← ClaudeAtlas

web-browselisted

Browse the web programmatically with ThinkRun — drive a real or cloud browser to navigate, interact, extract, and screenshot, from the CLI or any MCP client. Use when: visit or open a URL, check a webpage, interact with a browser, verify something works live, take screenshots of a page, scrape or extract content, automate a browser task. Do NOT use for structured UX audits with scoring and fix reports — use ux-audit for that.
dundas/thinkrun · ★ 1 · Web & Frontend · score 75
Install: claude install-skill dundas/thinkrun
# Web Browse Drive a browser programmatically with **ThinkRun**. Two interfaces, same capabilities: - **`thinkrun` CLI** — for shell scripts and terminal use. `npm install -g @thinkrun/cli` (bin: `thinkrun`). - **`@thinkrun/mcp`** — for MCP clients (Claude Code, Cursor, Cline, Windsurf). `npx @thinkrun/mcp`. Both support two execution modes: - **Local mode** — controls your real Chrome via the ThinkRun extension + native host. Best for sites needing your login/cookies, or visual work on the browser you already have open. - **Cloud mode** — provisions an isolated Playwright browser on Fly.io. Best for headless/autonomous scraping, multi-agent work, and anti-detection (stealth). Mode is auto-detected; override per-command with `--mode local|cloud` (CLI) or the `set_mode` tool (MCP). ## When to use which | Scenario | Mode | Why | |----------|------|-----| | Site needs your login cookies | **Local** | Uses your real Chrome session | | Visual/interactive work on an open tab | **Local** | Attach to the tab you're looking at | | Headless autonomous scraping | **Cloud** | No Chrome needed, runs detached | | Multi-agent / parallel sessions | **Cloud** | Isolated browser per session | | Anti-detection needed | **Cloud** | Built-in stealth (no `navigator.webdriver`) | > See [references/details.md](references/details.md) for the full CLI command + MCP tool reference, common patterns, and error codes. ## Setup ### Install ```bash # CLI (shell use) npm install -g @thinkrun/cli