awesome-rosetta-skills

Astronomical data analysis with astropy and astroquery — FITS I/O, WCS transforms, catalog cross-matching, aperture photometry, and CMB power spectra.

Seismological data analysis with ObsPy — FDSN waveform download, response removal, phase picking, moment tensor inversion, and seismicity mapping.

Download and analyze oceanographic data from Copernicus Marine Service and Argo floats using copernicusmarine, gsw, and xarray.

Use this Skill to process oral history recordings: Whisper transcription with timestamps, pyannote speaker diarization, OHMS metadata XML, and speaker anonymization.

Educational psychology experiment design and analysis covering IRT, growth modeling, A/B testing, and learning curve estimation for research.

Knowledge graph construction, SPARQL querying, and entity linking for library and research data management using RDF and Wikidata.

Bibliometric analysis using the OpenAlex API covering co-authorship networks, citation analysis, h-index, and research trend mapping.

Patent landscape analysis with IPC classification, citation networks, technology emergence detection, and inventor collaboration mapping.

Research impact measurement with altmetrics, citation normalization, field-weighted indicators, and journal ranking analysis for evaluation studies.

Mixed methods research design with qualitative-quantitative integration, triangulation, content analysis, and systematic comparison using NVivo-style coding.

Science of science analysis covering disruption index, team size effects, sleeping beauty detection, and knowledge recombination with citation data.

Scientific text mining with topic modeling, NER for scientific entities, claim extraction, and trend detection in research literature corpora.

Containerize research environments with Docker and Singularity for reproducible computation, HPC deployment, and research environment management.

Data version control with DVC covering pipeline tracking, remote storage, experiment comparison, and reproducible ML workflows for research.

Python research package development with pyproject.toml, testing with pytest, documentation with Sphinx, and publishing to PyPI for academic software.

Reproducible research reporting with Quarto covering parameterized reports, multi-format output, inline computation, and journal article templates.

R research package development with devtools, roxygen2 documentation, testthat testing, CRAN submission, and vignette creation for statistical methods.

Use this Skill to structure research grant proposals: NSF/NIH Specific Aims, budget justification, ERC narrative sections, structured abstracts, and biosketch formatting.

Use this Skill to apply machine learning in research: scikit-learn pipelines, FLAML AutoML, SHAP explainability, nested cross-validation, and model cards.

Use this Skill to preregister a study on OSF or AsPredicted, generate CONSORT/STROBE/PRISMA compliance checklists, and track deviations between the registered protocol and final analysis.

Use this Skill for research data lifecycle management: codebook generation, DVC versioning, anonymization (k-anonymity, pseudonymization), and README templates.

Use this Skill to design, validate, and deploy research surveys: Likert scale construction, attention checks, pilot testing, ICC reliability, and Qualtrics/LimeSurvey export.

Use this Skill for research version control: Git workflow for analysis code, DVC data pipelines, GitHub Actions for reproducibility CI, and .env secrets management.

Use this Skill for 3D scientific visualization with Mayavi: vector fields, isosurfaces, volume rendering, and animated 3D plots for physics data.

Use this Skill when simulating physical systems with Monte Carlo methods: statistical integration, MCMC sampling, Ising model, error estimation.

Physics-informed neural networks, neural ODEs, and data-driven force-field learning using PyTorch, DeepXDE, and torchdiffeq.

Labeled multi-dimensional array analysis with xarray: NetCDF/HDF5 I/O, lazy Dask loading, rechunking, Zarr stores, and CF conventions.

Use this Skill to query ChEMBL for bioactivity data: target lookup, IC50/Ki retrieval, activity cliffs, SAR tables, and pChEMBL-normalized values.

Analyze molecular dynamics trajectories with MDAnalysis — RMSD, RMSF, hydrogen bonds, contact maps, and protein-ligand distances.

Process and analyze NMR spectra with nmrglue — FID processing, peak picking, chemical shift referencing, and J-coupling extraction.

Use this Skill for chemical file format interconversion (SDF, SMILES, MOL2, PDB), 3D coordinate generation, conformer enumeration, and reaction SMARTS.

Use this Skill for graph construction, centrality measures (betweenness, PageRank), community detection (Louvain), and random graph models via networkx.

Use this Skill for SVD, PCA, eigendecomposition, Cholesky, iterative solvers, sparse matrix formats, and condition number analysis with numpy and scipy.

Apply persistent homology, Betti numbers, and mapper graphs to extract topological features from complex datasets.

Use this Skill to access OpenAQ air quality data (PM2.5, O3, NO2), compute spatial interpolation, health exposure indices, and city comparisons.

Use this Skill for climate trend analysis: Mann-Kendall test, Sen's slope, extreme indices (RX1day, R10mm), percentile thresholds, IPCC-style figures.

Query GBIF occurrence data, apply spatial thinning, and build species distribution models using pygbif, geopandas, and elapid.

Use this Skill for DEM-based hydrological analysis: watershed delineation, flow direction/accumulation, stream networks, and runoff estimation with pysheds.

Atmospheric analysis with MetPy and Siphon: download NWP data from THREDDS/NOMADS, plot skew-T log-P diagrams, compute CAPE/CIN parcel metrics, and build synoptic composites.

Use this Skill for seismological analysis with ObsPy: waveform download, filtering, P/S phase picking, moment magnitude, and spectral analysis.