K-Dense

Use Hugging Face Transformers to load pretrained models, generate text, and classify text, images, or audio. Prepare model inputs, control generation settings, and fine-tune models on custom datasets with the Trainer API.

• Prototype text, image, or audio classification
• Configure text generation and conversational responses
• Fine-tune a model on a custom dataset

Retrieve U.S. federal financial data from the Treasury’s public API, including debt, revenue, spending, interest rates, and exchange rates. Filter dates and fields, retrieve multiple pages, and organize results into tables for analysis.

• Tracking U.S. national debt over time
• Comparing monthly federal revenue and spending
• Retrieving Treasury reporting exchange rates

Work with Waypoint models to analyze microbiome samples, the communities of microbes in a sample. Convert taxonomic abundance tables, generate numerical sample representations, configure further training for prediction tasks, and evaluate models on the Compass benchmark.

• Convert microbiome abundance tables into Waypoint inputs
• Generate sample vectors for clustering and visualization
• Configure further training with sample labels

Build and check clinical machine learning workflows with PyHealth, from loading electronic health records, signals, or images to training and evaluation. Includes patient-level data splits, prediction task checks, model checkpoints, and medical code mapping.

• Prototype mortality and readmission prediction models
• Check patient splits and data leakage
• Train and evaluate sleep staging models

Process mass spectrometry data using scripts for format conversion, signal cleanup, peak detection, and quantification across samples. Prepare protein and metabolite analyses with identification filtering, candidate annotations, data tables, and plots.

• Inspect, convert, and preprocess mass spectrometry files
• Build quantitative tables across multiple samples
• Find metabolite candidates from accurate mass

Validate particle data and run RELION refinement for single-particle cryo-electron microscopy. Check independently refined half maps, calculate diagnostic map correlations, and perform soft-mask postprocessing while preserving execution logs and restart information.

• Check particle metadata and image-stack consistency
• Run refinement on a selected particle population
• Inspect agreement between independent half maps

Build evolutionary trees from related nucleotide or protein sequences using MAFFT with IQ-TREE or FastTree. Review branch support, a measure of evidence for each grouping, and produce tree summaries and optional visualizations.

• Build gene trees from related nucleotide sequences
• Compare evolutionary relationships within protein families
• Review branch support and analysis logs

Manage Zotero reference libraries through Python: search, create, update, and delete references, organize collections and tags, upload PDF attachments, and export citation data. Guidance covers both remote libraries and access through a running local Zotero app.

• Searching references in a Zotero library
• Organizing references with collections and tags
• Uploading PDF attachments to references

Inspect and transform local DICOM medical imaging files, including metadata, image frames, and compression formats. Generate technical inventories and preview images, check installed codecs, and review pseudonymized derivatives without treating those checks as proof of de-identification.

• Create a technical inventory of local DICOM files
• Check compression support and frame memory needs
• Export a frame as a non-diagnostic preview

Design and review laboratory automation with PyLabRobot, including equipment layouts and liquid transfers. Check planned volumes and tip capacities, draft protocols, and simulate operations in software before a trained operator reviews any physical run.

• Reviewing liquid-transfer plans
• Checking labware layouts and capacities
• Simulating protocols without physical equipment

Explore public pathogen genome data to verify lineage names, summarize weekly sequence proportions, examine reporting delays, and compare mutation frequencies. Results include filters and denominators, with clear limits on what submitted sequences reveal about infections.

• Tracking weekly lineage proportions in submitted sequences
• Verifying current Pango lineage names
• Examining delays between sample collection and reporting

Prepare and review research funding proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Maps application requirements to draft sections, identifies gaps, and helps refine research aims, budgets, impact statements, and responses to reviewers.

• Map funding-call requirements to proposal sections
• Review research aims against evaluation criteria
• Align budgets and timelines with the research plan

Organize PyTorch models and data pipelines with PyTorch Lightning, automate training, save checkpoints, and track experiments. Includes templates and guidance for configuring training across multiple GPUs or TPUs.

