Auto-sci-research: End-to-end research writing, literature reviews, bibliometrics, GIS exposure assessment, ML/XAI, and SCI writing Skills for geography and sports science with Codex.
This repository also configures its own agents. See what agent-auto-sci-skills tells them →
Lzy599775/agent-auto-sci-skills
Skill Codex
A research workflow for building and checking machine-learning and artificial-intelligence models, including models that work with maps, time-based data, text, or images.
Lzy599775/agent-auto-sci-skills
Skill Codex
A guide for turning research projects into lasting local workflows with source tracking, structured notes, experiments, paper planning, reviews, and checkpoints. It also describes a shared memory system for research materials.
Lzy599775/agent-auto-sci-skills
Skill Codex
A workflow for exploring data, choosing statistical tests, and creating clear charts, tables, maps, and dashboards for research.
Lzy599775/agent-auto-sci-skills
Skill Codex
A guide for working with geographic and satellite data, including maps, location-based measurements, and spatial analysis. It covers common tools such as GeoPandas, which handles geographic data in Python.
Lzy599775/agent-auto-sci-skills
Skill Codex
A research-planning and critical-thinking workflow for turning broad ideas into testable questions and defensible studies.
Lzy599775/agent-auto-sci-skills
Skill Codex
A skill for planning and writing scientific papers, reviews, posters, presentations, cover letters, and replies to peer reviewers.
Lzy599775/agent-auto-sci-skills
Skill Codex
A coordinating skill for managing a complete research workflow, from choosing a topic and finding literature to analysis, figures, manuscript writing, review, submission, and later revisions.
Lzy599775/agent-auto-sci-skills
Skill Codex
A writing guide for English papers in geography, remote sensing, urban exposure, spatial fairness, and related fields. Remote sensing uses measurements from satellites or other sensors to study places and environmental conditions.
Lzy599775/agent-auto-sci-skills
Skill Codex
A selected toolkit for exploring data, running statistical analysis, and creating scientific charts. It covers tools such as Matplotlib, Seaborn, NetworkX, Polars, and Dask, with guidance for publication-ready figures.
Lzy599775/agent-auto-sci-skills
Skill Claude Code
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed…
Lzy599775/agent-auto-sci-skills
Skill Claude Code
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
Lzy599775/agent-auto-sci-skills
Skill Claude Code
Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for…
Lzy599775/agent-auto-sci-skills
Skill Claude CodeCodex
Create, analyze, and visualize complex networks and graphs in Python with NetworkX. Use when working with network/graph data structures, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks (random, scale-free, small-world), reading/writing graph…
Lzy599775/agent-auto-sci-skills
Skill Claude Code
High-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.
Lzy599775/agent-auto-sci-skills
Skill Claude Code
Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use for figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning.
Lzy599775/agent-auto-sci-skills
Skill Claude Code
Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use…
Lzy599775/agent-auto-sci-skills
Skill Claude CodeCodex
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…
Lzy599775/agent-auto-sci-skills
Skill Codex
A toolkit for geospatial science and remote sensing, the analysis of information collected about Earth from satellites or other sensors. It covers geographic data, maps, spatial analysis, and related research workflows.
Lzy599775/agent-auto-sci-skills
Skill Claude CodeCodex
Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing…
Lzy599775/agent-auto-sci-skills
Skill Claude Code
Guidance and local audit tools for Python workflows that directly use GeoPandas GeoSeries, GeoDataFrame, spatial operations, or vector-data I/O.
Lzy599775/agent-auto-sci-skills
Skill Codex
A selected toolkit of machine-learning and artificial-intelligence guidance for libraries and methods such as scikit-learn, PyTorch Lightning, Transformers, SHAP, time-series forecasting, graph learning, and UMAP.
Lzy599775/agent-auto-sci-skills
Skill Claude Code
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…
Lzy599775/agent-auto-sci-skills
Skill Claude Code
Deep learning framework (PyTorch Lightning / lightning package). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
Lzy599775/agent-auto-sci-skills
Skill Claude Code
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for…
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: