293 スキル
Break down unknowable quantities into estimable components to reach order-of-magnitude accuracy when making quick decisions without precise data
Optimize scheduling with algorithms. TRIGGERS - Use when user needs help with scheduling-optimization related tasks.
端到端生成期货跨月套利结论表的入口 skill。输入是四大期货交易所(上期所 / 大商所 / 郑商所 / 广期所)当日的原始行情和合约参数,产出是项目根目录下的「套利结论.xlsx」。内部由两步流水线组成,分别对应两个子 skill —— step 1 `excel-template-contract-fill` 把原始数据整理为统一模板,step 2 `excel-arbitrage-conclusion` 把统一模板转成套利结论表。触发词:期货套利、套利结论、生成套利表格、跑套利流水线、/futures-arbitrage-pipeline。
Build price optimization models. TRIGGERS - Use when user needs help with price-optimization-model related tasks.
Component skill for systematic result interpretation with intellectual honesty in DataPeeker analysis sessions
Build and analyze discrete or continuous Markov chains including transition matrix construction, state classification, stationary distribution computation, and mean first passage times. Use when modeling a memoryless system with observed transition counts or rates, computing long-run steady-state probabilities, determining expected hitting times or absorption probabilities, classifying states as transient or recurrent, or building a foundation for hidden Markov models or reinforcement learning MDPs.
Model system dynamics with stocks (accumulations), flows (rates of change), and feedback to quantitatively predict behavior over time
Data analysis, pattern recognition, and systematic troubleshooting patterns
Design statistically valid A/B tests for marketing optimization
Apply SY5 Systems Archetypes to recognize recurring dynamic patterns across different domains.
Constraint satisfaction problems
Apply SY8 Homeostasis/Dynamic Equilibrium to understand self-regulating mechanisms maintaining stable states despite disturbances.
Apply RE11 Calibration Loops to repeatedly check predictions against outcomes to improve forecasting accuracy.
Development effort estimation with T-shirt sizing and risk adjustment
Adjust aggregated probability forecasts upward when diverse forecasters converge, compensating for crowd conservatism
Hypothesis formation, null/alternative, control/variant setup, randomization hash-based, stratification
Guide users through weighted parametric group sequential design using the wpgsd R package. Use this skill when the user asks about: correlated test statistics across hypotheses, generate_bounds, closed_test, correlation matrices for nested populations, or parametric multiplicity adjustment with group sequential designs.
A state or set of states toward which a dynamical system naturally evolves over time, regardless of where it starts
Probability-weighted average of all possible outcomes used to compare uncertain options and make optimal decisions under risk
Identify reinforcing loops that drive exponential growth and balancing loops that provide automatic correction and self-regulation - map feedback mechanisms to understand control systems, homeostasis, and why systems amplify or dampen changes in engineering, biology, and organizations
Guides applied microeconometrics workflows for estimands, identification, specification, inference, and robustness. Use when working on DiD, IV, RD, panel regressions, treatment effects, or empirical design questions.
数模赛题分析与经典方法检索。分析赛题结构、识别子问题、检索经典建模方法。当用户说'分析赛题'、'problem analysis'、'赛题解读'时使用。
Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical statistical rigor.
Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.
Comprehensive guide to optimization models. Master the concepts, implementation, best practices, and real-world applications of optimization models in professional environments.
Use when evaluating whether evidence supports a causal claim or designing a study to test one. Triggers on "does X cause Y", "should we change X to improve Y", "we noticed X and Y move together", "the data shows...", "our A/B test found...", auditing causal reasoning in a document or analysis, drawing conclusions from observational data, confounders, selection bias.
Comprehensive guide to monte carlo. Master the concepts, implementation, best practices, and real-world applications of monte carlo in professional environments.
Comprehensive guide to prescriptive analytics. Master the concepts, implementation, best practices, and real-world applications of prescriptive analytics in professional environments.
Formulate and solve convex optimization problems for engineering or ML workflows with clear assumptions and constraints.
Design effective excitation signals (step tests) for system identification and parameter estimation in control systems.