🍎SciDER: Scientific Data-centric End-to-end Researcher🍹
Skill Claude CodeCodex
Publication-quality figure guidelines for scientific papers — DPI, font sizes, colorblind-friendly palettes, plot type selection, multi-panel layout, uncertainty representation, and statistical annotation. Use when creating figures for papers or reports.
Skill Claude CodeCodex
Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib.
Skill Claude CodeCodex needs its repo
Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimentallog.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges…
Skill Claude CodeCodex
Social science and economics methods — survey analysis (Cronbach's alpha, factor analysis), econometrics (OLS diagnostics, robust SEs), panel data, behavioral experiments, administrative data linkage, and program evaluation (ITT vs LATE). Use when analyzing social, behavioral, or economic data.
Skill Claude CodeCodex
Guided statistical analysis with test selection, assumption checking, power analysis, and APA-formatted reporting. Use when choosing appropriate tests or formatting results for academic reporting.
Skill Claude CodeCodex
Advanced statistical methods — Bayesian inference with PyMC/MCMC, mixed-effects models, resampling (bootstrap, permutation), spatial statistics, and missing data handling. Use when standard frequentist tests are insufficient or you need full uncertainty quantification.
Skill Claude CodeCodex
Time series data analysis — stationarity testing, decomposition, autocorrelation, forecasting method selection, temporal cross-validation, and evaluation metrics (MAPE, RMSE, MASE). Use when working with sequential temporal data.
Skill Claude CodeCodex
UV package manager for fast Python dependency management and virtual environments. Use when installing packages, managing dependencies, or setting up virtual environments.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: