HK IPO Subscription Analysis
Paste the following prompt into your AI chat to install this skill:
Please install @user_15f2c71f/hk-daxin according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem context
HK IPO subscription decisions often suffer from fragmented data: prospectuses are on HKEX, subscription multiples are on broker pages, and sentiment requires combining sponsor quality, cornerstone shareholding, and order-book heat. Manually reconciling fields and comparing tranches is easy to do inconsistently.
How it works
The skill focuses on new-share analysis, weighted scoring, and winning-rate estimation. It starts from a ticker or name, then tries to fetch missing fields such as price range, lot size, entry fee, subscription deadline, sponsor, and cornerstone ratio from Sina Finance, HKEX News, Futu, or Tiger. It scores sentiment 30%, scarcity 23%, fundamentals 20%, allocation structure 15%, and valuation 12% on a 0-10 scale. After subscription closes, it can calibrate Group A / Group B tranche probabilities using subscription multiples and historical cases, while noting that final clawback and allocation mechanics change actual outcomes. When data is incomplete, it still produces a marked estimate rather than hiding the gap.
Scope
It is best for pre-subscription screening, not execution. Winning-rate output is a probabilistic reference, not a guarantee.
Use Cases
- Before subscription, fill price range, lot size, entry fee, and deadline to draft an IPO check.
- After closing, compare subscription multiples with sponsor and cornerstone data to judge Group A vs Group B tranches.
- Turn prospectus screenshots or links into structured fields for sentiment, fundamentals, and scarcity notes.
- Score available fields when data is incomplete and flag missing inputs and possible bias.
Best For
- Retail investors tracking HK IPOs who need a quick pre-subscription view of whether a new share is worth joining.
- Secondary-market researchers who need to standardize prospectus, multiples, and sponsor data into one scoring view.
- Wealth advisers guiding clients through Group A / Group B tranche choices with winning-rate references.
- Finance writers compiling weekly HK IPO notes who need scoring summaries and missing-data caveats.
Related Skills
Switch AI from a polite executor into a skeptical thinking partner, using assumption checks, pre-mortems, and evidence gates to expose weak ideas early.
Applies research discipline, data lookup, evidence grading, red-team checks, and structured reporting to analyze AI company investment logic.
Uses Qichacha or Tianyancha MCP data and public information to score corporate credit across 12 dimensions and output a Markdown risk report.
Calculates personal injury compensation via CLI and outputs case summary, standards, line items, sources, and risk notes.