Back to directory

Playwright Skill

An agent skill that lets a coding agent write and run real Playwright browser-automation code on the fly, from simple page checks to complex multi-step flows.

Playwright Skill

Playwright Skill is an Agent Skill that lets a coding agent write and execute Playwright browser automation on the fly, covering everything from a simple page test to a complex multi-step flow. It is also packaged as a Claude Code plugin, and the agent decides on its own when the skill applies, loading only the information it needs for a given task.

It runs the browser visibly by default so automation can be watched in real time, provides a portable executor for both file-based and inline scripts with stable module resolution, uses progressive disclosure so a concise skill file only pulls in the full API reference when needed, and manages temporary files safely without race conditions. It suits tasks where the automation script itself is the artifact worth keeping and rerunning, such as loops, assertions, multiple browser contexts, network interception, screenshots or video; for simpler interactive browsing or tool-based control with accessibility snapshots, the project points to Microsoft's own Playwright tooling instead.

It installs with a skills command-line tool and is released under the MIT license.

More in Testing

See all 69
  • Canary

    runcanary.ai

    An independent testing service, backed by Y Combinator, that runs an application and tries to break every change an AI coding agent makes, reporting what would have reached production.

  • MoEWatch

    github.com

    A diagnostic and audit library for Mixture-of-Experts models in HuggingFace Transformers that instruments router modules to catch expert collapse, routing entropy collapse and load imbalance during training.

  • Mockwave

    github.com

    An open-source, multi-protocol mock server for HTTP, GraphQL, SOAP, and gRPC, with weighted traffic splitting, dynamic JavaScript responses, chaos-testing fault injection, and an MCP server so an AI assistant can generate mock rules directly.