Large datasets can exceed memory or make pandas and NumPy workflows too slow. This skill guides Dask collections, schedulers, chunking, and distributed execution.

Engineering leaders need clear frameworks for architecture, metrics, hiring, and technical debt. This skill turns CTO planning questions into structured assessments, templates, and practical next steps.

ClinVar data is large, versioned, and difficult to interpret safely. This skill guides Claude, Codex, and Claude Code through ClinVar searches, evidence review, and variant annotation workflows.

Pharmacogenomics data is spread across guidelines, labels, variants, and literature annotations. This skill helps Claude, Codex, and Claude Code query ClinPGx resources and summarize gene-drug evidence.

Finding relevant public trial records requires precise filters and careful review of nested registry data. This skill searches ClinicalTrials.gov and produces focused summaries or exports.

Clinical teams need clear reports that follow medical and regulatory standards. This skill provides templates, checklists, and validation guidance for case reports, diagnostics, trials, and patient notes.

Research projects often lose time to incomplete, inconsistent, or incorrect references. This skill helps Claude, Codex, and Claude Code find citation metadata, validate entries, and format BibTeX files.

Quantum workflows require careful circuit design, simulation, optimization, and provider setup. This skill provides practical Cirq guidance for simulators, noise studies, experiments, and hardware execution.

Drug discovery teams need reliable access to compound, target, and bioactivity records. This skill guides focused ChEMBL queries, structure searches, and result interpretation.

Technical commit messages make release notes slow and difficult to understand. This skill groups relevant commits and rewrites them as clear, structured changelogs.

Population-scale single-cell queries can exceed memory or produce duplicated counts. This skill provides focused, reproducible query patterns for CELLxGENE Census analysis.

Quality teams need consistent CAPA investigations, action plans, and effectiveness checks. This skill structures root cause analysis, preventive actions, metrics, and compliance-focused reporting.

Bioinformatics research often requires separate interfaces for proteins, pathways, compounds, and identifiers. This skill guides unified BioServices workflows across major biological databases.

Complex biomedical analyses require coordinated reasoning, data access, and reproducible reporting. Biomni guides an autonomous agent through these multi-step research workflows.

Astronomy workflows require careful handling of units, coordinates, time scales, and specialized formats. This skill provides practical Astropy guidance for accurate, efficient analysis.

Complex interactive artifacts require more structure than a single HTML file. This skill scaffolds React projects and bundles them into self-contained HTML artifacts.

Gene expression analysis requires careful data preparation, algorithm selection, and resource planning. This skill creates practical Arboreto workflows for reproducible local or distributed inference.

API integrations often fail because authentication, retries, and rate limits are incomplete. This skill guides robust clients, OAuth flows, webhook verification, and operational checks.

Annotated biological matrices are complex to build, combine, and store efficiently. This skill provides practical AnnData patterns for reliable Python workflows.

Finding and interpreting predicted protein structures requires several APIs, formats, and confidence measures. This skill organizes AlphaFold DB retrieval, downloads, confidence analysis, and bulk workflows.