Use after changing extension code, to prove it works: which test tier to run, the red-before-green rule, and what to record in the PR test plan. Start here, then branch to `browser-verify` or `e2e-spec` as needed.
Use when an extension change needs exploration in a real browser — finding selectors, watching a flow, reading console or network. Drives the agent's own headless Chromium through the Playwright CLI. Exploration only; the verification that counts is a spec…
Use when about to write or modify a Playwright e2e spec under `packages/danmaku-anywhere/e2e/`. Points at the canonical doctrine and surfaces the load-bearing rules so the spec doesn't get bounced in review.
Use when you need to load a specific published preview/nightly extension build into the agent's browser by run-number, branch name, or tag. Faster than rebuilding locally when you only want to exercise an existing artifact.
Use to monitor an open PR for AI/bot review comments, evaluate them critically, push fixes for real issues, and resolve threads — capped at a sensible duration so it self-terminates. Invoke as "babysit PR
Use when adding or changing user-facing strings in the extension (i18n.t calls or locale JSON) under packages/danmaku-anywhere. Surfaces the extract workflow and footguns so the change does not fail the i18n CI check or ship an untranslated or inconsistent…
Use to open a fresh Claude session in a new terminal tab for a da-dev worktree, after `scripts/da-bootstrap.mjs` prints its READY block. Covers Warp, Windows Terminal, and a manual fallback.
Use when evaluating review comments from AI reviewers (gemini-code-assist, copilot-pull-request-reviewer) on a PR. Default to assuming the reviewer is right; verify before declining. Includes reporting in chat and resolving threads after handling.