Zhijun Zhang
Community@zhnnky329 · Shenzhen
Algorithm Team Navigation @XDU-IRobot
Agent Skills by Zhijun Zhang
Showing 28 vetted skills indexed across 1 GitHub repositories.
matlab-model-code-generator
Generates executable MATLAB/.m scripts from a validated method plan and cleaned data.
robustness-checker
Run robustness, sensitivity, error, and baseline checks on modeling outputs.
model-code-analyzer
Translate validated modeling plans into language-neutral coding blueprints for Python or MATLAB.
consistency-auditor
Audit cross-media consistency across tex, code, results, data, and appendix.
model-assumptions-builder
Extract and categorize assumptions into a structured planning/model_assumptions.md document.
data-auditor-cleaner
Audit and clean raw contest data with a reproducible cleaning log.
workflow-orchestrator
Coordinates gate-driven workflows across modeling-contest stages from parsing to QA.
python-model-code-generator
Generate executable Python modeling code from validated method plans and cleaned data.
figure-table-planner
Classify figures and tables by type and map them to paper sections.
paper-polisher
Polish mathematical modeling paper drafts for grammar, clarity, and formatting compliance.
python-code-reviewer
Review Python modeling scripts against a validated method plan and expected artifacts.
matlab-code-reviewer
Validates MATLAB and Beita Tianyuan scripts for runnability and traceable outputs.
symbol-table-builder
Build a global symbol table for mathematical modeling concepts across subquestions.
decision-prompt-builder
Generate trade-off questions for human judgment at modeling decision gates.
problem-parser
Parse contest problem statements into structured specifications with goals, constraints, and subquestions.
problem-classifier
Classify parsed subquestions into standard mathematical modeling problem types.
math-figure-generator
Generate publication-quality multi-panel mathematical modeling figures with Matplotlib.
method-selector
Generate candidate modeling schemes with PoC scripts and decision artifacts.
modeler-decision-logger
Append human modeling decisions with timestamps to an auditable log.
result-report-generator
Generate structured experiment reports from multi-method model outputs.
related-paper-analyzer
Analyze user-supplied papers and generate a literature-analysis report.
completeness-auditor
Verify completion artifacts contain at least five explicit pass items.
code-reviewer
Route Python or MATLAB modeling code to the appropriate language-specific reviewer.
solution-package-builder
Combine method explanations and result analyses into a writer-ready manuscript package.