菜单
Use when implementing and exposing a product/application service or UI that should run outside Reef root. Choose child/resource VM placement, stand up the app, and report how to reach it.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when doing code work that must be integration-friendly: branches, commits, tests, PR-ready receipts, owned paths, and parent-friendly handoff.
Use when handling parent commands such as steer, abort, pause, or resume, or when deciding how urgently to react to inbox messages from above.
Use when agents need to coordinate through reef store, peer signals, barriers, rendezvous, or child/peer communication without breaking authority boundaries.
Create a new service module for reef. Use when adding a new capability to the server — a new store, API routes, LLM tools, behaviors, or dashboard widget.
Use when a task has multiple independent subsystems, needs recursive delegation, or requires a parent to split implementation and then integrate the results.
Use when inspecting the live fleet, differentiating active vs historical lineage, tracing ancestry, checking subtree state, or doing post-mortem investigation.
| name | app-deployment |
| description | Use when implementing and exposing a product/application service or UI that should run outside Reef root. Choose child/resource VM placement, stand up the app, and report how to reach it. |
Use this skill when the task is to build, run, or expose a product/application service or UI that is not clearly part of Reef's own operator control plane.
For repo implementation requests, default deployment target is outside Reef root.
Typical choices:
agent_vm for a cohesive implementation slice that owns its own runtime setuplieutenant for a persistent coordinator that owns an operational systemresource_vm for stateful support infrastructure, raw environments, databases, or long-lived app hostingDo not treat Reef root as the default home for the product you are building.
Before you stand anything up, decide explicitly:
Is this a Reef control-plane feature?
Or is it product/application infrastructure?
Default to product/application infrastructure on a child VM unless the answer to (1) is clearly yes.
Root should usually:
Root should not usually:
If a child owns deployment, root should not quietly redo that deployment itself.
If the current execution path changes:
Then report the change so scheduled checks, receipts, and supervision state remain truthful.
When reporting a deployed app or service, include:
agent_vm, lieutenant, resource_vm)