Beita6969@ScienceClaw

Natural language processing with spaCy. Use when: (1) named entity recognition, (2) POS tagging and dependency parsing, (3) text tokenization and linguistic analysis, (4) rule-based pattern matching, (5) custom NER pipelines. NOT for: LLM inference or text generation (use transformers), sentiment analysis at scale (use dedicated models), or machine translation.

Medical question answering using structured biomedical knowledge bases and clinical datasets

Symbolic mathematics via SymPy. Use when: user asks for algebraic manipulation, calculus, equation solving, or mathematical proofs. NOT for: numerical computation (use scipy) or statistical analysis.

US Census Bureau data via API. Use when: user asks about US demographics, population, housing, or economic data by geography. NOT for: non-US data or real-time statistics.

Query the ChEMBL REST API for drug-target interactions, bioactivity data, ADMET properties, and approved drug information. Use when the user needs drug mechanism of action, binding affinity data, target information, or pharmacokinetic properties. NOT for basic compound lookup (use pubchem-compound), NOT for gene-disease associations (use open-targets), NOT for protein 3D structures (use pdb-structure).

Computer science bibliography via DBLP API. Use when: user asks about CS publications, author publication lists, or venue (conference/journal) metadata. NOT for: non-CS publications or citation counts.

Machine learning pipeline for scientific research including data preprocessing, feature engineering, model selection, training, evaluation, and interpretation. Covers supervised/unsupervised learning, deep learning, cross-validation, hyperparameter tuning, and model explainability. Use when user asks to build a predictive model, classify data, cluster samples, do feature selection, or apply ML to research data. Triggers on "machine learning", "classification", "clustering", "random forest", "neural network", "deep learning", "predict", "feature selection", "cross-validation", "train model".

Query NCBI E-utilities for GenBank sequences, gene info, SNPs, ClinVar variants, and literature links. Use when the user needs nucleotide/protein sequences from GenBank, gene summaries, variant data, or cross-database links. NOT for protein annotations (use UniProt), 3D structures (use PDB), or pathway mapping (use KEGG).

Conducts structured peer review of scientific manuscripts including methodological evaluation, statistical assessment, clarity analysis, and constructive feedback generation following journal-specific guidelines; trigger when users ask for manuscript critique, reviewer reports, or feedback on research papers.

Search arXiv for preprints in physics, math, CS, quantitative biology, quantitative finance, statistics, electrical engineering, economics. Use when: (1) finding preprints by topic, (2) searching by author, (3) browsing arXiv categories, (4) getting paper metadata/abstracts. NOT for: published journal articles (use crossref-search), biomedical (use pubmed-search).

Scientific programming best practices including reproducible research, computational notebooks, version control for research, data management, HPC/parallel computing, and research software engineering. Use when user needs help with research code organization, reproducibility, scientific Python/R workflows, or computational infrastructure. Triggers on "reproducible research", "research code", "scientific computing", "HPC", "parallel computing", "Jupyter", "notebook", "data management plan", "research software", "code review for science".

Performs epidemiological analyses including disease modeling (SIR/SEIR), outbreak investigation, risk factor identification, incidence/prevalence estimation, and causal inference from observational data; trigger when users discuss disease spread, public health data, or population-level health patterns.

Analyzes food science topics including nutritional composition, food chemistry, food safety hazard analysis, sensory evaluation design, and food processing optimization; trigger when users discuss nutrients, food additives, HACCP, shelf life, or food product development.

Query the KEGG REST API for metabolic pathways, genes, compounds, drugs, and diseases. Use when the user needs pathway mapping, gene-to-pathway links, compound info, or cross-reference ID conversion. NOT for protein sequences (use UniProt), 3D structures (use PDB), or variant/SNP data (use NCBI).

Lean 4 theorem prover for formal verification. Use when: formal theorem proving, mathematical verification, proof search, type theory exploration. NOT for: numerical computation (use scipy), symbolic math (use sympy), statistical analysis (use statsmodels).

