comses

Guide modelers in applying good modeling practice across the full computational modeling lifecycle, from problem framing through evaluation, uncertainty disclosure, governance, and maintenance. Use this skill when users want lifecycle guidance, quality self-assessment, required modeling deliverables, or protocol-specific checks for ABM, uncertainty, reproducibility, ethics, participatory modeling, and deep uncertainty. Expected output: staged modeling guidance, identified deficiencies against required practices, and a concrete set of required artifacts and review checks.

Generate narrative documentation for computational models and research software, and select the appropriate documentation framework for a given model type. Use this skill when a user wants to: * document a computational model * generate documentation from source code * write an ODD or ODD+2 narrative for an agent-based model * create model narratives for publication or reuse * draft a model card, mathematical specification, or workflow description The skill classifies the model type, selects a framework, extracts model structure from supplied materials, and drafts documentation. It does not assess or score existing documentation — use the document-review skill for completeness assessment, gap analysis, or structured review output. Inputs may include source code, pseudocode, READMEs, publications, architecture descriptions, or model metadata.

Repository-local maintainer workflow for refreshing skill assets and references when upstream standards, rubrics, or guidance change. Use when updating compressed artifacts, checklists, and linked policy text across this repository in a consistent PR.

Create FAIR4RS-compliant metadata, publication checklists, and citation files for computational models of social-ecological systems to prepare them for publication, sharing, and reuse. Use this skill when preparing models for Zenodo, arXiv, discipline-specific repositories, or journal supplementary materials. Triggers: "prepare for publication", "create FAIR metadata", "generate publication checklist", "archive my model", "submit to Zenodo", "make my code citable". Expected output: codemeta.json (canonical metadata source), CITATION.cff generated from codemeta.json, data management plan (DMP), software management plan (SMP), publication checklist, and metadata JSON-LD suitable for Zenodo, arXiv, or disciplinary repositories.

Generate Slurm job scripts, job arrays, and resource allocation templates for running computational models on HPC (High-Performance Computing) clusters. Use this skill when you need multi-node execution, high-memory jobs, GPU/accelerator access, or direct Slurm cluster submission. Triggers: "run on HPC", "generate Slurm script", "set up batch array job", "submit to cluster", "create Slurm job array". Expected output: Slurm batch scripts (.slurm), job array configurations, resource allocation templates, and submission validation checklist.

Generate HTCondor job submission scripts, parameter sweep configurations, and batch job templates for running computational models on the Open Science Grid (OSPool). Use this skill when you need to run parameter sweeps, large ensembles, or distributed sensitivity analysis on OSPool infrastructure. Triggers: "run on OSPool", "generate HTCondor script", "set up batch parameter sweep", "submit to OSG", "create HTCondor DAG". Expected output: HTCondor submit files (.submit), DAG specification files, parameter sweep configuration, and submission checklist.

Evaluate computational model submissions for CoMSES-style peer review readiness using reproducibility, documentation, code quality, and research software engineering criteria. Use this skill whenever a user asks to review a computational model, codebase, model release, or submission package for publication, reuse, or peer review. Trigger on phrases like: "peer review my model", "is this model submission ready", "review codebase quality", "check reproducibility", "review ODD documentation", "assess FAIR/research software quality". Expected output: structured peer review report with binary pass/fail recommendation, criterion-by-criterion findings, prioritized fixes, and an evidence-based checklist mapped to CoMSES review criteria and key EVERSE research software quality indicators.

Independently verify a generated ODD document against source materials and ODD+2 requirements, producing a scored verification report. Invoke manually as part of the odder workflow, after /odd-draft.

Execute an ODD generation plan to produce the complete ODD+2 protocol document and traceability matrix. Invoke manually as part of the odder workflow, after /odd-plan.

Collect structured feedback from a scientist after ODD generation, producing a report to improve the plugin. Invoke manually after completing an ODD generation workflow.

Analyze user feedback reports and conduct a structured interview with the plugin developer to plan concrete improvements to odder skills. Invoke manually when you have feedback reports to process.

Conduct a structured interview with a modeler to gather complete information for ODD+2 protocol generation from agent-based model code and documentation. Invoke manually as part of the odder workflow. Accepts a path to model files as an argument.

Transform ODD research findings into a standalone mega-prompt that a fresh agent can execute to generate the full ODD document. Invoke manually as part of the odder workflow, after /odd-interview.