메뉴
Alibaba Cloud expert guardrails — RAM least-privilege, data boundaries, residency (mainland/international split), cost, and official-source validation. Trigger when designing or reviewing any Alibaba Cloud workload, especially agents or LLMs (Model Studio/Bailian, Qwen, AgentScope).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Bootstrap or harden a project's operating model for mixed human and AI delivery teams. Use when starting a repository, adopting an agent harness, defining authority and risk tiers, coordinating parallel agents safely, binding evidence and review to an exact candidate, or correcting fragmented rules that prevent coherent, consistent, complete delivery.
Architecture decisions, trade-off analysis, and ADR authoring. Trigger when a significant technical decision needs to be made, documented, and owned — not when an implementation detail needs a choice.
Decompose an epic into atomic parallelizable tasks and route each task to the right skill. Use this as a meta-router when you have more than one skill available and need to decide which applies. Trigger at the start of any multi-track epic or when the skill count in your harness exceeds ~12.
Check proposed stack, data flows, cloud choices, and delivery controls against declared enterprise policies, compliance frameworks, and security controls. Trigger at R2/R3 risk classification, before locking architecture decisions, or when the operating profile names a governance pointer.
Govern the SemVer release process — versioning discipline, tag-based GitHub releases, changelog hygiene, and the ADR that confirms the release strategy is agreed. Trigger when setting up a release process, before a first public release, or when release practice has become inconsistent. Owned by delivery-orchestrator.
Session-start orientation for this team harness. Load first, before any work. Explains the operating contract, when each skill triggers, and how installed companion plugins supply agent-craft capabilities while this harness supplies the team contract. Trigger at the start of every session and whenever unsure which skill applies.
| name | alibaba-expert |
| description | Alibaba Cloud expert guardrails — RAM least-privilege, data boundaries, residency (mainland/international split), cost, and official-source validation. Trigger when designing or reviewing any Alibaba Cloud workload, especially agents or LLMs (Model Studio/Bailian, Qwen, AgentScope). |
Same discipline, different control plane: RAM and ActionTrail are the guardrails; Model Studio and AgentScope are the agent surface. The mainland/international split is a design input, not an afterthought.
This skill enforces the discipline that makes Alibaba Cloud workloads production-safe: identity, data boundaries, cost controls, and residency. It is not a feature tour — it is a checklist of the things that cause incidents and compliance failures when skipped.
Identity and RAM — verify least-privilege for every principal:
Data boundaries — for every data store:
Data residency — for each resource:
Cost controls — for every LLM, compute, or storage resource:
Network and egress — confirm:
Observability — confirm:
Run the Adversarial Gate — common Alibaba Cloud failure modes: long-lived AccessKeys, public OSS buckets, mainland/international residency confusion, uncapped DashScope spend, missing ActionTrail.
alibabacloud.com/help (international) · help.aliyun.com (mainland)github.com/alibaba/spring-ai-alibaba).github.com/aliyun (incl. terraform-provider-alicloud and landing-zone modules)github.com/modelscope/agentscope · github.com/alibaba/spring-ai-alibaba · github.com/QwenLM