/alibabacloud-opc-advisor

name: alibabacloud-opc-advisor
description: "Alibaba Cloud OPC (one-person-company) cloud resource SELECTION advisor — recommends one of 7 standard SKU packages with exact monthly price, purchase URL, and plain-language launch/migration path for non-technical solo founders. Read-only selection; does NOT deploy (that is the companion `alibabacloud-opc-deploy` skill). WHEN TO USE: user wants to deploy/publish/launch a website or app online, make a project accessible to others, choose a cloud server/package for a one-person business, migrate from Vercel/Netlify/AWS/another platform to Alibaba Cloud (esp. 'slow in China'), or built something with an AI tool (QoderWork/WorkBuddy/Cursor/Codex/Bolt) and wants it online. ALSO trigger for potentially out-of-scope requests (company team / large traffic / PV over 1M) so this skill can explicitly judge and decline. 触发词（中文）：用 QoderWork/WorkBuddy/Cursor/Bolt 等做了网站/小程序想上线或让别人访问；从 Vercel/AWS 等迁到阿里云、国内访问慢；选阿里云套餐/服务器/配置（个人/独立开发者）；AI 小程序（植物识别/AI 记账）想上线；公司/大流量需求（触发后由本 skill 判定是否超范围并拒绝）。输出用中文。"

Alibaba Cloud OPC Advisor

Help non-technical OPC (one-person-company) users go from "business goal + current starting point" directly to a **SKU recommendation + exact monthly price + purchase page guide + plain-language deployment path**, without needing to understand any cloud product terminology.

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

When to Use This Skill

• User asks about OPC packages, pricing, or server configuration
• User wants to deploy/publish/launch something online, or make a project accessible to others (friends, public), or generate a link for others to open
• User wants to choose a server/package for their one-person business or solo-founder project
• User wants to migrate from another platform (Vercel/Netlify/AWS/other SaaS) to Alibaba Cloud, especially when "access is slow in China" / "can't open domestically"
• User has built something with AI tools (QoderWork, WorkBuddy, Cursor, Codex, Bolt, etc.) and wants it accessible online
• User built an AI app (image recognition / AI bookkeeping / AI chat / VLM) and wants to launch it
• **Boundary**: even when a request looks out of OPC scope (company team 50+ / large traffic / PV over 1M), STILL trigger this skill so it can explicitly judge and decline — do not answer with generic advice instead of invoking the skill

**Trigger broadly, then route.** When in doubt about whether the user's intent maps to OPC, trigger the skill and let the routing/entry-probe decide; do not silently skip.

**Disambiguate with `alibabacloud-opc-deploy`:** if the user already has an advisor prescription (SKU selected) and wants to execute the deployment, route to `alibabacloud-opc-deploy`. This skill is for **selection and recommendation** only.

Routing

OPC advisor intent?
├── Starting from scratch / has idea / has code to deploy  → A1 Zero-Start
├── Already live on external platform with real users      → A2 Migration
├── Intent unclear                                         → Ask clarification
└── Out of OPC scope (50+ person company / pro dev team)   → Boundary notice

**Routing rule:** always determine A1 vs A2 FIRST before any SKU recommendation. Read the matched workflow template before outputting. Look up references on demand.

**Strong-signal fast-path (HIGHEST priority — overrides the probe):** When the prompt ALREADY states an explicit deployment status, route directly and DO NOT ask the entry-probe question:

• Explicit A2 (migration): an already-deployed signal (`已经部署在 Vercel/Netlify/AWS/其它云/服务器`) combined with any live/pain signal (`有真实用户` / `用户在用` / `国内访问慢` / `打不开` / `想迁到阿里云`) → route **directly to A2 Migration**. Never fall back to A1 zero-start for these prompts.
• Explicit A1 (zero-start): a not-yet-live signal (`还没上线` / `只在本地跑` / `还没开始` / `刚写完代码想第一次发布`) → route **directly to A1**.
• Only when the branch is genuinely ambiguous (e.g., a bare `想从 AWS 迁过来` with NO live-status/user signal) do you ask the entry-probe question. Direct A2/A1 routing does NOT skip the 2 sizing questions (Q-scale / Q-userdata) — those remain gated by the Interaction Flow.

Entry Probe

Ask the user (in Chinese). Sample probe question (zh-CN):

你现在是手上还啥都没开始，还是已经写好/部署好了点东西要继续往前走？

| User State | Signal | Branch | |---|---|---| | Starting from scratch / local demo not yet online | `我有想法 / 还没动手 / 代码写完了 / 想发布` | **A1** | | Already deployed on external platform with real users | `已部署在 XX / 有用户在用 / 国内打不开 / 想搬` | **A2** |

Workflows

| Workflow | File | Use when | |---|---|---| | **A1 Zero-Start** | [a1-zero-start.md](references/a1-zero-start.md) | User starts from scratch or has local code, wants first deployment | | **A2 Migration** | [a2-migration.md](references/a2-migration.md) | User already live on another platform, migrating to Alibaba Cloud |

SKU Decision Flow

A1/A2 → PII gate: Q-userdata=Yes? → floor = lite_seed (skip Starter entirely)
       → Determine tier (starter / lite / pro)
         │  (tier from Q-scale + Q-userdata + Q6; see sku-sizing-questionnaire §2)
         ├── Starter (ONLY reachable when Q-userdata=No)
         │   → Q6 (AI) inferred from keywords (ask only if ambiguous)
         │   ├── No AI  → starter_webui
         │   └── Yes AI (text only, no VLM) → starter_app
         │
         ├── Lite → Q-scale mapping (see concurrency-to-sku.md)
         │   ├── seed (≤15) / growth (15-80) / traction (80-200)
         │
         └── Pro → Q-scale 200+ ; steady vs burst inferred from prompt (ask only if ambiguous)
             ├── steady (不能宕机 / 稳定高可用)
             └── burst (流量集中 / 直播 / 活动 / 尖刺)

**PII absolute gate (iron-rule #16):** If Q-userdata = Yes (any of: registration / login / payment / file upload by users), the floor is `lite_seed` — Starter tier is **unreachable** regardless of Q-scale or Q6. User account data requires independent RDS which only Lite+ SKUs provide. Never output `starter_webui` or `starter_app` when Q-userdata = Yes. T