Search US and EU case law, court opinions, dockets, and regulations via CourtListener, Harvard Case Law, and EUR-Lex. Use when: (1) finding US court opinions by keyword or citation, (2) searching federal and state dockets, (3) querying EU legislation and case law, (4) looking up cases by date range or jurisdiction. NOT for: current legislation text (use congress.gov), legal advice (never provide), patent search (use USPTO APIs).

Supports neuroscience research including brain imaging analysis (fMRI, EEG), neural circuit modeling, cognitive experiment design, and neurological disorder investigation; trigger when users discuss brain regions, neural signals, cognitive tasks, or neuroimaging data.

Natural language processing for research including text mining, sentiment analysis, topic modeling, named entity recognition, text classification, and corpus analysis. Use when user needs to analyze text data, extract information from documents, do sentiment analysis, topic modeling, or text classification for research purposes. Triggers on "text mining", "sentiment analysis", "topic modeling", "NER", "named entity", "text classification", "word embeddings", "LDA", "corpus analysis", "word frequency", "TF-IDF".

Query the Open Targets Platform GraphQL API for gene-drug-disease associations, evidence scores, and therapeutic target validation. Use when the user needs disease associations for a gene, drug evidence for a target, or target prioritization for a disease. NOT for compound property lookup (use pubchem-compound), NOT for bioactivity measurements (use chembl-drug), NOT for protein 3D structures (use pdb-structure).

Bioinformatics operations via Biopython. Use when: user asks about DNA/protein sequences, BLAST, or PDB structures. NOT for: clinical genomics or variant calling pipelines.

Performs biostatistical analyses specialized for clinical and biomedical research including survival analysis, Kaplan-Meier estimation, Cox proportional hazards regression, longitudinal data modeling, and diagnostic test evaluation; trigger when users discuss clinical outcomes, survival curves, or biomedical study statistics.

Scientific data analysis including data cleaning, exploratory data analysis (EDA), statistical testing, regression, and reporting. Uses Python with pandas, scipy, statsmodels, scikit-learn. Use when user asks to analyze data, clean a dataset, run statistics, do EDA, fit a model, or process CSV/Excel files. Triggers on "analyze this data", "clean my dataset", "run regression", "EDA", "descriptive statistics", "data processing", "correlation analysis".

Assists with research grant proposal writing including specific aims, significance framing, innovation articulation, approach design, and budget justification for NIH, NSF, ERC, and other funding agencies; trigger when users discuss grant proposals, funding applications, or research funding strategy.

Write and format LaTeX documents for academic journals. Use when: user asks to write LaTeX code, format papers for specific journals (Nature/Science/IEEE/ACM), create equations, tables, or BibTeX entries. NOT for: non-LaTeX writing (use paper-writing), data analysis, or literature search.

Perform quantitative meta-analysis with effect size calculation, forest plots, funnel plots, and heterogeneity assessment. Use when: user asks to combine results from multiple studies, calculate pooled effect sizes, assess publication bias, or create forest/funnel plots. NOT for: systematic review protocol (use systematic-review) or single-study statistics (use statsmodels-stats).

Write scientific papers following IMRaD structure with proper citations. Use when: user asks to draft or improve a scientific paper, write specific sections, or format citations. NOT for: non-academic writing or presentation slides.

Query the RCSB PDB API for protein 3D structures, experimental metadata, and structure files. Use when the user needs crystal or cryo-EM structure data, PDB entries, resolution info, or structure file downloads. NOT for protein sequences/annotations (use UniProt), gene data (use NCBI), or pathway info (use KEGG).

Search PubMed/MEDLINE for biomedical literature via NCBI E-utilities API. Use when: (1) searching medical/biomedical papers, (2) finding clinical studies, (3) querying with MeSH terms, (4) retrieving abstracts by PMID. NOT for: non-biomedical papers (use arxiv-search or semantic-scholar), full-text access (PubMed provides abstracts), or social science literature.

