314 skills · sorted by relevance
Use scGPT to convert single-cell gene expression data into numerical representations of cells and genes. These representations support clustering, data integration, cell-type annotation, and analyses of gene perturbations or regulatory relationships.
Search multiple academic databases, screen studies against documented criteria, and compare findings by theme. Produce literature reviews in Markdown and PDF with study quality assessments, verified citation details, and diagrams explaining the review process or findings.
Edit English and Chinese prose to reduce formulaic wording, inflated claims, vague attributions, and repetitive sentence patterns. It preserves the core meaning and intended tone while improving rhythm, directness, and the writer’s voice.
Plan literature searches for six review types, from systematic to rapid reviews. Develop database-specific search queries, selection criteria, citation tracking, and search records, while comparing approaches for coverage, reproducibility, and available time.
Learn from top Kaggle solutions across text, images, time series, tabular data, and multimodal tasks that combine data types. Explore technical analyses, model settings, reusable code templates, and practical lessons to inform machine learning projects.
Review research ethics, participant protection, and potential bias from planning through publication. The skill examines questionable research practices and study trustworthiness, then produces a structured report with evidence, risk levels, and prioritized recommendations.
Choose quantitative or qualitative methods that fit a research question and dataset. Compare alternatives, check assumptions, generate analysis code, interpret results, and examine sensitivity, meaning how conclusions change under different analytical choices.
Check an economics paper before submission with two parallel reviewers. Assess its contribution, whether the design supports causal conclusions, and unsupported claims, then receive a short report with fixes ranked by severity.
Revise a LaTeX academic manuscript from referee reports, approving changes comment by comment. The skill separates requests for additional analysis from text edits and prepares a revision plan or a revised manuscript with a detailed response letter.
Turn a research proposal into a corporate finance study using data from the United States, Europe, Japan, or multiple countries. The workflow supports journal selection, Python analysis, statistical checks, and preparation of LaTeX tables and figures.
Review difference-in-differences analyses, which compare changes across treated and comparison groups. It checks pre-policy trends, event-study charts, assumption violations, placebo tests, and robustness, then organizes findings and suggested revisions into a structured report.
Turn a research proposal on Chinese corporate finance into a structured empirical project. The workflow recommends target journals, guides Python data preparation and statistical analysis, and produces code, LaTeX tables, and figures while recording changes to the analysis plan.
Build a Python workflow for empirical research, from data cleaning and statistical checks to estimation, robustness checks, and paper-ready tables and figures. Economics is the default, with additional modes for epidemiology, public health, and machine learning for causal inference.
Search multiple academic databases, screen studies, assess their quality, and combine findings by theme. Produce a literature review in Markdown and PDF, with checked citations and a documented search and selection process.
Develop literature reviews on AI for medical imaging, including segmentation, detection, and classification. Organize research from multiple sources into a structured manuscript with method comparisons, evaluation metrics, supporting citations, and limitations.
Build a reproducible Stata analysis from data cleaning through modeling, diagnostic checks, and robustness tests. Generate runnable .do files, regression tables, and figures for empirical papers, with additional workflows for epidemiology and machine learning approaches to causal inference.
Run empirical and causal analyses in Python with StatsPAI, from stating assumptions to estimating effects and checking how results change under alternative choices. Produce diagnostic figures, regression tables, and replication bundles for economics, public health, or machine learning studies.
Build causal inference analyses to estimate intervention effects using templates drawn from Causal Inference: The Mixtape. Adapt code across Python, R, and Stata, with checks for method assumptions and guidance on language-specific packages and limitations.
Examine strategy, design, and difficult decisions through AI personas modeled on thinkers and engineers. The skill selects a panel, checks how members frame the problem, gathers independent analyses, and assigns a separate chair to synthesize a verdict.
Estimate causal effects from existing data. Use when fitting or interpreting DiD, ITS, synthetic control, regression discontinuity, or other treatment-effect analyses, including robustness checks and counterfactual plots. For choosing a study design before analysis, use designing-experiments instead.
The English summary is being prepared. Showing the original description.
Check CPU cores, GPUs, available memory, and disk space before demanding computing tasks. Save a JSON report with recommendations for parallel workers, GPU use, and processing data in chunks when memory is limited.
Use LaminDB to organize biological datasets, search their metadata, and track how analyses produce results. Standardize annotations with biological vocabularies, validate data structures, and record versions and computational history for reproducible research.
Search multiple academic databases, screen papers against defined criteria, and compare findings by theme. Produce literature reviews in Markdown and PDF, with documented search methods, study quality assessments, and verified citations in a consistent style.
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
The English summary is being prepared. Showing the original description.