Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Plan how to introduce AI into economic research, teaching, or policy analysis. Identify suitable tasks, choose tools with privacy and licensing in mind, and design reproducible data workflows with output checks and ongoing model monitoring.
Create figures for machine learning papers from text or experiment data. Uses Gemini for architecture diagrams and matplotlib/seaborn for numerical charts, choosing suitable layouts and chart types while preparing consistent styling, export files, and reusable generation scripts.
Build reproducible empirical analyses in R, from data cleaning to statistical modeling and publication tables and figures. Covers economics, epidemiology, and machine learning approaches to causal inference, which estimates effects of interventions.
Interpret statistical models in R and Python using predictions, comparisons, and marginal effects, which describe how outcomes change with predictors. Get guidance on choosing quantities, evaluating scenarios, summarizing groups, measuring uncertainty, and testing hypotheses.
Build a reproducible Stata analysis from data cleaning through modeling, diagnostic checks, and robustness tests. Generate runnable .do files, regression tables, and figures for empirical papers, with additional workflows for epidemiology and machine learning approaches to causal inference.
Estimate how an intervention affects outcomes using Bayesian causal analysis. The workflow confirms causal assumptions with the user, selects a suitable method, checks whether findings withstand challenges, and reports effects with uncertainty and limitations.
Coordinate AI research from literature review to paper drafting. The skill alternates focused experiments with broader reviews of findings, tracks hypotheses and decisions, and uses specialist skills to carry out research tasks and prepare progress reports.
Fetch public social media data through the ScrapeCreators API, including profiles, posts, comments, transcripts, ads, and trends. Select the appropriate data endpoint and retrieve JSON, a structured data format, for research or further analysis.
Generate PNG or SVG charts from data for reports, monitoring alerts, and dashboards. Choose from line, bar, pie, candlestick, and heatmap charts, then adjust labels, colors, and annotations using Node.js without a browser or external API calls.
Run linear or logistic regression on CSV or Excel tables to examine relationships between variables. Get coefficients, measures of model fit, significance tests, and checks for overlapping predictors, with explanations in plain language.
Check CSV, Excel, TSV, and JSON tables for missing values, duplicates, unusual values, and inconsistent formats. Receive scores across 12 quality dimensions, an overall grade, and practical suggestions for fixing the detected issues.
Explore SQLite and PostgreSQL databases through read-only queries. List tables and row counts, inspect columns and constraints, preview records, and generate Mermaid ER diagrams, which describe how tables relate to one another.
Turn JSON data into browser-ready infographics with metric cards, grouped bar charts, process diagrams, or mixed dashboards. Outputs include all styling and SVG graphics in one HTML file, with preset palettes and icons and no external dependencies.
Implement agents that use recorded task outcomes to choose future approaches. ReasoningBank supports matching past patterns, comparing strategies, retaining experience in AgentDB, and tracking how strategy success and learning change over time.
Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.
Train, deploy, and run predictions with neural networks using Flow Nexus and E2B sandboxes, isolated computing environments. Use existing model templates, distribute training across multiple environments, and check training progress and model performance.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.
Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.
Tune AgentDB memory use and search speed through quantization, which stores vectors more compactly, search indexes, caching, and batch operations. Includes configuration examples and benchmarks to help balance accuracy, speed, and storage as datasets grow.
Build advanced AgentDB workflows with database synchronization, multiple databases, and search that combines meaning with attribute filters. Covers similarity measures, diverse search results, and operational patterns for distributed AI applications.
Plan and implement a unified AgentDB memory backend for agents. Migrate SQLite and Markdown data, add HNSW indexing for similarity search, and support shared memory and SONA learning patterns while preserving compatibility with existing systems.
Build AI agents that retain conversation history, user preferences, and useful interaction patterns with AgentDB. The skill covers persistent storage, meaning memories survive between sessions, plus retrieval, context management, and ReasoningBank integration.
Help text-only models work with images by converting visible text, layout, meaning, and visual clues into structured JSON. The skill also guides configuring image analysis providers and reporting unclear details from the returned evidence.