High-Dimensional Decision Framework
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_3a2528f5/gaoweijuece.
About this skill
What it addresses
In high-uncertainty situations, decision makers often face three recurring problems: narrow single-dimension analysis, anchoring on short-term information, and analysis paralysis. This skill structures how to think into a reusable decision workflow, turning vague problems into comparable, evaluable, executable options.
How it works
It operates across three layers:
- Module layer: it draws on nine modules, such as Zhouyi decision thinking, systems science, spacetime reasoning, Kondratieff cycles, world models, cosmic perspective, Nüwa decision paradigm, Cangjie information encoding, and Fei-Fei Li cognitive upskilling.
- System layer: it follows a five-layer decision system: cognitive self-check, problem decomposition, root-cause and value judgment, goal and option evaluation, and retrospective improvement.
- Process layer: it selects a path by complexity: simple decisions use the first three layers; moderate decisions use the full flow; major decisions use the nine-step method, from problem framing, multi-dimensional analysis, and future exploration to creative action.
Each selected module produces at least one core insight, and the output is a structured decision report that helps compare options, identify risks, time actions, and close the execution loop.
Boundaries
It fits strategy, organizational transformation, startup trade-offs, cycle judgment, and complex project retrospectives where cross-dimensional reasoning is needed. It does not replace professional legal, financial, medical, or investment compliance advice, and it does not guarantee accurate forecasts. Use it as a reasoning scaffold, not a magic checklist, and still ground conclusions in problem scope, evidence quality, and execution constraints.
Use Cases
- Startup partners evaluate whether to launch a new business line by comparing market, technical, funding, and cycle-position options.
- Investors assess sector allocation by identifying the current Kondratieff, inventory, and mid-cycle position and associated risks.
- Strategy leaders diagnose a failed transformation by building a structured retrospective across goals, results, root causes, and patterns.
- Product owners prioritize feature trade-offs by simulating user paths, competitor reactions, and risk scenarios with a world model.
Best For
- Founders making major calls on startup pivots, organizational transformation, or strategic project approval.
- Investors comparing long-term risk and opportunity across sector allocation and cycle judgments.
- Strategy leaders turning complex project retrospectives into executable improvement actions.
- Product owners evaluating feature trade-offs, roadmap choices, user impact, competitor response, and risk consequences.
Related Skills
A local A-share quant workspace for quotes, k-lines, conditional screening, MA/RSI backtesting, simulated trading, and risk control via REST APIs.
Systematically identify and evaluate the economic moats of listed companies using the Tang Shu Fang investment methodology for long-term investment analysis.
A skill that converts natural language questions into A-stock data queries and returns verifiable structured analysis conclusions, covering multi-dimensional analysis of market trends, fundamentals, and news.
An AI financial copilot by Wind, integrating financial databases and multimodal analysis to provide end-to-end support across investment research, asset allocation, risk control, quant, and report generation.