メニュー
Research browser and webview UI safety, accessibility, and automation constraints, including the mandatory prohibition on native browser dialogs.
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
Screenshot-first visual end-to-end validation policy for browser-rendered UI and webview jobs after verifier approval.
Default engineering workflow. Classify a technical request, route it through the native T1/T2/T3 engineering fleet, and return only independently verified completion to the orchestrator.
Safely operate Claude Code's opt-in advanced capabilities—sessions, worktrees, agent teams, Skills, MCP, plugins, hooks, Channels, schedules, goals, and Agent SDK integrations—when the user explicitly asks for one. Do not use for an ordinary build request.
Routes selective local Codex plan, code, verification, and visual judgment with evidence-backed blocking and strict cost caps.
Shared evidence, accessibility, context, and handoff rules for the local design-agent fleet.
Produces contextual creative theses and bounded visual directions without generic model defaults.
| name | research-browser-ui-safety |
| description | Research browser and webview UI safety, accessibility, and automation constraints, including the mandatory prohibition on native browser dialogs. |
| user-invocable | false |
Use with researcher-core whenever the target includes a browser-rendered UI or webview.
alert, confirm, prompt, window.* variants, and beforeunload prompts. Record every observed use and its user/test impact.RESEARCH_EVIDENCE, include a browser_ui_dialog_policy item: observed native-dialog use, modal/inline-validation recommendation, migration risks, and deterministic validation measures.