K-Dense

Turn supplied data or optional research into infographic drafts for reports, presentations, or social posts. Choose layouts and visual styles, generate PNG images, and use automated reviews to guide revisions while retaining review logs.

• Turning report statistics into an infographic
• Creating a timeline of project milestones
• Comparing product features visually

Convert PDF, Office, and other documents into Markdown that preserves useful text structure. Use batch conversion and literature organization to prepare files for search, text analysis, or AI systems that retrieve information from documents.

• Convert PDF and Office files to Markdown
• Batch-convert a document folder
• Organize research papers with source metadata

Optimize scientific Python workloads for NVIDIA GPUs by choosing suitable libraries and reducing bottlenecks. Compare outputs with the CPU version and measure complete processing time, including data transfers, to determine whether the GPU implementation provides a useful improvement.

• Assess whether slow Python processing would benefit from a GPU
• Move NumPy or pandas workloads to suitable GPU libraries
• Validate GPU results against CPU outputs

Inspect CPU, memory, disk, and accelerator information alongside container and scheduler limits. Produce a JSON snapshot with identifying details removed and conservative worker and memory estimates for planning local workloads, without running stress tests.

• Choosing worker counts before a large local job
• Checking CPU and memory limits inside a container
• Comparing resource snapshots before and after changes

Search biomedical papers, regulatory documents, clinical trials, and protein records through GXL Paperclip. Extract comparable information across documents, inspect figures, and organize findings with citations linked to the source lines that support them.

• Finding biomedical papers on a topic
• Comparing methods and results across papers
• Reviewing regulatory documents and clinical trials

Find and download public cancer imaging data from NCI Imaging Data Commons. Select CT, MR, PET, or pathology datasets using metadata, view images in a browser, and check licenses and citations before using the data.

• Find cancer images by disease, modality, or anatomical site
• Download selected DICOM image series
• View radiology and pathology images in a browser

Find scientific datasets, AI models, methodology posts, and interactive demos through the Hugging Science catalog. Compare candidates for a research task and verify their licenses, input formats, access requirements, and supported ways to run them.

• Finding models for protein or genome analysis
• Selecting datasets for scientific machine learning
• Comparing resource licenses and runtime requirements

Analyze 2D fluorescence microscopy images to detect nuclei and measure their counts, intensity, and area. Run repeatable CellProfiler batches, inspect nucleus outlines, and review measurement tables with recorded pipeline settings and quality checks.

• Count nuclei across microscopy image batches
• Measure fluorescence intensity and area for each nucleus
• Inspect nucleus outlines for segmentation errors

Build and simulate quantum circuits in Python with Cirq. Compare noise effects, test parameter values, transform circuits for hardware constraints, and prepare experiments for Google Quantum AI or supported providers when the required access is available.

• Building and simulating quantum circuits
• Comparing measurement results at different noise levels
• Testing circuits across a range of parameter values

Review supplied writing through twelve DHDNA dimensions, a framework for describing reasoning and expression. Receive observations supported by quotations, optional scores, and comparisons between samples, with clear limits separating textual patterns from psychological traits.

• Reflect on reasoning patterns in your writing
• Compare argumentation across selected texts
• Review how a text expresses assumptions and uncertainty

Simulate a uniform gas mixture in a closed, insulated reactor at constant volume or pressure. Calculate ignition delay from the peak temperature rise rate, export temperature and species histories, and check conservation and numerical stability.

• Calculate ignition delay at constant volume or pressure
• Inspect temperature and species histories
• Compare ignition delays across reaction mechanisms

Find academic papers, verify authors and publication details, and create BibTeX entries, a structured format for references. Use it to organize bibliographies, remove duplicates, and check missing fields or mismatches with a manuscript.

• Find papers across multiple academic databases
• Convert DOIs into BibTeX references
• Remove duplicate bibliography entries

Analyze a chosen period of Screenpipe work history to find repeated research tasks, match them with existing skills, and prepare new skill drafts or combinations of existing skills for review.

