TDD
Build features and fixes through agreed public interfaces and small failing-test-to-implementation cycles.
Matt Pocock
- Coding
- Testing & Debugging
- Test-Driven Development
- Testing
Choose between reproducing a bug, writing a regression test, and inspecting a running application. These tasks need different evidence and different stopping conditions.
An unexplained failure calls for diagnosis; a known behavioral change calls for a test that expresses the expected result. Browser QA adds evidence from the running interface. Keep reproduction steps, observed output, and the proposed fix separate so an agent can check whether the change addresses the original failure rather than merely making a command pass.
Build features and fixes through agreed public interfaces and small failing-test-to-implementation cycles.
Matt Pocock
Diagnose difficult bugs through a reproducible signal, minimized case, and verified correction.
Matt Pocock
Investigate root causes through four evidence-led phases before implementing and verifying a correction.
Jesse Vincent
Reproduce defects, save replayable evidence, and propose regression checks with gstack’s report-only workflow.
Garry Tan
Collect DOM, console, request, and screenshot evidence from an isolated browser session.
Addy Osmani
Run targeted browser checks on a local web app with Python Playwright. Capture the failing interaction and relevant browser evidence so another developer can repeat it.
Anthropic
Connect composable engineering Skills with a software development workflow and integrations for coding agents, covering design, implementation, review, and verification.
Jesse Vincent
Connect a coding agent to Playwright through MCP for navigation, accessibility snapshots, and browser interactions. Compare the persistent MCP workflow with the separate Playwright CLI and its official Skill.
Microsoft
Let a coding agent inspect live Chrome with console, network, performance, and page tools. Use the evidence to diagnose a particular failure rather than treating a screenshot as the whole investigation.
Chrome DevTools
Skills supply instructions; projects supply software or supporting resources. Check each source for setup, runtime, access, and license requirements.
Start with a minimal reproduction and ranked hypotheses before editing code.
Use TDD to express the behavior and preserve the failing case as a regression test.
Inspect browser interactions and report reproducible findings before deciding whether to change the application.
Find instructions and software for the next stage of your work, from code changes and interface design to office tasks and media production.
Collect the failing input, logs, and expected result so the investigation can end with a reproducible verification.