←back to thread

Show HN: Playwright Skill for Claude Code – Less context than playwright-MCP

(github.com)
186 points syntax-sherlock | 6 comments | 20 Oct 25 11:58 UTC | HN request time: 0.325s | source | bottom

I got tired of playwright-mcp eating through Claude's 200K token limit, so I built this using the new Claude Skills system. Built it with Claude Code itself.

Instead of sending accessibility tree snapshots on every action, Claude just writes Playwright code and runs it. You get back screenshots and console output. That's it.

314 lines of instructions vs a persistent MCP server. Full API docs only load if Claude needs them.

Same browser automation, way less overhead. Works as a Claude Code plugin or manual install.

Token limit issue: https://github.com/microsoft/playwright-mcp/issues/889

Claude Skills docs: https://docs.claude.com/en/docs/claude-code/skills

1. Rooster61 ◴[20 Oct 25 14:47 UTC] No.45644552[source]▶
I have a few questions about test frameworks that use AI services like this.

1)The examples always seem very generic: "Test Login Functionality, check if search works, etc". Do these actually work well at all once you step outside of the basic smoketest use cases?

2) How to you prevent proprietary data from being read when you are just foisting snapshots over to the AI provider? There's no way I'd be able to use this in any kind of real application where data privacy is a constraint.

replies(3): >>45644611 #>>45644980 #>>45645114 #
2. syntax-sherlock ◴[20 Oct 25 14:52 UTC] No.45644611[source]▶
Good questions!

1) Beyond basic tests: You're right to be skeptical. This is best for quick exploratory testing during local development ("does my new feature work?"), not replacing your test suite. Think "scriptable manual testing" - faster than writing Playwright manually, but not suitable for comprehensive CI/CD test coverage.

2) Data privacy: Screenshots stay local in /tmp, but console output and page content Claude writes tests against are sent to Anthropic. This is a local dev tool for testing with dummy data, not for production environments with real user data. Same privacy model as any AI coding assistant - if you wouldn't show Claude your production database, don't test against it with this.

replies(2): >>45644692 #>>45661538 #
3. Rooster61 ◴[20 Oct 25 14:59 UTC] No.45644692[source]▶
Thanks. I keep seeing silver bullet testing solutions pitched left right and center and wondering about these two points. Glad to see a project with realistic boundaries and expectations set. Would definitely give this a shot if I was working on a local project.
4. jcheng ◴[20 Oct 25 15:22 UTC] No.45644980[source]▶
For 2, a lot of companies use AWS Bedrock to access Claude models instead of Anthropic, for exactly this reason. Amazon’s terms say they don’t log prompts or completions and don’t send anything to the model provider. If your production database is already hosted by AWS, it doesn’t seem like much additional risk.
5. siva7 ◴[20 Oct 25 15:34 UTC] No.45645114[source]▶
> Do these actually work well at all once you step outside of the basic smoketest use cases?

Excellent question... no, beyond basic kindergarten stuff playwright (with AI) falls quickly apart. Have some OAuth? Good luck configuring playwright for your exact setup. Need to synthesize all information available from logs and visuals to debug something? Good luck..

6. blks ◴[21 Oct 25 20:52 UTC] No.45661538[source]▶
Another llm-generated response. This is sad.