Create publication-quality scientific figures and plots using Python (matplotlib, seaborn, plotly). Supports bar charts, scatter plots, heatmaps, box plots, violin plots, survival curves, network graphs, and more. Use when user asks to plot data, create figures, make charts, visualize results, or generate publication-ready graphics. Triggers on "plot", "chart", "figure", "graph", "visualize", "heatmap", "scatter plot", "bar chart", "histogram".

Performs bioinformatics analyses including pathway enrichment, gene ontology analysis, protein-protein interaction networks, multi-omics integration, and biological sequence database querying; trigger when users discuss gene sets, biological pathways, functional annotation, or omics data integration.

Search bioRxiv biology preprints with natural language queries. Semantic search powered by Valyu.

Designs and analyzes clinical trials including sample size calculation, randomization schemes, endpoint selection, CONSORT reporting, and interim analysis planning; trigger when users ask about RCTs, Phase I-IV trials, or clinical study design.

Supports drug discovery workflows including target identification, virtual screening, ADMET prediction, lead optimization, pharmacokinetics modeling, and drug repurposing analyses; trigger when users discuss drug targets, compound libraries, medicinal chemistry, or pharmaceutical development.

Analyzes energy systems including renewable energy resource assessment, power grid modeling, battery storage optimization, energy efficiency evaluation, and techno-economic analysis of energy technologies; trigger when users discuss solar, wind, grid integration, energy storage, or power system design.

Structured hypothesis generation workflow. Use when: user needs to formulate testable scientific hypotheses from observations, gaps, or preliminary data. NOT for: testing hypotheses or running experiments.

Analyze legal contracts, extract clauses, and perform legal research with structured frameworks

Scientific visualization via Matplotlib. Use when: user asks for plots, charts, or data visualization. NOT for: interactive dashboards or web-based charts.

Read, summarize, and critically analyze scientific papers. Extract key findings, methodology, limitations, and contributions. Use when user shares a paper (PDF/URL/DOI), asks to summarize a paper, critique methodology, extract data from a paper, compare papers, or do a critical review. Triggers on "summarize this paper", "analyze this study", "what does this paper say", "critique this methodology", "extract findings from".

Physics problem solving including classical mechanics, electromagnetism, thermodynamics, quantum mechanics, optics, and computational physics. Use when user asks to solve physics problems, simulate physical systems, derive equations, or do unit conversions. Triggers on "physics problem", "Newton's law", "electromagnetic", "quantum", "thermodynamics", "optics", "wave equation", "Schrödinger", "relativity", "unit conversion", "circuit analysis".

Extract structured information from scientific texts: entities, relations, data tables, methods, results. Use when: (1) parsing papers for key data, (2) extracting experimental parameters, (3) building knowledge graphs from literature, (4) NER on scientific documents, (5) extracting methods/results sections. NOT for: summarization (use scienceclaw-summarization), full text retrieval (use scienceclaw-retrieval).

Answer scientific questions across all disciplines with evidence-based responses and citations. Use when: (1) user asks factual science questions, (2) needs explanation of concepts/theories/methods, (3) multi-step scientific reasoning needed. Covers natural sciences (physics, chemistry, biology, medicine, materials, astronomy, earth science, math, CS) and social sciences (economics, sociology, psychology, political science, linguistics, history, law, philosophy, education). NOT for: opinion-based questions, non-scientific queries, or when code execution is needed (use code-execution skill).

Scientific computing and statistical analysis with SciPy, NumPy, and pandas. Use when: (1) statistical hypothesis testing, (2) optimization problems, (3) signal processing, (4) numerical integration, (5) data manipulation and analysis. NOT for: symbolic math (use sympy-math), machine learning (use sklearn directly), or visualization (use matplotlib-viz).

