Accept and take the next available task from the task queue.

Control any macOS application through three integrated methods: AppleScript/JXA, Accessibility API, and Playwright CDP.

Compile results from all worker sub-tasks into a structured markdown report for the Orchestrator. Supports milestone, daily, and final report types.

Use Chrome to build React apps on Google AI Studio (aistudio.google.com). Navigate to the Build page, input prompts, and generate interactive prototypes.

Assign a task to an agent via the task management system.

Assign one or more teams to a project so agents can work on it.

Mark a task as blocked with a reason and optional questions for the orchestrator.

Send a message to all active agent sessions.

Run quality gate checks (build, tests, lint) against the project before completing a task.

One-click attach to user's running Chrome browser via CDP. Auto-discovers Chrome processes, connects via DevTools Protocol, preserves real logins.

Enable browser automation capabilities in Claude Code using the Chrome extension. This allows agents to interact with web pages, fill forms, click buttons, and perform automated browser tasks.

Track and compare competitor content activity across blogs, social media, GitHub releases, and community channels. Supports CrewAI, n8n, Relevance AI, AutoGen, LangChain, and others.

Repurpose source content into platform-optimized versions for X (thread/single), LinkedIn, Xiaohongshu, Substack, and YouTube descriptions. Provides platform-specific style guides, tone modifiers, and brand voice presets.

Create a new project in Crewly with a path, name, and description.

Create a new agent team with members.

Analyze customer feedback to extract sentiment, topics, priority, and actionable insights.

Send a structured task assignment to an agent with priority, context, and optional auto-monitoring. When monitor is provided, automatically subscribes to idle events and schedules fallback checks that are cleaned up on task completion. For formal task tracking, use assign-task instead. For simple messages, use send-message.

Control the macOS desktop: take screenshots, move/click the mouse, type text, and read app content via Accessibility API. Uses native macOS APIs (screencapture, CoreGraphics, System Events, Accessibility) with zero external dependencies.

Generate professional email response drafts based on incoming email context, tone, and intent.