• Find repeated tasks in recent work history
• Identify workflows existing skills do not cover
• Draft a skill from a recurring workflow

Implement and debug astronomical data analysis with Astropy in Python. Work with physical units, celestial coordinates, observation files, tables, precise time conversions, and cosmological models to prepare data and calculate astronomical quantities.

• Convert celestial coordinates and physical units
• Read and edit FITS observation files
• Match objects across astronomical catalogs

Process DNA, RNA, and protein sequences with Biopython, convert biological files, and retrieve NCBI records. Supports batch workflows for sequence comparison, searches for similar sequences, protein structure analysis, and evolutionary trees.

• Convert GenBank files to FASTA
• Calculate sequence length and GC content in batches
• Retrieve sequences and publication records from NCBI

Retrieve and combine protein annotations, biological pathways, and chemical identifiers from services such as UniProt, KEGG, and UniChem using Python. Supports cross-database lookups and batch identifier conversion while preserving multiple matches and failed requests.

• Collect protein sequences and functional annotations
• Retrieve pathway information for genes
• Match compound identifiers across databases

Build draft structures and aggregate tables for clinical case, trial, diagnostic, and safety reports from verified synthetic, de-identified, or aggregate data. Local checks flag structural and consistency issues; qualified professional review remains required.

• Prepare a structured case-report draft
• Check trial-report sections for missing items
• Format aggregate adverse-event tables

Rank possible gene regulatory relationships from bulk or single-cell expression data using GRNBoost2 or GENIE3. The skill guides input preparation, compatible execution, method comparison, and stability checks to help prioritize candidates for further biological investigation.

• Rank candidate regulator–target gene relationships
• Compare GRNBoost2 and GENIE3 results
• Check network stability across seeds and resampled data

Plan protein characterization experiments with Adaptyv's cloud laboratory, estimate costs, submit sequences, track progress, and retrieve measured results. Supports binding, thermal stability, expression, fluorescence, and enzyme activity workflows through the API and Python SDK.

• Plan binding screens for candidate protein sequences
• Estimate experiment costs before submission
• Track laboratory progress and retrieve results

Prepare genomic interval data for machine learning by checking BED files, reference genome consistency, and model compatibility. Plan Region2Vec or scEmbed workflows and assess shared reference regions using local validation and planning helpers.

• Check BED coordinates and reference genome consistency
• Plan Region2Vec or scEmbed training
• Inspect model and tokenizer compatibility

Estimate intracellular reaction rates from steady-state carbon-13 tracing measurements. Validate carbon atom mappings and measurement inputs, simulate labeling, fit constrained fluxes, and diagnose which pathway rates the data can meaningfully constrain.

• Estimate metabolic fluxes from carbon-13 labeling
• Validate atom mappings and measurement inputs
• Simulate labeling for proposed reaction rates

Analyze time series with aeon, a Python toolkit for data that changes over time. Supports classification, regression, clustering, forecasting, anomaly detection, and pattern search, with guidance on preprocessing, algorithm selection, and evaluation.

• Classify time series and predict continuous outcomes
• Group time series with similar patterns
• Forecast future values

Explore difficult decisions, research trade-offs, or creative challenges through several simulated perspectives. Separate facts, assumptions, and values, compare competing priorities, and produce a conditional recommendation with unresolved questions, a next step, and conditions that would change the choice.

• Comparing business options with competing priorities
• Reviewing trade-offs in a research plan
• Challenging assumptions behind a preferred choice

Build and operate genomics workloads on DNAnexus using its command-line tools and Python SDK. The skill covers data transfers, app configuration checks, workflow imports, execution monitoring, and explicit cost controls for reproducible analysis workflows.

• Transfer and organize genomics data on DNAnexus
• Validate app configuration and build applets
• Import WDL, CWL, or Nextflow workflows