. Usebrowser action=actwith the appropriate request (click/type/press/etc.) d. Take a screenshot after each step e. Record what selector/ref was used and whether it passed - Save run results:
node scripts/ui-test.js save-run "<name>" passed=true/false - Report results to user with pass/fail per step
When exporting to Playwright:
- Load the test definition and most recent successful run
- Map each plain English step to Playwright API calls based on what worked during execution
- Generate a
.spec.tsfile with proper imports, test structure, and assertions - Save to the user's project or a specified output path
Step Interpretation Guide
The agent should interpret plain English steps like:
| User says | Browser action | Playwright equivalent |
|---|---|---|
| "click the Sign In button" | act: click ref="Sign In button" | page.getByRole('button', {name: 'Sign In'}).click() |
| "type hello@test.com in the email field" | act: type ref="email" text="hello@test.com" | page.getByLabel('Email').fill('hello@test.com') |
| "verify the dashboard shows Welcome" | snapshot + check text | expect(page.getByText('Welcome')).toBeVisible() |
| "wait for the page to load" | act: wait | page.waitForLoadState('networkidle') |
| "click the hamburger menu" | act: click (find menu icon) | page.getByRole('button', {name: 'menu'}).click() |
| "scroll down" | act: evaluate fn="window.scrollBy(0,500)" | page.evaluate(() => window.scrollBy(0, 500)) |
| "check the Remember Me checkbox" | act: click ref="Remember Me" | page.getByLabel('Remember Me').check() |
| "select 'USD' from the currency dropdown" | act: select values=["USD"] | page.getByLabel('Currency').selectOption('USD') |
| "take a screenshot" | browser action=screenshot | page.screenshot({path: 'step-N.png'}) |
| "verify URL contains /dashboard" | check current URL | expect(page).toHaveURL(/dashboard/) |
Commands
Run via: node ~/workspace/skills/ui-test/scripts/ui-test.js <command>
| Command | Description |
|---|---|
create <name> [url] | Create a new test |
add-step <name> <step> | Add a plain English step |
set-steps <name> <json> | Replace all steps |
set-url <name> <url> | Set the test URL |
get <name> | Show test definition |
list | List all tests |
remove <name> | Delete a test |
save-run <name>... | Save execution results |
runs [name] | Show run history |
export <name> [outfile] | Export as Playwright script |
Export Format
Generated Playwright files include:
- Proper TypeScript imports
test.describeblock with test nametest.beforeEachwith navigation to base URL- Each step as a sequential action with comments showing the original English
- Assertions where the user said "verify", "check", "should", "expect"
- Screenshots on failure
Screenshots & Video
During test execution, the agent should:
- Before each step: take a screenshot → save as
step-NN-before.jpg - After each step: take a screenshot → save as
step-NN-after.jpg - On failure: take a screenshot → save as
step-NN-FAIL.jpg
Screenshots are saved to: ~/.ui-tests/runs/<slug>-<timestamp>/
After the run completes, generate a walkthrough video:
ffmpeg -framerate 1 -pattern_type glob -i '~/.ui-tests/runs/<folder>/step-*.jpg' \
-vf "scale=1280:-2" -c:v libx264 -pix_fmt yuv420p -y output.mp4Then send the video to the chat.
Storage
- Test definitions:
~/.ui-tests/<slug>.json - Run history:
~/.ui-tests/runs/<slug>-<timestamp>/run.json - Screenshots:
~/.ui-tests/runs/<slug>-<timestamp>/step-*.jpg - Video:
~/.ui-tests/runs/<slug>-<timestamp>/walkthrough.mp4 - Exported scripts: user-specified path or
./tests/<slug>.spec.ts