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

Provides guidance on using the Aeon library for time series forecasting, covering model selection, implementation, and evaluation.

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations from Arize AI.

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

Systematically collects, categorizes, and distributes indicators of compromise (IOCs) during and after security incidents to enable detection, blocking, and threat intelligence sharing.

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

Triages and enriches indicators of compromise (IPs, domains, file hashes, URLs, email artifacts) from phishing emails, security alerts, or threat feeds, assigning confidence scores and dispositions using VirusTotal, AbuseIPDB, MalwareBazaar, and MISP.

Analiza series temporales: tendencia, estacionalidad y pronóstico con Prophet, statsmodels y ML, incluyendo descomposición, tests de estacionariedad y evaluación contra baselines.

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

Predicts gene and transcript structure from a DNA sequence using the hosted Genomic Intelligence API, producing a report and JSON output.

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.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Recommend model families and validation strategy based on data, constraints, and objective. Use when: (1) choosing algorithms, (2) balancing bias/variance, (3) planning benchmark baselines. NOT for: final legal/compliance sign-off.

Design a spaced retrieval schedule for any topic list and timeline. Use when planning units, term sequences, or revision programmes.

Econometrics skill for panel data models. Activates when the user asks about: "panel data", "fixed effects", "random effects", "Hausman test", "within estimator", "between estimator", "two-way fixed effects", "clustered standard errors panel", "FE model", "RE model", "pooled OLS", "unobserved heterogeneity", "panel regression", "first difference estimator", "entity fixed effects", "time fixed effects", "面板数据", "固定效应", "随机效应", "豪斯曼检验", "双向固定效应", "面板回归", "个体效应", "时间效应", "一阶差分"

Use for writing, reviewing, debugging, testing, or diagnosing Python Bayesian models built directly with PyMC, including Model, coords/dims, Data, random variables, potentials, posterior sampling, prior/posterior predictive checks, and InferenceData output. Trigger on model geometry, shape errors, divergences, sampler choice, mutable prediction data, and probabilistic validation. Do not use for Bambi formula models, NumPyro/JAX programs, ArviZ-only analysis of existing draws, deterministic optimization, or general statistics without PyMC code.

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.

Mathematical AI interpretability with sheaf cohomology, spectral analysis, causal inference, and hallucination prevention

Tracks indicators of compromise from initial discovery through validation, enrichment, deployment, monitoring, and retirement to maintain a high-quality, actionable indicator database.

Proactively hunt for threats by analyzing IOCs, detecting behavioral anomalies in telemetry, and prioritizing signals mapped to MITRE ATT&CK.

Design and evaluate paid-ad experiments with hypotheses, randomization, sample-size calculations, guardrails, and decision rules for A/B and split tests.

Automates enrichment of raw indicators of compromise with multi-source threat intelligence context using SOAR platforms, Python pipelines, or TIP playbooks to reduce analyst triage time and standardize enrichment outputs.

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

Use for writing, reviewing, debugging, testing, or diagnosing Bayesian regression and hierarchical models built with Bambi formulas, Model, Family/Likelihood/Link, Prior, fit, prior predictive, and predict. Trigger on common versus group-specific terms, categorical coding, family/link choice, automatic prior scaling, missing rows, PyMC backend settings, and InferenceData predictions. Do not use for hand-built PyMC graphs, NumPyro programs, ArviZ-only analysis of existing draws, frequentist statsmodels formulas, or generic pandas work.

Perform fast genomic interval operations (overlap, nearest, merge, coverage, cluster, complement, subtract, count-overlaps), multi-format bioinformatics I/O, DataFusion SQL, and pileup on Polars DataFrames via the polars-bio library, serving as a scalable alternative to bioframe and bedtools.

v5.6.0 joint multi-TF model: single model per symbol with broadcast 1Hour context replaces dual 15Min/1Hour models. Trigger: (1) replacing weighted-voting model aggregation, (2) adding broadcast features to vectorized env, (3) limited training data + worried about overfitting from doubling obs_dim, (4) backtest builder mismatch with newer feature counts.

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])

Performs differential expression analysis on label-free quantitative (LFQ) proteomics data from MaxQuant and DIA-NN outputs, including preprocessing, imputation, statistical testing, and visualization.

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"

Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.