browser-automation
This skill should be used when working on frontend code, debugging UI issues, verifying visual changes, scraping web pages, testing web features, or inspecting page state. Also triggers on "open browser", "take screenshot", "navigate to URL", "scrape website", "extract page content", "check accessibility", or any web automation task. Use proactively during frontend development to verify changes visually.
What this skill does
# Browser Automation with Rodney
Rodney is a CLI tool that drives a persistent headless Chrome instance. Each command connects to the same long-running browser process, making it natural to script multi-step browser interactions via Bash.
## When to Use Proactively
**Use without being asked when:**
- Verifying frontend changes visually
- Debugging UI issues or layout problems
- Scraping or extracting content from web pages
- Testing web features or form interactions
- Checking accessibility of page elements
## Core Workflow
### 1. Start the Browser
```bash
rodney start # headless (default for agents)
rodney start --show # visible window (for debugging with user)
```
Check if already running first:
```bash
rodney status || rodney start
```
### 2. Navigate and Wait
```bash
rodney open "https://example.com"
rodney waitstable # wait for DOM to settle
```
Always wait after navigation. Prefer `waitstable` for general use, `waitidle` when network requests matter, `waitload` for simple pages.
### 3. Inspect the Page
```bash
rodney title # page title
rodney url # current URL
rodney text "h1" # text content of element
rodney html ".main-content" # HTML of element
rodney attr "a.logo" "href" # attribute value
rodney js "document.querySelectorAll('.item').length" # run JS
```
### 4. Take Screenshots
```bash
rodney screenshot /tmp/page.png # full viewport
rodney screenshot -w 1280 -h 720 /tmp/page.png # specific size
rodney screenshot-el ".hero-section" /tmp/hero.png # element only
```
Use the Read tool to view screenshot files after capturing them.
### 5. Interact with Elements
```bash
rodney click "button.submit"
rodney input "#email" "[email protected]"
rodney select "#country" "GB"
rodney submit "form#login"
rodney hover ".tooltip-trigger"
```
### 6. Check Element State
```bash
rodney exists ".error-message" # exit 0 if exists, 1 if not
rodney visible ".modal" # exit 0 if visible, 1 if not
rodney count ".list-item" # prints count
rodney assert "document.title" "Expected Title" # assert equality
```
Use exit codes for conditional logic:
```bash
if rodney exists ".error-message"; then
rodney text ".error-message"
fi
```
### 7. Accessibility Inspection
```bash
rodney ax-tree --depth 3 # dump a11y tree (truncated)
rodney ax-tree --json # full tree as JSON
rodney ax-find --role button # find all buttons
rodney ax-find --role link --name "Sign in" # find specific link
rodney ax-node "#main-nav" --json # a11y info for element
```
The accessibility tree is often more useful than screenshots for understanding page structure, especially for forms and navigation.
### 8. Stop When Done
```bash
rodney stop
```
The SessionEnd hook automatically runs `rodney stop`, so explicit cleanup is not required but is good practice when switching contexts.
## Session Management
Rodney keeps a single Chrome process alive between commands. State (cookies, localStorage, current page) persists across commands until `rodney stop`.
**Directory-scoped sessions** isolate browser state per project:
```bash
rodney start --local # state in ./.rodney/state.json
rodney open "..." # auto-detects local session
rodney stop # cleans up local session
```
**Tab management** for multi-page workflows:
```bash
rodney newpage "https://docs.example.com"
rodney pages # list all tabs
rodney page 0 # switch back to first tab
rodney closepage 1 # close second tab
```
## Common Patterns
### Visual Verification After Code Changes
```bash
rodney status || rodney start
rodney open "http://localhost:3000"
rodney waitstable
rodney screenshot /tmp/after-change.png
```
### Form Testing
```bash
rodney open "http://localhost:3000/login"
rodney waitstable
rodney input "#email" "[email protected]"
rodney input "#password" "password123"
rodney click "button[type=submit]"
rodney waitstable
rodney screenshot /tmp/after-login.png
```
### Content Extraction
```bash
rodney open "https://example.com/data"
rodney waitstable
rodney js "JSON.stringify([...document.querySelectorAll('tr')].map(r => r.textContent))"
```
### Waiting for Dynamic Content
```bash
rodney open "https://example.com/dashboard"
rodney wait ".data-loaded" # wait for specific element
rodney text ".metric-value" # then extract content
```
## Tips
- **Selectors**: Standard CSS selectors work everywhere. Prefer specific selectors (IDs, data attributes) over fragile positional ones.
- **JavaScript**: `rodney js` wraps expressions as `() => { return (expr); }` — return complex values as JSON strings.
- **Screenshots**: Always save to `/tmp/` and use the Read tool to view them.
- **Exit codes**: `rodney exists` and `rodney visible` return exit code 1 on failure, not stderr — use `if` statements, not `||`.
- **Debugging**: Use `rodney start --show` to make the browser visible when debugging visual issues with the user.
For the complete CLI command reference, consult **`references/commands.md`**.
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.