smestern
@smestern
Public Skills
update-domain
by smestern
Incrementally update domain knowledge — add new packages, refine workflows, or extend template content without re-running the full configuration interview. Use after initial /configure-domain setup.
configure-domain
by smestern
First-time domain setup — interviews you about your research field, discovers relevant scientific packages via PyPI and GitHub, then fills in all template placeholder sections across your SciAgent instruction files. No Python runtime or wizard dependency needed.
data-qc
by smestern
Performs systematic data quality control checks before analysis — missing values, outliers, distributions, unit validation, duplicates, and structural integrity assessment with severity-rated reporting.
docs-ingestor
by smestern
Ingest documentation for any Python library — crawls PyPI, ReadTheDocs, and GitHub to produce a structured API reference (classes, functions, pitfalls, recipes). Use when the agent needs to learn an unfamiliar library for scientific analysis. Requires sciagent[wizard].
analysis-planner
by smestern
Creates step-by-step analysis plans for scientific data — designs the pipeline, specifies parameters, anticipates risks, and defines success criteria before any code is executed.
report-writer
by smestern
Generates structured scientific reports from analysis results — publication-quality Markdown with abstract, methods, results, figures, tables, uncertainty quantification, limitations, and reproducibility information.
code-reviewer
by smestern
Reviews scientific analysis scripts for correctness, reproducibility, error handling, code quality, performance, and scientific best practices — provides severity-rated actionable feedback without modifying code.
rigor-reviewer
by smestern
Audits analysis outputs, code, and claims for scientific rigor violations — statistical validity, effect sizes, data integrity, p-hacking risks, reproducibility, visualization integrity, and reporting completeness.
scientific-rigor
by smestern
Enforces scientific rigor principles during data analysis — data integrity, objective analysis, sanity checks, transparent reporting, uncertainty quantification, reproducibility, and safe code execution. Auto-loads when scientific analysis is detected.