Use when the user needs to research multiple systems, products, or technologies in parallel and synthesize findings into actionable recommendations. Triggers on competitive analysis, technology comparison, market research, "research X vs Y", architectural research across multiple systems, or any investigation requiring structured multi-source analysis.
Use when the user needs to automate browser interactions — testing web apps, scraping data, filling forms, monitoring pages, or verifying UI behavior. Triggers on requests involving Playwright, browser testing, web scraping, screenshot verification, form automation, or end-to-end testing.
Use when reviewing code changes — PRs, diffs, pre-commit review, or self-review before merging. Triggers on requests to review code, check for bugs, audit security, or assess code quality. Also use before completing any significant implementation to catch issues.