🔬Experiment Analysis Skills
Browse skills in the Experiment Analysis category.
Ab Test Setup
A powerful skill for Claude agents.
upgrade-integration
Integrate Carnegie Learning's UpGrade A/B testing platform into LMS and EdTech applications. Guides setup of decision points, experiment conditions, LTI/xAPI integration, and outcome logging. Use when asked to add A/B testing, experiments, or feature flags to educational software.
group-sequential-methods
Group sequential design methods for interim analyses, alpha spending, and futility stopping. Use when designing trials with interim looks or implementing spending functions.
casino-math-balancer
Calculate and balance casino game mathematics including odds, RTP, house edge, variance, and payout tables. Use when designing betting mechanics, balancing meta-pot systems, creating probability tables, validating game economy math, or ensuring fair-but-profitable game mechanics. Triggers on requests involving gambling math, odds calculations, payout balancing, or RTP optimization.
power-optimization-patterns
Direct and tradeoff-based optimization strategies for clinical trial design. Use when optimizing sample size, selecting design parameters, or performing sensitivity analysis.
time-to-event-methods
Survival analysis methods including weighted logrank, MaxCombo, RMST, and milestone tests. Use when analyzing TTE data or choosing analysis methods for non-proportional hazards.
analysis-assumptions-log
Systematic tracking of analysis assumptions and decisions. Use when documenting data filtering choices, handling edge cases, making assumptions about missing data, or logging methodology decisions.
cv-strategy
Cross-validation configuration and fold management for this competition
simtrial-fundamentals
Core simtrial package functions for time-to-event clinical trial simulation. Use when generating survival data, performing weighted logrank tests, or running TTE simulations.
ab-test-analysis
Rigorous A/B test statistical analysis. Use when analyzing experiment results, calculating statistical significance, checking for sample ratio mismatch, or validating test design before launch.
funnel-analysis
Conversion funnel analysis with drop-off investigation. Use when analyzing multi-step processes, identifying conversion bottlenecks, A/B testing funnel performance, or optimizing user journeys.
clinical-trial-design-patterns
Common clinical trial design patterns including multi-arm, multi-endpoint, adaptive, and stratified designs. Use when selecting or implementing trial designs.
mediana-fundamentals
Core Mediana package functions for Clinical Scenario Evaluation (CSE). Use when designing data models, analysis models, evaluation models, and running comprehensive trial simulations.
multiplicity-methods
Multiple testing procedures reference for clinical trials. Use when selecting or implementing multiplicity adjustments, gatekeeping procedures, or graphical approaches.
product-analytics
Product analytics and growth expert. Use when designing event tracking, defining metrics, running A/B tests, or analyzing retention. Covers AARRR framework, funnel analysis, cohort analysis, and experimentation.
growth-hacker
Design and execute growth experiments using lean, data-driven tactics
nixtla-timegpt-lab
Provides expert Nixtla forecasting using TimeGPT, StatsForecast, and MLForecast. Generates time series forecasts, analyzes trends, compares models, performs cross-validation, and recommends best practices. Activates when user needs forecasting, time series analysis, sales prediction, demand planning, revenue forecasting, or M4 benchmarking.
ab-test-designer
Design statistically valid A/B tests for marketing optimization
nixtla-uncertainty-quantifier
Quantifies prediction uncertainty using conformal prediction.Use when risk assessment, scenario planning, or decision-making under uncertainty is required.Trigger with "quantify uncertainty", "generate prediction intervals", "confidence bands".
nixtla-timegpt-finetune-lab
Enables TimeGPT model fine-tuning on custom datasets with Nixtla SDK. Guides dataset preparation, job submission, status monitoring, model comparison, and accuracy benchmarking. Activates when user needs TimeGPT fine-tuning, custom model training, domain-specific optimization, or zero-shot vs fine-tuned comparison.
fyp-jupyter
Complete data science research workflow for Jupyter notebooks covering CRISP-DM methodology from data loading through model validation, with MLflow experiment tracking integration, phase-based workflow guidance (Exploration, Systematic Experimentation, Analysis, Documentation), and skill integration points. Use when working on FYP data science projects requiring systematic data preprocessing, EDA, feature engineering, modeling, statistical validation, experiment tracking, or needing guidance on what to work on at each project phase. Includes MLflow setup for tracking 30+ experiment runs, weekly work planning for 10-week FYP timeline, and clear decision framework for when to use which skill (fyp-jupyter, crossvit-covid19-fyp, fyp-statistical-validator, tar-umt-fyp-rds, tar-umt-academic-writing).
nixtla-experiment-architect
Generate production-ready forecasting experiments with StatsForecast and TimeGPT. Use when setting up model benchmarking or cross-validation. Trigger with 'scaffold experiment' or 'compare models'.
empirical-config-builder
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.
escape-room-balance-engineer
Balance escape room difficulty, timing, and hint systems to achieve 60-70% completion rate. Designs progressive difficulty curves, three-tier hint systems, stuck-point analysis, and playtest metrics. Use when balancing game difficulty, designing hint systems, analyzing playtest data, or optimizing escape room completion rates.
nixtla-baseline-review
Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other benchmark datasets). Use when the user asks about baseline performance, model comparisons, or metric interpretation for Nixtla time-series experiments. Trigger with "baseline review", "interpret sMAPE/MASE", or "compare AutoETS vs AutoTheta".
