メニュー
Use when you have a written implementation plan to execute in a separate session with review checkpoints
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。
Browser automation for protected sites. This skill should be used when navigating websites with advanced protection layers (Cloudflare, DataDome, Akamai), performing browser automation that requires natural interaction patterns, or when standard Playwright fails due to compatibility issues. Covers Camoufox, CDP, Patchright, fingerprint management, captcha handling, and natural behavior simulation.
Core skill for all Bridge IDE agents. This skill should be used for bridge communication, task management, agent coordination, and understanding the Bridge IDE platform. Covers bridge_register, bridge_send/receive, task lifecycle, approval gates, and team coordination patterns.
Restart a Bridge IDE agent by ID. Use when an agent is stuck, crashed, or needs to be restarted. Accepts agent ID as argument (e.g. /agent-restart backend).
Deploy Bridge IDE — Server-Restart mit Health-Check und Agent-Benachrichtigung. Use when deploying changes, restarting the server, or applying backend updates.
Use when completing any task via bridge_task_done, claiming work is finished, or about to report task results on the Bridge platform - requires concrete verification evidence with command output before any completion claim
PFLICHT vor jeder externen Aktion. Wird automatisch geladen wenn ein Agent mit externen Services interagiert, Browser-Aktionen durchfuehrt, Accounts verwaltet, APIs aufruft, Dateien auf fremden Systemen aendert, oder Credentials benoetigt. Erzwingt systematische Analyse VOR dem Handeln. IMMER laden wenn: Login, Signup, API-Call, Browser-Aktion, Deployment, Account-Management, DNS-Aenderung, Domain-Verwaltung, Payment, oder jede andere Interaktion mit der Aussenwelt.
SOC 職業分類に基づく
| name | executing-plans |
| description | Use when you have a written implementation plan to execute in a separate session with review checkpoints |
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for architect review.
Announce at start: "I'm using the executing-plans skill to implement this plan."
Default: First 3 tasks
For each task:
When batch complete:
Based on feedback:
After all tasks complete and verified:
STOP executing immediately when:
Ask for clarification rather than guessing.
Return to Review (Step 1) when:
Don't force through blockers - stop and ask.
Required workflow skills:
