Browser automation commands

unclecode/crawl4ai

Command Claude Code

Test current changes with adversarial tests, then run full regression suite.

bytedance/UI-TARS-desktop

Command

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra.

different-ai/openwork

Command

Guide user through OpenWork Browser automation setup.

yusufkaraaslan/Skill_Seekers

Command

One-command skill creation and packaging for a target platform.

yusufkaraaslan/Skill_Seekers

Command

Sync a scraping config's URLs against the live documentation site.

browseros-ai/BrowserOS

Command Claude Code

You are a code review specialist. Identify genuine issues while filtering out false positives.

Untrivial-ai/agent-orchestrator

Command

Inspect and control the current AO session's target-isolated browser. The desktop app must be open. The agent and user share the same live page, cookies, navigation state, and WebContentsView; the runtime remains usable while the Browser panel is hidden. Tabs in this worker share an ephemeral browser profile, while…

Untrivial-ai/agent-orchestrator

Command

Open a URL or workspace file in the desktop browser panel for the current session, or start a deterministic session-owned dev server from an existing .ao/launch.json.

backnotprop/plannotator

Command

The core plan review flow across Claude Code, Codex, and other supported agent hosts.

steipete/summarize

Command

Manage the local daemon and Chrome Native Messaging bridge used by the Side Panel.

zenstory-ai/oh-story-claudecode

Command

A browser-automation command that controls Chrome through the Chrome DevTools Protocol (CDP), including the browser's existing signed-in session.

microsoft/Webwright

Command

Craft a reusable Webwright CLI tool by parameterizing a web task.

microsoft/Webwright

Command

Run a one-shot web task with the Webwright Playwright workflow.

macro-inc/macro

Command Claude Code

Launch local Swagger UI for a service's OpenAPI spec.

Manavarya09/design-extract

Command

Fuse two extracted designs into a single hybrid identity. Pick which axis (colour, typography, spacing, shape, motion, voice, components) comes from which site. Defaults to "visual A × voice B" — same colours/spacing as the first URL, type/voice/components from the second.

qawolf/cli

Command

How to use what qawolf run get --run-id --json returns, and how to read the Playwright trace it links to.

qawolf/cli

Command

Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; request automation of…

cloudflare/skills

Command

Build an AI agent on Cloudflare using the Agents SDK.

vercel/workflow

Command Claude Code

Run the 7full demo workflow.

digitalsamba/claude-code-video-toolkit

Command Claude Code

Generate AI voiceover from script.

digitalsamba/claude-code-video-toolkit

Command Claude Code

Scene-by-scene review in Remotion Studio (before voiceover).

digitalsamba/claude-code-video-toolkit

Command Claude Code

Video projects - list, resume, or create new.

xu-xiang/everything-claude-code-zh

Command

A browser-testing command that creates and runs end-to-end tests with Playwright. End-to-end tests imitate a user moving through a complete feature in a real browser.

WorldFlowAI/everything-claude-code

Command

Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.