dotfiles

Use whenever the user writes, drafts, revises, edits, polishes, or translates scientific or academic prose in ENGLISH - Q1 research articles, theses, dissertations, abstracts, introductions, methods, results, discussions, conclusions, acknowledgments, literature reviews, grant proposals, conference papers, or any IMRaD section. Provides 5000+ pre-cooked, idiomatic, native-academic phrases plus paragraph- and sentence-level guidance for every standard section of a scientific document, avoiding robotic / LLM-style prose. Triggers: "write the introduction", "draft the abstract", "help me with the discussion", "polish this scientific paragraph", "translate this paper to English", "this sounds like AI, rewrite it", "write the methods section", "I need phrases for...", "academic English", "make this sound more academic", "make this Q1-ready".

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

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 ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Conduct comprehensive, systematic literature reviews across multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). Use for systematic reviews, meta-analyses, scoping reviews, research synthesis, and broad literature searches, including topic overviews, surveys, and state-of-the-art summaries that gather and organize the major work on a subject by theme or method. Produces professionally formatted markdown and PDF documents with verified citations in multiple styles (APA, Nature, Vancouver, etc.).

Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

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 publication-ready multi-panel figures with journal styling, use scientific-visualization.

Enforces rigorous scientific methodology for machine learning experiments intended to support publication-grade claims (Q1 journals, conference papers, regulated decisions). Use this skill when designing an ML pipeline, splitting datasets, evaluating performance, selecting features, tuning hyperparameters, comparing models, quantifying uncertainty, validating externally, or preparing results for a paper. Consult it for any task where experimental validity, reproducibility, or publication standards (TRIPOD+AI, CLAIM, STARD-AI, CONSORT-AI) are in scope. Routine "train a model" or "compute accuracy" requests do NOT automatically trigger this skill unless results will be reported, compared, or acted on.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics simulation, differentiable rendering, mesh ray casting, particle systems (DEM/SPH/fluids), vector/similarity search, GPUDirect Storage file IO, interactive dashboards, geospatial analysis, medical imaging, and sparse eigensolvers. Also use when you see CPU-bound Python code (loops, large arrays, ML pipelines, graph analytics, image processing) that would benefit from GPU acceleration, even if not explicitly requested.

High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.

Fast DataFrame library built on Apache Arrow with lazy evaluation, a query optimizer, and multithreaded parallel execution. Use as a faster pandas replacement for ETL and analytics on datasets from megabytes to roughly 100GB, and use its streaming, out-of-core engine to process larger-than-memory data that does not fit in RAM, with predicate and projection pushdown when scanning Parquet or CSV, plus joins, group-bys, window and rolling operations. For distributed multi-machine clusters consider dask or Spark.

Push Python stdlib idioms over hand-rolled code. Use whenever the user writes, refactors, optimizes, or reviews Python — including one-liners and code-review feedback. Replaces common reinventions: manual dict counters with `Counter`, `dict.setdefault` loops with `defaultdict`, `isinstance` chains with `singledispatch` or `match`/`case`, hand-rolled memoization with `functools.cache`, `os.path.join` with `pathlib.Path`, `sorted(..., reverse=True)[:k]` with `heapq.nlargest`, manual class boilerplate with `dataclass(slots=True, frozen=True)`, `zip(lst, lst[1:])` with `itertools.pairwise`. Covers Python 3.9-3.14 with per-version reference files. Trigger phrases: "write a Python function", "refactor this Python", "Pythonic way to X", "optimize Python code", "make this more Pythonic", "implement X in Python", or any task whose answer involves Python source.

Usar siempre que el usuario escriba, redacte, revise o traduzca texto científico/académico en ESPAÑOL: artículos, papers, tesis, abstracts, introducciones, metodologías, resultados, discusión, conclusiones, agradecimientos, revisiones de literatura, defensas, propuestas de investigación o cualquier sección IMRyD. Aporta más de 5000 frases "precocinadas" idiomáticas y formales para cada sección estándar de un documento científico, evitando la prosa robótica/IA. Disparadores: "escribe la introducción", "redacta el abstract", "ayúdame con la discusión", "mejora este párrafo científico", "tradúceme este paper", "redacta la metodología", "necesito frases para...", "esto suena a IA, mejóralo".

Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.

Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.

Apply senior-level engineering judgment on non-trivial code work: designing systems, writing new modules, refactoring, implementing algorithms, or making structural decisions. Triggers: "design X", "refactor this", "implement an algorithm/feature/service", "optimize this", "review this code", "what's the best way to structure X", or any task that involves architecture, complexity reasoning, or multi-file changes. SKIP for trivial edits (rename, typo, single-line fix), config tweaks, documentation edits, or tasks already covered by the base "match request scope" guidance. Languages: Python, TypeScript, C, C++, SQL.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.