eve-web-ui-testing-agent-browser
Web UI testing and browser automation. Use Vercel agent-browser for general apps, or the repo-pinned Playwright wrapper inside Eve Horizon. Use when tasks require opening pages, interacting with forms, validating UI flows, taking screenshots, extracting page data, or running repeatable browser-based checks locally or in CI.
What this skill does
# Web UI Testing with agent-browser Use `agent-browser` as the default CLI for deterministic UI checks in app repos. Inside the Eve Horizon repo itself, prefer the repo-pinned Playwright wrapper (see "Eve Horizon Repo Wrapper" below). ## Install agent-browser ```bash # macOS/Linux (recommended) npm install -g agent-browser agent-browser install # Linux containers/VMs that need extra browser libs agent-browser install --with-deps ``` Alternative install on macOS: ```bash brew install agent-browser agent-browser install ``` ## Configure for Reliable Runs Use isolated state for each test target: ```bash # one session per test flow agent-browser --session login-flow open https://example.com # persistent auth/session state per app agent-browser --profile ~/.agent-browser/myapp open https://example.com ``` Set environment variables for CI: ```bash export AGENT_BROWSER_SESSION=ci export AGENT_BROWSER_PROFILE="$PWD/.tmp/agent-browser-profile" export AGENT_BROWSER_PROVIDER=local ``` Optional cloud providers: - Browserbase: set `AGENT_BROWSER_PROVIDER=browserbase`, `BROWSERBASE_API_KEY`, `BROWSERBASE_PROJECT_ID` - Browser Use: set `AGENT_BROWSER_PROVIDER=browseruse`, `BROWSER_USE_API_KEY` - Kernel: set `AGENT_BROWSER_PROVIDER=kernel`, `KERNEL_API_KEY` For proxy testing: ```bash export AGENT_BROWSER_PROXY="http://user:pass@proxy-host:port" ``` ## Install the Upstream Skill (Optional) If your runtime supports skill installation, add the upstream skill: ```bash eve skill install https://github.com/vercel-labs/agent-browser ``` ## Core Workflow Run every flow in this sequence: 1. Navigate: `agent-browser open <url>` 2. Snapshot interactive refs: `agent-browser snapshot -i` 3. Interact with refs: `agent-browser click @e1`, `agent-browser fill @e2 "value"` 4. Re-snapshot after page changes: `agent-browser snapshot -i` 5. Assert output: `agent-browser get text <selector-or-ref>` 6. Capture artifacts: `agent-browser screenshot <path>` ## Minimal Test Template ```bash agent-browser --session smoke open https://example.com/login agent-browser --session smoke snapshot -i agent-browser --session smoke fill @e1 "[email protected]" agent-browser --session smoke fill @e2 "password" agent-browser --session smoke click @e3 agent-browser --session smoke wait --url "**/dashboard" agent-browser --session smoke screenshot ./artifacts/login-dashboard.png agent-browser --session smoke close ``` ## Guardrails - Re-snapshot after every navigation or dynamic UI update; refs become stale. - Prefer `snapshot -i` refs over brittle CSS selectors. - Use `--json` for machine-readable assertions in scripts. - Keep one session/profile per environment to avoid cross-test leakage. - Save screenshots and logs as artifacts for failed runs. ## Eve Horizon Repo Wrapper When working inside the Eve Horizon source repo, use the repo-pinned Playwright wrapper instead of installing `agent-browser` separately. It ships with the repo and targets the local dashboard out of the box: ```bash ./bin/eh browser install # one-time per machine / Playwright upgrade ./bin/eh browser dashboard # headed Chromium with Eve token injected ./bin/eh browser open <url> ./bin/eh browser codegen <url> # capture a draft Playwright spec ./bin/eh browser screenshot <url> [file] ./bin/eh browser test -g "<name>" # run the dashboard Playwright suite ``` Defaults: `chromium` browser, persistent profile under `tmp/playwright-browser/profile`, screenshots in `tmp/playwright-browser/screenshots`, codegen output in `tmp/playwright-browser/codegen`, dashboard URL `http://dashboard.eve.lvh.me`, API URL `http://api.eve.lvh.me`. Set `EVE_API_URL=https://api.eh1.incept5.dev` to point at staging. `./bin/eh browser dashboard` mints a token via `eve auth token --raw` and injects it as `sessionStorage.eve_access_token`. If minting fails, run `eve auth login` first. Escalate exploratory repros into committed Playwright specs under `apps/dashboard/e2e/` when you need assertion coverage, CI protection, or a regression suite. ## References and Templates - Full commands: `references/commands.md` - Ref lifecycle: `references/snapshot-refs.md` - Session strategy: `references/session-management.md` - Authentication flows: `references/authentication.md` - Proxy setup: `references/proxy-support.md` - Video capture: `references/video-recording.md` - Reusable scripts: `templates/*.sh`
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.