Use when automating browser tasks - clicking, filling forms, taking screenshots, debugging UI, or testing web flows. Requires chrome-devtools or playwright MCP.
Use when analyzing Claude Code raw session logs, parsing JSONL transcripts, investigating agent behavior, extracting metrics from session data, debugging subagent dispatches, or building session analysis tools. Triggers on session IDs, JSONL paths, ~/.claude/projects references, or requests to understand what happened in a CC session.
Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors.
Use when writing or modifying frontend React/HTML components, creating interactive widgets, building forms, or implementing overlays/modals/dropdowns — ensures accessible output by default with correct ARIA, keyboard, focus, and screen reader support
(user)
Use when writing or reviewing Playwright E2E tests - locator strategies, Page Object Model, auto-waiting, network interception, and WordPress/WooCommerce test helpers.
Use when writing or reviewing Go tests - standard testing package, table-driven tests, subtests, test helpers, httptest, benchmarks, fuzz testing, and interface-based mocking.
Use when writing or reviewing JavaScript/TypeScript tests - Jest/Vitest assertions, React Testing Library queries, module mocking, async patterns, and snapshot discipline.