data-science
Data science and analytics expertise for statistical analysis, machine learning pipelines, data governance, business intelligence, predictive modeling, and analytics strategy. Use when building ML models, analyzing data, creating dashboards, or designing data architectures.
nixtla-model-benchmarker
Generate benchmarking pipelines to compare forecasting models and summarize accuracy/speed trade-offs. Use when evaluating TimeGPT vs StatsForecast/MLForecast/NeuralForecast on a dataset. Trigger with "benchmark models", "compare TimeGPT vs StatsForecast", or "model selection".
nixtla-forecast-validator
Validates time series forecast quality metrics by comparing current performance against historical benchmarks. Detects degradation in MASE and sMAPE metrics. Activates when user mentions "validate forecast", "check forecast quality", or "assess forecast metrics".
nixtla-event-impact-modeler
Analyze causal impact of events on time series forecasts using TimeGPT. Use when quantifying promotion or disaster effects. Trigger with 'event impact analysis' or 'causal analysis'.
fyp-statistical-validator
Automate statistical validation, hypothesis testing, and confidence interval calculations required by TAR UMT thesis standards and top ML research conferences. Use when you need to (1) calculate 95% confidence intervals for model performance metrics, (2) perform hypothesis testing to compare models (McNemar's test, paired t-test, Bonferroni correction), (3) generate APA-formatted results tables for thesis chapters, (4) create reproducibility statements for experimental setup, (5) validate statistical significance of model improvements, or (6) format results according to academic publishing standards. Essential for FYP Chapter 4 (experimental setup documentation) and Chapter 5 (results with statistical validation).
nixtla-model-selector
Automatically selects the best forecasting model between StatsForecast and TimeGPT based on time series data characteristics. Use when unsure which model performs best. Trigger with "auto-select model", "choose best model", "model selection".
nixtla-cross-validator
Performs rigorous time series cross-validation using expanding and sliding windows.Use when needing to evaluate the performance of time series models on unseen data.Trigger with "cross validate time series", "evaluate forecasting model", "time series backtesting".
run-stata
Run Stata code by copying it into tempdo.do and executing the file. Use this when the user wants to run Stata code, test a figure, execute a do-file section, or run regressions. This workaround ensures graphs display correctly and multi-line commands with /// work properly.
ipd-meta-analysis
Teach Individual Patient Data (IPD) meta-analysis methods for analyzing raw participant-level data from multiple studies. Use when users have access to original datasets, need to explore treatment-effect modifiers, or want to conduct time-to-event analyses.
ml-workflow
ML development workflow covering experiment design, baseline establishment, iterative improvement, and experiment tracking best practices.
trial-sequential-analysis
Teach Trial Sequential Analysis (TSA) for controlling type I and II errors in cumulative meta-analyses. Use when users need to assess if meta-analysis has sufficient information, want to avoid premature conclusions, or need to plan future trials.
startup-data-scientist
Data scientist specializing in startup analytics, user behavior tracking, and metrics analysis for Lean Startup and Customer Development methodologies. Use when analyzing user data, setting up analytics, measuring validation metrics, cohort analysis, or when user asks about tracking, metrics, data analysis, or measuring startup hypotheses.
marimo-editor
This skill should be used when working with marimo reactive notebooks for data science and analytics.Triggers include:- Creating new marimo notebooks- Converting Jupyter notebooks to marimo- Editing existing marimo notebooks- Implementing reactive patterns and UI components- Building interactive data visualizations with marimo
random-selection
Randomly select items from lists using various algorithms for fair and unbiased selection
ab-testing-statistician
Expert in statistical analysis for blind A/B and ABX audio testing. Validates randomization, calculates statistical significance, and ensures proper experimental design. Use when implementing A/B test features or analyzing test results.
spata2-docs-local
SPATA2 空间转录组学分析工具包 - 100%覆盖414个核心文件（388个API参考+25个教程+1个主页）
analysis-report
Generates comprehensive, structured research reports.
experiment-analysis
Analyze GRPO training runs for learning dynamics and pipeline performance. Use when diagnosing training issues, reviewing Elo progression, checking throughput, or updating experiment results.
sc-best-practices-auto
单细胞分析最佳实践集合——目录索引自动发现，完整抓取HTML/MD与代码块
analizador-traccion
Analiza métricas post-lanzamiento para determinar si un producto tiene tracción real o si debes pivotar. Interpreta señales de usuarios, retención, engagement y monetización. Úsalo después de lanzar para tomar decisiones basadas en datos sobre continuar, pivotar o cerrar.
mechinterp-investigator
Orchestrate a systematic research program to investigate and meaningfully label SAE features
moai-domain-data-science
Data analysis, visualization, statistical modeling, and reproducible research workflows.
experiment-analyzer
Analyze completed growth experiment results, validate hypotheses, generate insights, and suggest follow-up experiments. Use when experiments are completed, when the user asks about results or learnings, or when discussing what to do next based on experiment outcomes.
kaggle-workflow
Guide through complete Kaggle competition workflow from TODO updates to submission. Use PROACTIVELY when user starts new experiments, prepares submissions, or asks about competition workflow. Keywords: Kaggle, 提出, submission, workflow, ワークフロー, コンペ
scanpy-complete
Scanpy 单细胞分析工具包 - 100%覆盖文档（API+教程+预处理+分析+可视化）