Computational chemistry tools including molecular structure, chemical reactions, thermodynamics, spectroscopy analysis, and cheminformatics. Use when user works with chemical formulas, molecular structures, reaction balancing, thermodynamic calculations, or chemical databases (PubChem, ChemSpider). Triggers on "chemical structure", "molecular weight", "balance equation", "reaction", "thermodynamics", "spectroscopy", "SMILES", "PubChem", "chemical formula", "stoichiometry".

Academic metadata search via CrossRef API. Use when: user needs DOI resolution, citation counts, journal metadata, or publisher info. NOT for: full-text access or downloading papers.

Performs genomics analyses including gene expression profiling, BLAST sequence alignment, GWAS interpretation, variant calling, and genome assembly tasks; trigger when the user mentions DNA/RNA sequences, SNPs, gene panels, or comparative genomics.

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

Social network and graph analysis via NetworkX. Use when: graph analysis, community detection, centrality measures, network visualization, knowledge graphs, bipartite networks, graph I/O. NOT for: large-scale graph processing (>1M nodes), GPU graph analytics (use cuGraph).

Open academic metadata via OpenAlex API. Use when: user needs author profiles, institution data, concept mapping, or open citation data. NOT for: full-text search or downloading papers.

Conducts patent landscape analysis including prior art searches, patent claim interpretation, freedom-to-operate assessment, and intellectual property strategy for scientific inventions; trigger when users discuss patents, prior art, IP protection, or technology licensing.

Molecular chemistry operations via RDKit. Use when: user asks about molecular structures, SMILES, chemical properties, or fingerprints. NOT for: reaction databases or wet lab protocols.

Promotes research reproducibility through guidance on pre-registration, open data/code sharing, replication study design, computational reproducibility, and open science best practices; trigger when users discuss replication, open science, pre-registration, data sharing, or research transparency.

Guides research ethics compliance including IRB protocol preparation, informed consent document drafting, research integrity standards, data management plans, and ethical considerations for human/animal subjects; trigger when users discuss IRB, ethical approval, consent forms, or responsible conduct of research.

Machine learning with scikit-learn. Use when: classification, regression, clustering, dimensionality reduction, model evaluation, feature engineering. NOT for: deep learning (use transformers/pytorch), time series forecasting (use statsmodels), big data (use spark).

COPYRIGHT NOTICE

Track and improve skill effectiveness over time using VOYAGER-style skill library patterns. Use when: analyzing which tools/strategies worked best, proposing skill improvements, or storing reusable research patterns. NOT for: active research tasks or immediate problem-solving.

Search social science research papers across SSRN, RePEc/IDEAS, CrossRef, and Semantic Scholar. Use when: (1) finding working papers in economics, finance, law, or political science, (2) searching RePEc for economics papers, (3) querying CrossRef for social science journal articles, (4) retrieving citation metadata for social science research. NOT for: natural sciences (use arxiv-search or pubmed-search), computer science preprints (use arxiv-search), general academic search (use semantic-scholar).

Query the UniProt REST API for protein sequences, function annotations, structure info, and cross-references. Use when the user needs protein data, gene-to-protein mapping, functional annotation, or FASTA sequences. NOT for nucleotide sequences (use NCBI), 3D structure files (use PDB), or pathway data (use KEGG).

World Bank Open Data API for development indicators. Use when: user asks about GDP, population, poverty, health, or education statistics by country. NOT for: real-time financial data or stock prices.

Mathematical computation including symbolic math, numerical methods, linear algebra, calculus, differential equations, optimization, and mathematical modeling. Uses Python with SymPy, NumPy, SciPy. Use when user asks to solve equations, compute integrals/derivatives, do matrix operations, solve ODEs/PDEs, optimize functions, or build mathematical models. Triggers on "solve equation", "integral", "derivative", "matrix", "eigenvalue", "differential equation", "optimization", "linear algebra", "symbolic math", "proof".

NLP and corpus analysis via NLTK. Use when: user asks about tokenization, POS tagging, parsing, sentiment, or corpus statistics. NOT for: deep learning NLP or transformer models.