• Restructure PyTorch training code into LightningModules
• Build reusable data preparation and loading pipelines
• Configure checkpoints, early stopping, and experiment logs

Process paired-end 16S sequencing reads in QIIME 2 to produce ASVs, distinct sequence variants, and taxonomic assignments. Check input files, primer settings, and read retention while preserving artifacts that record the processing history.

• Validate paired FASTQ files and sample metadata
• Remove primers and denoise reads with DADA2
• Assign taxonomy using a compatible classifier

Explore gene, drug, disease, and phenotype associations in a downloaded PrimeKG CSV. Retrieve direct relationships, disease summaries, and paths through one intermediate node while preserving relationship types and data provenance for reproducible research and hypothesis generation.

• Checking associations between genes, drugs, and diseases
• Summarizing genes, drugs, and phenotypes linked to a disease
• Exploring short paths between two entities

Develop and prioritize early research ideas through independent brainstorming, structured discussion, evidence checks, and critical review. Keep assumptions, uncertainty, dissent, and scoring reasons visible, then record the human decision and appropriate next steps.

• Exploring candidate directions for a new research topic
• Organizing ideas before a research team discussion
• Comparing proposals using explicit evaluation criteria

Research current web information with Parallel CLI and organize findings with supporting sources. The skill covers search, page extraction, detailed reports, adding sourced fields to existing lists, finding matching entities, and recurring monitoring of web changes.

• Research current information and locate academic sources
• Extract content from public webpages and PDFs
• Add sourced information to company or product lists

Combine laboratory animal welfare measurements into reference-relative RELSA severity scores. Analyze individual trajectories, explore forecasts for specified observation times, and derive candidate score zones, with explicit checks on normalization, reference selection, prediction intervals, and evaluation limits.

• Combine animal welfare measurements into daily scores
• Compare group severity using a shared reference
• Explore severity forecasts at specified observation times

Simulate lithium-ion battery charging, discharging, and rest with PyBaMM. Track voltage and capacity, record parameter sources, check how numerical settings affect predictions, and compare simulated curves with measured cycling data.

• Predicting voltage changes during charge, discharge, and rest
• Comparing simulation results with measured cycling data
• Checking how numerical settings affect predictions

Analyze gene-expression differences in bulk RNA-seq data using PyDESeq2. Validate count tables and experimental designs, test explicit comparisons, adjust for multiple testing, shrink effect estimates, and export statistical results with volcano and MA plots.

• Compare gene expression between treatment and control groups
• Analyze expression differences while accounting for batch effects
• Validate count tables against sample metadata

Read, analyze, modify, and visualize molecular structures with RDKit in Python. Calculate molecular properties, search for similar structures or specific structural patterns, apply reaction rules, and generate 2D or 3D coordinates with detailed control over processing.

• Calculating properties for a collection of molecules
• Searching for molecules with similar structures
• Filtering molecules by specific structural patterns

Find biological pathways and functions enriched in gene lists or ranked gene data. Choose an appropriate statistical method, align gene identifiers, define comparison backgrounds, and turn results into interpretable tables and plots with multiple-testing corrections.

• Finding enriched pathways among differentially expressed genes
• Running GSEA on a complete ranked gene list
• Calculating gene-set scores for individual samples or cells

Run molecular property predictions, explore molecular shapes, and estimate how compounds bind to proteins through a cloud Python API. Process compound batches and connect modeling steps without maintaining local high-performance computing infrastructure.

• Predicting properties across a compound library
• Exploring molecular shapes and tautomeric forms
• Estimating how compounds bind to proteins

Review papers, drafts, and research ideas with evidence-linked feedback focused on improvement. Audit low-stakes assessment rubrics, trace supporting evidence, and check rater agreement and uncertainty without ranking people or recommending consequential decisions.

• Prepare evidence-linked feedback on a paper draft
• Review strengths and limitations of a research idea
• Check assessment criteria and evidence traceability