Research & Learning skills

Work with crystal structures and materials calculations in Python. Convert structure files, examine symmetry and stability, analyze electronic properties, prepare calculation inputs, and retrieve computed materials data from Materials Project using pymatgen and its supporting tools.

• Convert crystal structure files between CIF and POSCAR
• Analyze crystal symmetry and neighboring atoms
• Create phase diagrams and assess material stability

Choose a mathematical approach for a problem you do not yet know how to model. Guided questions clarify change, uncertainty, optimization goals, and required precision, leading to a recommended framework, starting equations, tools, and related skills.

• Choosing a mathematical approach for a real-world problem
• Deciding how to model discrete or continuous change
• Selecting methods for uncertainty or optimization

Analyze Neuropixels neural recordings from raw data through quality review. Supports preprocessing, motion correction, spike sorting to separate signals by neuron, quality metrics, visual inspection, reports, and exports for further review or data sharing.

• Preprocess recordings and correct probe drift
• Separate neural signals with Kilosort4
• Select units using Allen or IBL quality criteria

Develop testable scientific hypotheses from observations, preliminary data, and published evidence. The skill compares competing explanations, defines measurable predictions, proposes experiments, and organizes evidence and decision criteria into a structured research report.

• Developing hypotheses from preliminary data
• Comparing competing explanations for a phenomenon
• Designing experiments to distinguish hypotheses

Organize manuscript text, figures, and references with version control and repeatable builds. Track how each figure was produced, separate source files from generated outputs, and use automated checks to prepare submission artifacts.

• Organizing files for collaborative manuscript writing
• Tracking changes across submissions and revisions
• Reproducing figures from code, data, and fixed parameters

Edit and compare phylogenetic trees, diagrams showing evolutionary relationships. Use ETE to identify gene duplication and speciation events, add NCBI taxonomy information, and export annotated tree figures as PDF, SVG, or PNG files.

• Pruning and rerooting existing phylogenetic trees
• Investigating gene duplication and speciation events
• Adding scientific names and taxonomy to trees

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.

• Prepare a literature review for a paper or thesis
• Compare research findings on a specific topic
• Identify gaps and future research directions

Find and retrieve economic indicators from FRED, including GDP, unemployment, inflation, and interest rates. Supports comparisons across periods, changes in reporting frequency, historical releases before revisions, regional data, and publication schedules for economic research.

• Compare trends in GDP, prices, and interest rates
• Check economic figures as originally reported
• Retrieve upcoming economic data release dates

Set up and run fluid dynamics simulations in Python to study turbulence, vortices, shallow water, and layered flows. Covers choosing equation solvers, configuring parameters, parallel execution, and plotting fields and energy spectra.

• Simulate two-dimensional turbulence and vortices
• Study oceanic or atmospheric flows with density layers
• Compare simulation results across viscosity settings

Search local VCO/vibe documentation, configuration, and skill descriptions for evidence behind rules or recommendations. Retrieve ranked excerpts with file paths and line numbers so explanations can point directly to the supporting source passages.

• Finding the source of a VCO rule
• Explaining why a skill pack was selected
• Checking configuration thresholds and their meaning

Search and summarize public FDA data through openFDA using Python. Retrieve adverse event reports, recalls, drug labels, device approvals, and substance identifiers to support safety research, regulatory analysis, and comparisons across products or time periods.

• Summarizing drug adverse event reports
• Researching medical device approvals and recalls
• Tracking food recalls involving allergens

Search the European Nucleotide Archive for DNA and RNA sequences, raw sequencing reads, and assembled genomes. Retrieve records by accession, a unique record identifier, or filter by research metadata, then download data for analysis workflows.

• Retrieve sequence data by accession
• List samples belonging to a study
• Find genome assemblies for an organism

Look up biological evidence about genes, variants, diseases, pathways, and proteins across databases. Map identifiers between sources and organize findings into comparison tables that preserve source names, query terms, access dates, and access limitations.

• Map gene identifiers across databases
• Gather evidence on variant clinical significance
• Compare target–disease association evidence

Support experimental validation of designed proteins through a cloud laboratory. Prepare and optimize sequences, submit tests for binding, expression, thermal stability, or enzyme activity, track experiment progress, and retrieve results through the API.

• Submit designed proteins for binding tests
• Request expression, thermal stability, or enzyme activity tests
• Optimize sequences for solubility before experiments

Build and clean academic reference lists by retrieving publication details from paper identifiers. Generate BibTeX, a bibliography file format, verify citation information against source records, and find duplicate or incomplete entries before manuscript submission.

• Converting DOI, PMID, or arXiv IDs to BibTeX
• Checking citation details before submission
• Removing duplicate references and standardizing formatting

Search ClinicalTrials.gov for studies by condition, drug, location, recruitment status, or phase. Retrieve trial details and eligibility criteria, summarize study information, and export results as CSV for research analysis or reviewing potential trial matches.

• Finding recruiting trials for a specific condition and region
• Tracking trials for a drug or intervention
• Reviewing eligibility criteria and study locations

Guide multi-step research with source checks, comparisons across sources, and recovery from tool errors. The skill tracks retrieved evidence and unresolved gaps so reports show what supports their claims and what remains unverified.

• Check evidence across multiple sources
• Recover from failed searches or page retrievals
• Track retrieved sources and supporting claims

Look up how genetic differences affect medication response using ClinPGx. Retrieve gene–drug relationships, clinical guidelines, genetic variant functions, and drug labels to gather evidence for research and reviews of genotype-based dosing recommendations.

• Investigate gene–drug relationships
• Review guidelines for genotype-based dosing
• Compare genetic variant frequencies across populations

Learn programming through tutorials tailored to your experience, goals, and actual project code. Keep a shared learning history across projects, record questions, and use quizzes with spaced review to revisit concepts based on demonstrated understanding.

• Learning concepts through code from an existing project
• Choosing what to study next based on previous learning
• Reviewing weak concepts through quizzes

Coordinate specialized AI agents to develop research hypotheses, plan methods, run computational experiments, search literature, and draft journal-formatted LaTeX papers. Start from a dataset description or supply existing ideas, methods, and results at individual stages.

• Generate research hypotheses from dataset descriptions
• Develop methods for an existing research question
• Run computational experiments and create figures

Creates LaTeX/PDF reports for pharmaceutical and clinical research. Compares patient groups by biomarkers, measurable biological indicators, and prepares treatment recommendation documents with evidence ratings, statistical results, and decision flowcharts.

• Comparing outcomes across biomarker-defined patient groups
• Preparing treatment recommendations with evidence ratings
• Creating flowcharts for biomarker-guided treatment selection

Study the mathematics behind computer science through a structured learning path and practice problems. Covers logic, proofs, sets, functions, counting, and number theory, connecting these foundations to algorithm correctness and computational thinking.

• Learning the mathematics behind computer science
• Practicing induction and proof by contradiction
• Reviewing sets, functions, and counting

Plan experiments and quasi-experiments before analyzing data. Define treatment and comparison groups, choose outcomes, assess design assumptions, and specify follow-up validation when results are weak or contradictory, including rules for continuing, revising, or stopping.

• Choose a study design before collecting or analyzing data
• Define treatment groups, comparison groups, and outcomes
• Review assumptions behind a proposed research design

Search ChEMBL for compounds by name, chemical structure, or properties. Retrieve biological activity measurements, target information, and drug mechanisms to investigate inhibitors and compare how structural differences relate to measured activity.

• Finding inhibitors for a specific protein target
• Searching for compounds with similar structures
• Comparing chemical structures and biological activity