Software Development Skills

Enforces high-impact academic writing principles (C-C-C, A-B-T, active voice, paragraph integrity) on draft text for bioinformatics and computational biology manuscripts.

Convert between .h5ad (AnnData) files and R single-cell data formats (Seurat, SingleCellExperiment) using anndataR. Use this skill whenever the user mentions: h5ad files, AnnData objects, converting between Python scanpy and R (Seurat/SingleCellExperiment), moving single-cell data between Python and R ecosystems, or needs to read/write .h5ad files from R. This skill provides pure R H5AD interface without Python dependencies.

R package for single-cell ATAC-seq analysis. Use for chromatin accessibility analysis, peak calling, motif enrichment, and integration with gene expression.

Batch-balanced k-nearest neighbors for single-cell data integration. Fast and simple Python implementation for batch correction.

Interactive web-based viewer for single-cell RNA-seq data. Use for exploring datasets, creating visualizations, and sharing results. For programmatic access use cellxgene-census.

Maintain this specific academic website repo safely and consistently. Use this skill whenever the user asks to update, review, polish, reorganize, or extend this website, especially when the request touches homepage identity statements, publications, CV assets, shared templates, or duplicated academic content.

Run CodeBTI interviews to infer coding style preferences and generate project-specific CodeStyle.md, SKILL.md, or SPEC.md for Python projects.

Acts as a peer review assistant to evaluate bioinformatics manuscripts. Identifies missing baselines, methodological flaws, and data leakage.

Check Cursor usage, billing, and quota through the shared provider usage checker. Reuse local browser session cookies and call Cursor's authenticated usage APIs before considering any browser automation.

Hugging Face Datasets library for loading and processing datasets. Use for loading datasets from Hub, processing with map/batch, tokenization, train-test splits, caching, and memory-mapped datasets. Best for NLP and ML datasets. For model training use transformers; for loading from files use PyTorch DataLoader.

Drafts highly precise Methods sections for spatial transcriptomics, single-cell RNA-seq (e.g., muscle aging/regeneration), and 3D interpolation pipelines.

Query Ensembl genome database REST API for 250+ species.

Translates complex deep learning architectures (VQ-VAE, Transformers, Neural ODEs) into standard biological manuscript text, focusing on the biological rationale for the architecture.

Toolkit for spatial genomics. Comprehensive R package for spatial transcriptomics analysis with advanced visualization and statistics.

Human Cell Atlas data portal. Use for accessing single-cell reference datasets, cell type markers, and standard atlases.

Upload or delete images through the locally installed imgur command from @rasch/imgur-cli. Use when the user wants to send a local image file or remote image URL to Imgur, retrieve the public link plus deletehash, remove a prior upload by deletehash, or verify/troubleshoot the local Imgur CLI installation.

Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion.

Access NIH Metabolomics Workbench via REST API (4,200+ studies).

R package for single-cell trajectory analysis. Use for reconstructing pseudotime trajectories, identifying cell differentiation paths, analyzing branch points, and ordering cells along developmental processes. Best for understanding dynamic biological processes from scRNA-seq data.

Use this skill any time a .docx file is involved, including creating Word documents, reports, letters, memos, proposals, or editing existing documents with tables, headers, footers, and comments.

Use this skill any time a .pptx file is involved, including creating slide decks, presentations, or editing existing presentations with charts, tables, images, animations, and notes.

Use this skill any time a .xlsx file is involved, including creating spreadsheets, financial models, dashboards, trackers, or editing existing workbooks with formulas, charts, validations, and named ranges.

Packages and distributes Python libraries with modern pyproject.toml, wheels, source distributions, build backends, and PyPI publishing workflows. Use this skill whenever a user mentions packaging, pyproject.toml, wheels, python -m build, Twine, trusted publishing, PyPI release problems, or making a Python package installable outside the repo.

Create a repo-specific maintenance skill for a personal website. Use this skill whenever the user wants to turn a website repo into a reusable maintenance workflow, codify site-specific editing rules, teach an agent which website sections can change and which must stay fixed, or generate a maintenance skill for an academic site, portfolio, blog, lab page, or personal homepage. Use it even if the user does not explicitly say "skill" but clearly wants persistent AI-safe maintenance rules for a website repo.