alibabacloud-opc-deploy

Installation
SKILL.md

Alibaba Cloud OPC Deploy

Create all cloud resources for an OPC package step-by-step via the Aliyun CLI. After receiving the SKU prescription from alibabacloud-opc-advisor, follow the Phase flow to create / tag / verify / tear down resources via the Aliyun CLI. The AI assistant explains as it goes, showing progress at every step — white-box, companion-style deployment built for non-technical OPC users.

All user-facing output MUST be in Chinese (zh-CN).

When to Use This Skill

Activate this skill when any of the following holds:

  • The user already has a SKU recommendation from alibabacloud-opc-advisor and explicitly says "help me provision / create / confirm purchase / start deployment"
  • The user names a SKU directly (e.g., "help me spin up a lite_seed")
  • The user asks "the advisor finished recommending — what's next?"
  • The user wants an OPC package but has NOT settled one — 帮我选个合适的套餐 / 哪个套餐合适 / 具体是哪个套餐 / 我想做个 X,用 OPC 套餐能实现吗 / any description of what they want to build followed by a package question. This case activates the skill too — it is Phase -2's job, not a reason to stay out.

⚠️ The absence of a SKU is NOT a reason to skip this skill. The skill owns the no-SKU path end to end (Phase -2 in references/sku-resolution.md): it checks whether the sizing tool is available, offers to install it, and stops until the user reports a package name. If this skill stays out because "nothing is chosen yet", the selection question falls to a general assistant that has no gates — which is exactly the failure this rule exists to prevent.

⚠️ Never answer a package-selection question outside this skill. Comparing tiers, listing what each package contains, quoting prices, or recommending one (even Starter 就够了) is selection work. It belongs to alibabacloud-opc-advisor, reached through Phase -2. Package facts that happen to sit in other context (an AGENTS.md baseline, a memory entry, general knowledge of the product line) are NOT a license to answer — they are for other purposes (e.g. fact-checking an article), never for telling a real user what to buy.

Installs
11
GitHub Stars
265
First Seen
Jul 23, 2026