Results for “prediction-intervals”

Use when making a forward-looking claim with a checkable outcome (reply within 24h, error rate will drop, this skill will see more use) — record to state/predictions.jsonl with a review horizon so reflection can grade you later. Closes the in-the-moment double-loop.

Temporal interval algebra for reasoning about time relationships in planning and knowledge representation

Prediction markets data - Polymarket, Kalshi markets, prices, positions, and trades. Use when: the user needs market data, stock analysis, watchlists, or portfolio workflows.

Compares prediction market probabilities from Polymarket with options-implied probabilities to identify mispricing signals and potential arbitrage opportunities.

Debugging constant Markov regime features in RL observations - when HMM probabilities show uniform values instead of dynamic regime estimates

Generates at most one token recommendation and one prediction-market pick per run, each with a falsifiable thesis, entry, sizing, and kill criterion. Returns NO_PICK when no candidate meets the bar.

通用时间抽象接口。当定义时间维度、时序关系、时间演化时调用此技能。

Screen US equities for parabolic exhaustion patterns, generate conditional pre-market short plans, and monitor intraday trigger signals using 5-min bars.

Mine winning ad angles, hooks, and creative patterns from top-performing ads

在启动高风险项目或重要决策前，需要预先识别潜在失败点以增强心理韧性和方案鲁棒性时

Derive selection thresholds from market data instead of hardcoding. Trigger when: (1) reviewing hardcoded parameters, (2) volume/price thresholds seem arbitrary, (3) selection returns too many/few candidates.

rate(http_requests_total[5m])

Econometrics skill for Difference-in-Differences (DID) analysis. Activates when the user asks about: "difference in differences", "DID", "DiD", "diff-in-diff", "parallel trends", "treatment group", "control group", "pre-treatment", "post-treatment", "policy evaluation", "natural experiment", "staggered DID", "event study regression", "two-way fixed effects DID", "callaway santanna", "sun and abraham", "双重差分", "倍差法", "平行趋势", "处理组", "对照组", "政策评估", "事件研究", "交错DID", "渐进处理"

Use when selecting a statistical test with AI consultation, when assumptions need checking against the actual data, when an analysis plan or decision log must be written before running anything, or when results need APA-style reporting with effect sizes.

Influence Functions in Deep Learning

The choice is not about scale or sophistication.

Performance profiling principles. Measurement, analysis, and optimization techniques.