AnthropicLets the agent open your dev server, click through it, screenshot what it sees and read the browser console. The gap it closes is an agent that writes frontend code it has never actually run.
In the author’s words
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
The description field from SKILL.md, quoted as written.
Read it before you install it
SKILL.md · 90 lines
Install on its own
Or add it to your stack above and install everything at once.
npx skills add https://github.com/anthropics/skills --skill webapp-testingTrust audit
View the source ↗- Checked automatically and confirmed.
- Resolved (HTTP 200), passed
- Checked automatically and confirmed.
- Resolves · 176,702 stars, passed
- Checked automatically and confirmed.
- Transcribed from the author's own page, passed
- Checked automatically and confirmed.
- Last updated 5 months ago, passed
- Checked automatically and confirmed.
- Credited to Anthropic, passed
Goes well with
tdd
Red, green, refactor, run by the agent.
Test-first for features and bug fixes, with integration tests rather than mocks where the integration is the risk. The discipline it adds is writing the failing test before the agent is allowed near the implementation.
npx skills add https://github.com/mattpocock/skills --skill tdd
TestingFull page & trust audit →diagnosing-bugs
A diagnosis loop for hard bugs and performance regressions.
Stops the agent from guessing at a fix. It reproduces, narrows, forms one hypothesis at a time and tests it, which is the difference between a bug being fixed and a symptom being buried.
npx skills add https://github.com/mattpocock/skills --skill diagnosing-bugs
DebuggingFull page & trust audit →systematic-debugging
Forces a method before any fix is proposed.
Fires on any bug, failing test or surprise, and it fires before the agent is allowed to suggest a change. The order is the whole point: understand the failure, then propose. It is the counterweight to an agent that is eager to be helpful.
npx skills add https://github.com/obra/superpowers --skill systematic-debugging
DebuggingFull page & trust audit →
Matt Pocock
Jesse Vincent