pwcli

Coordinate browser automation tasks across named sessions with command chains.

2|Updated Apr 25, 2026
One-click install
npx skills add https://github.com/chyax98/pwcli --skill pwcli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pwcli
Source: https://github.com/chyax98/pwcli/tree/main/skills/pwcli
Command: npx skills add https://github.com/chyax98/pwcli --skill pwcli

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

pwcli addresses the difficulty of orchestrating browser automation tasks across multiple sessions by turning ad-hoc commands into stable, agent-driven task chains.

Core Features & Use Cases

  • Agent-first command orchestration across sessions
  • Session lifecycle management: create, attach, recreate, and close
  • Page exploration, actions, waits, diagnostics, and state reuse
  • Built-in auth providers and authentication flows
  • Routing to built-in references and workflows for guided automation

Quick Start

Create a named session and begin chaining commands to explore a page, perform actions, and collect diagnostics.

Frequently Asked Questions about pwcli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage multiple browser automation sessions concurrently?

Browser automation sessions are managed through per-session serialization, allowing you to create, attach, recreate, and close named sessions. This enforces stable, agent-driven task chains without concurrent conflicts.

Can I inspect network and console logs during Playwright automation?

Yes, Playwright automation workflows support built-in network and console inspection. You can collect diagnostics and capture screenshots directly within your active named session during command execution.

What is the best way to reuse authentication state across browser sessions?

Reusing authentication state is handled through built-in auth providers and state reuse workflows. You establish authentication flows within a named session and reuse that state for subsequent automation tasks.

Does pwcli require external dependencies for page exploration and actions?

No, pwcli operates with zero external dependencies. It uses a centralized frontmatter-driven metadata system and internal references to load guidance for page exploration, action loops, and mocks directly into context.

Why should I use agent-driven command chains for browser diagnostics?

Agent-driven command chains transform ad-hoc commands into stable, orchestrated task sequences. This approach solves the difficulty of coordinating complex browser diagnostics and actions across multiple sessions reliably.