メニュー
Playwright-based browser QA skill for guided setup, auth handoff, scripted runs, and artifact capture.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Autonomous code refactoring agent that rewrites messy functions, splits large files, removes duplication, improves naming, enforces structure, and preserves behavior.
Interact with Anytype's local REST API to manage spaces, objects, types, properties, tags, lists, and search.
Generate API integration test suites from Harnessy regression artifacts using a QA profile plus optional delivery-profile adapters.
Generate browser integration suites from Harnessy regression artifacts using a QA profile plus optional delivery-profile adapters for fixtures, routes, and helper imports.
End-to-end product development orchestrator with human-in-the-loop reviews.
Safe repo pull/push workflow that targets the repository integration branch, uses deterministic planning, and keeps PRs moving with a bounded autonomous resolution loop.
| name | browser-qa |
| description | Playwright-based browser QA skill for guided setup, auth handoff, scripted runs, and artifact capture. |
| disable-model-invocation | true |
| allowed-tools | Read, Grep, Glob, Bash, ApplyPatch, Question |
| argument-hint | [setup|start|auth|inspect|run|qa-script|report] [--app <path>] [--url <url>] [--script <path>] [--headed] [--allow-destructive] |
Use Playwright for guided browser-based QA across local, preview, staging, or production environments while keeping setup deterministic, credentials safe, and artifacts easy to review.
Optional subcommand: setup, start, auth, inspect, run, qa-script, or report
Optional flags: --app <path>, --url <url>, --script <path>, --headed, --allow-destructive
Template paths are resolved from ${AGENTS_SKILLS_ROOT}/browser-qa/.
${AGENTS_SKILLS_ROOT}/browser-qa/commands/browser-qa.md exactly.${AGENTS_SKILLS_ROOT}/browser-qa/scripts/detect-runtime.js to inspect README.md, app-level READMEs, and package metadata before asking startup questions.${AGENTS_SKILLS_ROOT}/browser-qa/scripts/check-playwright.js to deterministically report whether Playwright packages and browser binaries are ready before attempting browser execution.read-only mode. Only perform create/edit/delete/submit/approve side effects when the user explicitly opts into destructive actions.${AGENTS_SKILLS_ROOT}/browser-qa/scripts/parse-qa-script.js to normalize markdown or JSON QA scripts into a deterministic scenario list before execution.${AGENTS_SKILLS_ROOT}/browser-qa/scripts/summarize-artifacts.js after execution to normalize artifact paths, scenario outcomes, and blocked reasons for handoff to the user or the qa skill..xlsx workbook with python3 ${AGENTS_SKILLS_ROOT}/qa/scripts/export-user-test-script.py <markdown-path> [xlsx-path] so human testers can use either format.qa workflow, return a structured summary that qa can incorporate into bug reports and QA artifacts.qa delegation and follow-up fixes.