ui-test
Plain English E2E UI testing. Describe tests in natural language, agent executes via browser tool, then exports real Playwright test scripts for CI/CD. Use when asked to create UI tests, test a website, or generate Playwright scripts.
What this skill does
# 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](https://pleblab.dev)*
## Workflow
1. **Create** — User names a test and describes steps in plain English
2. **Run** — Agent opens the clawd browser, executes each step, screenshots each action
3. **Export** — Agent generates a Playwright `.spec.ts` from the verified steps
4. **CI/CD** — User drops the script into their test suite, runs with `npx playwright test`
## Agent Execution Flow
When running a test:
1. Load test definition: `node scripts/ui-test.js get "<name>"`
2. Start clawd browser: `browser action=start profile=clawd`
3. Navigate to the test URL
4. For each plain English step:
a. Interpret what the user means (click, type, assert, wait, etc.)
b. Use `browser action=snapshot` to see the page
c. Use `browser action=act` with 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
5. Save run results: `node scripts/ui-test.js save-run "<name>" passed=true/false`
6. Report results to user with pass/fail per step
When exporting to Playwright:
1. Load the test definition and most recent successful run
2. Map each plain English step to Playwright API calls based on what worked during execution
3. Generate a `.spec.ts` file with proper imports, test structure, and assertions
4. 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 [email protected] in the email field" | `act: type ref="email" text="[email protected]"` | `page.getByLabel('Email').fill('[email protected]')` |
| "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.describe` block with test name
- `test.beforeEach` with 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:
1. **Before each step**: take a screenshot → save as `step-NN-before.jpg`
2. **After each step**: take a screenshot → save as `step-NN-after.jpg`
3. **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:
```bash
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.mp4
```
Then 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`
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.