179 skills · sorted by relevance
Group Excel figures by department or product line, assign performance tiers, and calculate projections using growth rates set for each tier. Compare current and projected values in charts and summarize overall growth for target setting.
Assess numeric Excel columns using IQR, a measure of the middle half of values, to flag outliers. Summarize counts and limits, create box plots, and examine distribution shape to inform data cleaning.
Analyze numerical data in Excel with box plots and an outlier summary. Extract error values from text containing the ± symbol, chart their distribution, and export statistical results as a CSV report.
Analyze one Excel worksheet by cleaning column names, extracting numbers, and handling gaps from merged cells. Create category counts, percentages, cross-tabulations comparing groups, high-resolution charts, and CSV exports, with Parquet storage for the data.
Clean Excel data and group records with similar numerical features. Produce a combined view of indicator trends, value distributions, category shares, and grouped data, then export the charts as an image and cleaned records as Excel.
Extract numbers from text values containing a specified unit, remove unusable rows, and visualize the distribution. Create a histogram with mean and median markers, plus a dashboard showing frequencies, proportions, and cumulative percentages.
Analyze trends and group performance in Excel data, clean percentage values, and calculate projections using growth rates assigned by performance tier. Produce comparison charts and a summary of current totals, projected totals, and growth.
Design protein sequences while accounting for bound small molecules, nucleic acids, or metals. Use LigandMPNN to redesign binding pockets or metal-coordinating sites, and export sequence files alongside PDB structures with the designed sequences applied.
Design amino acid sequences from a protein backbone stored in a PDB file using ProteinMPNN. Generate multiple candidates, redesign selected chains while preserving specified residues, and vary sampling settings to prepare sequences for downstream structure prediction.
Design amino acid sequences from a protein backbone using SolubleMPNN, a model trained on soluble protein structures. Generate candidates with a solubility bias for redesigning aggregation-prone proteins or preparing an E. coli expression screen.
Simulate quantum systems in Python with QuTiP, including open systems that interact with their surroundings. Calculate time evolution, energy loss, and entanglement, then visualize states and results for physics research or educational experiments.
Explore design options in Python when goals such as cost and performance compete. This skill guides optimization, constraint handling, and visualization of trade-offs, then helps compare candidate solutions using stated preferences.
Analyze strategic interactions in markets, including firm entry, pricing, auctions, and bargaining. Guides equilibrium selection and computation, explains how to handle multiple possible outcomes, and helps assess whether data can identify the model's parameters.
Prepare survey and administrative datasets for analysis with Python, R, or Stata. Generate cleaning code to handle missing values, duplicates, outliers, and derived variables, with documented transformations and integrity checks that support reproducible research.
Clean survey datasets using their codebooks, which explain variables and response codes. Check missing values and outliers, harmonize variables across years, and prepare combined data with a cleaning report, variable definitions, and recorded transformation history.
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 Python code for economic models and policy evaluation, with guidance on choosing libraries, estimating effects, plotting results, and checking robustness. Covers macroeconomic simulation and causal inference, the analysis of cause and effect.
Build a Python workflow for empirical research, from data cleaning and statistical checks to estimation, robustness checks, and paper-ready tables and figures. Economics is the default, with additional modes for epidemiology, public health, and machine learning for causal inference.
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.
Build 2D game maps and backgrounds with generated artwork and explicit layout data. Check collision and route reachability, explore a playable HTML preview, and export scenes to Tiled, Godot 4 or LDtk.
Turn an approved character still into animated game assets, with a separate video for each action. Process generated or supplied clips into transparent, aligned frames, adjust loops and timing, and export images, video, and playback metadata.
Generate 2D game characters, props, icons and effects, or prepare existing artwork for use in a game. The skill removes backgrounds, separates frames, adjusts size and palettes, checks results, and exports assets for game engines.
Create 2D game art from code, including sprites, icons, tiles and backgrounds. The skill renders written specifications, checks palettes and tile seams, and packages images with review sheets without using an image model.