mathmodeling-skills

Plugin mathmodeling-skills from marketplace mathmodeling-skills in zhnnky329/MathModeling-skills. Commands read from the repo's manifest — today.

Skills (29)

• code-reviewer

  Detect whether approved modeling code is Python or MATLAB/Beita Tianyuan and route it to the matching reviewer using the compact named-check review contract.

• completeness-auditor

  Audit whether the semantic evidence required by the active lean or submission profile exists and is current, without requiring one verbose artifact per skill or an arbitrary number of pass bullets.

• consistency-auditor

  Run scoped or final cross-media consistency checks for mathematical-modeling artifacts, comparing canonical numbers, symbols, parameters, decisions, files, and paper claims without performing full-workspace audits for low-risk changes.

• data-auditor-cleaner

  Map contest attachments to subquestions, audit and clean raw data, and emit one reusable data profile with quality, coverage, imbalance, concentration, and method-readiness evidence for downstream risk screening.

• decision-prompt-builder

  Build one compact choice card at a genuine mathematical-modeling judgment point. Use before method screening, after a meaningful experiment, or before final claim/freeze approval so the human chooses the trade-off while AI handles mechanical consequences.

• figure-table-planner

  Plan the smallest set of diagnostic, comparison, paper, and appendix figures or tables needed to support verified mathematical-modeling decisions and claims.

• final-method-explainer

  Build the authoritative final method explanation for a submission-ready subquestion from the method card, human decision ledger, code plan, final results, and robustness evidence.

• math-figure-generator

  Generate and render-verify publication-quality mathematical-modeling figures from saved evidence, using the approved figure plan, source data, claim, type, and consistent visual system.

• matlab-code-reviewer

  Review, run, debug, and verify approved MATLAB or Beita Tianyuan modeling code against its plan, data contract, method decision, compatibility constraints, and experiment outputs, saving one compact JSON review.

• matlab-model-code-generator

  Generate and run minimal reproducible MATLAB or Beita Tianyuan compatible code for the human-approved main method and usable baseline, with compact experiment artifacts and a canonical run summary.

• method-selector

  Build and risk-screen a compact role-based method shortlist for a mathematical-modeling subquestion. Use after problem framing and data profiling, before model code generation, to propose a main candidate, a usable baseline, and at most one conditional fallback without padding the pool.

• model-assumptions-builder

  Extract and maintain global and method-specific mathematical-model assumptions from the problem frame, active method cards, data profile, and risk probes, while leaving necessity and impact judgments to the human modeler.

• model-code-analyzer

  Translate a human-approved main method and usable baseline into a minimal language-neutral implementation and experiment contract. Use after G2.5 and data readiness, before Python or MATLAB code generation.

• modeler-decision-logger

  Faithfully append a human modeler's choice and rationale to one canonical per-subquestion JSONL decision ledger. Use after a choice card is answered or when migrating legacy decision artifacts; never originate or improve the decision.

• paper-polisher

  Polish mathematical modeling paper drafts for grammar, clarity, formula consistency, hedging calibration, overclaim detection, and contest formatting compliance. Use after paper-section-writer has drafted sections.

• paper-section-writer

  Draft submission-ready mathematical-modeling paper sections from the approved solution package, frozen numbers, human decision ledger, and verified figures without searching scattered exploratory outputs or inventing interpretation.

• problem-classifier

  Classify each parsed mathematical-modeling subquestion by required output and structure, surface ambiguous framing trade-offs for human choice, and record primary/secondary task types without selecting algorithms.

• problem-parser

  Parse a mathematical-modeling problem into goals, objects, data, constraints, outputs, subquestions, dependencies, variables, relationships, and human-confirmed success criteria before any method selection.

• python-code-reviewer

  Review, run, debug, and verify approved Python modeling code against its code plan, data contract, method decision, risk conditions, and experiment outputs, saving one compact JSON review.

• python-model-code-generator

  Generate and run minimal reproducible Python modeling code for the human-approved main method and usable baseline, saving compact experiment artifacts and a canonical run summary.

• quality-assurance-auditor

  Perform the final submission-level audit of mathematical-modeling workflow integrity, evidence quality, anti-fabrication, paper coherence, figures, references, and contest readiness after consistency and completeness audits pass.

• reference-manager

  Manage and verify references for mathematical modeling contest papers, generating BibTeX entries, checking citation completeness, and ensuring all references are traceable to actual sources.

• related-paper-analyzer

  Collect and analyze relevant papers, reports, and reference methods to inform method selection without fabricating references or copying models blindly.

• result-report-generator

  Summarize modeling experiment evidence, compare the approved main method with a usable baseline, surface fallback triggers, and produce a decision-point or final report without creating routine per-round prose.

• robustness-checker

  Design and run risk-targeted robustness, sensitivity, error, and baseline checks for an approved mathematical model, emitting compact machine evidence in lean mode and a final report in submission mode.

• solution-package-builder

  Assemble a submission-ready writer package from final method, result, robustness, figure, and human-decision artifacts, then freeze approved numerical claims with provenance.

• submission-packager

  Package a G6-approved mathematical-modeling paper and its exact supporting code, data, results, and figures without changing their behavior or the workspace.

• symbol-table-builder

  Build and maintain one global mathematical symbol and unit table from the problem frame and active method cards, resolving cross-subquestion conflicts before code or paper work.

• workflow-orchestrator

  Inspect a mathematical-modeling workspace, evaluate lean or submission gates per subquestion, update machine-readable manifests, classify change impact, and route one next action without duplicating downstream work.

Hooks (1)

• SessionStart

  echo '[math-modeling guardrails active] Human owns modeling judgment; raw data and frozen numbers stay immutable; final assembly requires all submission audits to pass.' >&2

Similar plugins