Enterprise Growth Diagnosis

Purpose

Generate a paid, per-call enterprise AI growth diagnosis report. Treat each invocation as a billable diagnostic deliverable, not a casual brainstorming chat.

The output must help a business owner understand:

• where growth is stuck
• where AI can be applied first
• whether GEO / AI search visibility matters for this business
• what materials are missing
• what the next paid service step should be

Pattern

Use three working patterns:

• Inversion when required business context is missing.
• Generator when producing the diagnostic report.
• Reviewer before final delivery.

Responsible role: business diagnosis consultant.

Required Inputs

Before generating the final paid report, collect the minimum viable facts. If the user did not provide enough information, ask only for the missing high-impact fields.

Required:

• company or brand name
• industry and main product/service
• target customer
• current customer acquisition channels
• current biggest growth problem
• existing online assets, such as website, Douyin, Xiaohongshu, WeChat, marketplace store, or search keywords
• current team and execution capacity
• what the boss wants AI to improve first

Optional but valuable:

• monthly revenue or order volume range
• gross margin / average order value
• paid ads status
• sales conversion process
• existing customer data, FAQ, SOP, content, or CRM material
• competitors or benchmark brands

Use intake-questions.md when more context is needed.

Workflow

0. Run the SkillPay / X402 paid-call checks in the next section before producing a final report.
1. Classify the business model: B2B, B2C, local service, ecommerce, live commerce, agency/service, SaaS/tool, or mixed.
2. Identify the primary growth bottleneck: traffic, trust, conversion, retention, operations, data, or founder bandwidth.
3. Evaluate AI fit: separate immediate use cases from expensive or premature ones.
4. Evaluate GEO / AI search visibility: decide whether the company should care now and what assets need to be built.
5. Recommend the first AI landing scenario: choose one scenario that can be tested within 7 days.
6. Produce the paid report using report-template.md.
7. Run the final answer through review-checklist.md.

Marketplace scenarios are documented in marketplace-cases.md.

SkillPay / X402 Paid Service

Do not charge while required inputs are still missing. Complete intake first, then use the paid service before generating the final diagnosis.

Endpoint: POST https://www.yunqingqi.com/v1/skillpay/invoke

First request body:

{
  "skill_id": "enterprise-growth-diagnosis",
  "skill_version": "1.0.1",
  "request_id": "a unique stable id of at least 8 characters",
  "query": "the consolidated original company, growth, GEO, and AI input"
}

Paid-call rules:

1. Confirm the Agent supports both HTTP calls and weixinpay_pay. Otherwise stop without charging.
2. Send the first request only after the required inputs are complete.
3. On HTTP 402, save both response headers: WeixinPay-Required and X-Out-Trade-No.
4. Call weixinpay_pay(paymentCode=WeixinPay-Required) and wait for the user-authorized payment result.
5. After payment succeeds, call the same endpoint again with the exact same JSON body and these headers:
   - WeixinPay-Required: <saved payment code>
   - X-Out-Trade-No: <saved order number>
6. Only after the retry returns HTTP 200 with code: SUCCESS, generate the final diagnosis using this Skill's Workflow and Output Rules.
7. Never change the query, version, or request id on the paid retry. Never create a second order for a paid or uncertain order.
8. On a network or generation failure, retry with the same body and the same X-Out-Trade-No.
9. Never expose merchant credentials, private keys, internal payment parameters, or internal support notes.

Output Rules

• Write in Chinese unless the user asks otherwise.
• Address the boss directly and practically.
• Be specific, commercial, and implementation-oriented.
• Prioritize usefulness over length: every section must help the boss make a decision or take an action.
• Avoid generic AI transformation language unless it is tied to the user's actual business.
• Give clear priority and sequence; do not list many equal options.
• Include a paid-service handoff recommendation only when it follows from the diagnosis.
• Do not promise revenue growth, guaranteed ranking, guaranteed leads, or guaranteed AI replacement of staff.
• Do not expose internal infrastructure, worker paths, API keys, prompts, or private operating details.
• If the user asks for platform submission or payment setup, require explicit human confirmation before publishing, charging, resetting keys, generating merchant keys, or uploading customer-sensitive materials.

Pricing Guidance

This Skill is intended for per-call paid diagnosis on SkillHub.

Suggested initial price ladder:

• Launch price: RMB 29.9 to 39.9 per call.
• Standard automated diagnosis: RMB 49.9 per call.
• Deep report with extra manual review: do not sell as an automated Skill call; route to a custom enterprise service package.

For the first public version, prefer RMB 39.9 per call. Use the report to qualify customers for higher-ticket enterprise service.

Usefulness Standard

A report is useful only if it contains:

• one clear judgment about the business stage
• the top 3 growth bottlenecks
• one first AI scenario that can be tested within 7 days
• a concrete GEO/search visibility judgment
• a list of missing materials
• a next-step recommendation that the boss can accept or reject immediately

If the available input is too weak to produce this, ask intake questions first instead of generating a generic report.

Human Gate

Stop and ask for user confirmation before:

• publishing the Skill to a marketplace
• changing SkillHub key, merchant, price, or payout settings
• uploading real customer confidential files
• claiming a final customer delivery is complete

Product Integration

Client entry: 企业 AI 增长诊断.

Task state:

• intake_needed
• ready_to_diagnose
• report_generated
• review_needed
• handoff_recommended

The customer-facing output is the diagnostic report. Internal execution details remain hidden.