Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Forecast sales, sensor readings, or other time series without training a custom model. Using Google's TimesFM, this skill produces forecasts and uncertainty ranges from CSV files or arrays, supports batch processing, and checks local computing resources before use.
Audit Kiln’s model list against provider APIs and catalogs to identify removed models and upcoming retirements. Get findings organized by provider, then mark affected entries as deprecated after reviewing and approving the proposed changes.
Check whether Kiln’s base models still support fine-tuning, the process of adapting a model with additional training. Compare configured identifiers and Fireworks’ allowlist with provider information, then report unsupported entries and recommend specific updates.
Maintain Kiln’s list of large language models by discovering new releases, testing provider access, and marking unavailable entries as deprecated. Prepare pull requests, report unresolved issues, and check whether the updated list needs publication.
Use a transaction hash, its identifying code, to retrieve records from TRES Finance. The skill draws asset movements and network fees, then explains the action, participants, amounts, and net result in plain English.
Analyze ML and AI experiment data with statistical tests, effect sizes, confidence intervals, and figures. The skill validates comparisons and produces an analysis report, statistical appendix, and figure catalog while identifying missing evidence and limitations.
Retrieve economic data from official statistics and established research sources after confirming price basis, seasonal adjustment, frequency, and currency. Return structured tables with source details and access dates, plus loading guidance for the user’s statistical software.
Write and review R analysis scripts for a sewage research project using its established conventions. Estimate requested regression models, add specifications, and save LaTeX tables, figures, and model objects for use in the research paper.
Choose quantitative or qualitative methods that fit a research question and dataset. Compare alternatives, check assumptions, generate analysis code, interpret results, and examine sensitivity, meaning how conclusions change under different analytical choices.
Learn from top Kaggle solutions across text, images, time series, tabular data, and multimodal tasks that combine data types. Explore technical analyses, model settings, reusable code templates, and practical lessons to inform machine learning projects.
Prepare research papers for RAG, a method that supplies retrieved documents to AI. Download PDFs, extract and split text, and build a local searchable database, with parallel processing for document batches.
Analyze datasets in R or Python, from exploring distributions and missing values to fitting regressions. Produce tables and figures for publication, save scripts and model results, and review the analysis for common problems.
Build and estimate economic models that represent underlying choices and incentives. Get guidance on demand, dynamic choice, and auction models, select estimation methods, and diagnose numerical problems such as failed convergence or sensitivity to starting values.
Analyze U.S. electoral district plans in R with redistverse. Guides data preparation, simulations under population and geographic constraints, diagnostic checks, and comparisons of district shape, partisan fairness, and administrative splits through maps and summary tables.
Build research workflows that regenerate results from raw data with a single command. Organize project files, configure workflow tools, manage software environments and data versions, and prepare replication packages for journal submission.
Estimate policy effects by constructing a weighted comparison from untreated regions or other units. Guides donor selection, weight fitting, placebo tests, and reporting, with examples in R, Python, and Stata for studies with few treated units.
Choose and interpret models for panel data, which tracks the same firms, people, or countries over time. Use Python, R, or Stata examples to compare fixed and random effects, check assumptions, and select standard errors.
Develop Bayesian models for quantitative social science, from choosing priors to reporting posterior results. Guide MCMC, a sampling method for estimating distributions, check convergence, and assess sensitivity for hierarchical models and small datasets.
Route structural estimation tasks into a staged workflow, from data validation and identification, checking whether model parameters can be determined, through estimation, standard errors, robustness checks, and results. Each phase must meet its conditions before the next begins.
Write, debug, and understand Stata code for data cleaning, statistical analysis, causal inference, and charts. The reference covers command syntax, common pitfalls, Mata programming, and community packages for estimation and reporting.
Plan, run, and interpret linear regression with guidance on model choices, diagnostic checks, and reporting. Python, R, and Stata examples help examine coefficients, assess assumptions, and choose standard errors that account for different error patterns.
Estimate effects by comparing observations just above and below an eligibility threshold using regression discontinuity design. Covers plots, comparison range selection, sharp and fuzzy designs, validity checks, and sensitivity analysis for reporting research findings.
Choose and implement machine learning methods for estimating causal effects with many control variables or effects that differ across groups. Guidance covers DML, causal forests, and related methods, including diagnostics and limits on interpretation.
Apply machine learning methods to estimate intervention effects and explore how effects vary across groups. Provides implementation examples, diagnostic checks, and reporting guidance for Double Machine Learning, causal forests, and variable selection.