My-Academic-Skills

Write, revise, and evaluate academic prose and research ideas with disciplined confidence, precise claim calibration, minimal redundant caveats, and room for exploratory hypotheses. Use for papers, abstracts, discussions, conclusions, limitations, reviewer responses, research plans, and idea development when the writing or reasoning risks becoming over-defensive, repetitive, apologetic, or prematurely dismissive of testable directions.

Coordinate advisory-only academic manuscript drafting, revision, resubmission, reviewer-response preparation, section-agent delegation, literature positioning, theorem or proof checking, mathematical validation, and linguistic smoothing. Use when Codex needs to organize scholarly manuscript work with a master agent and specialist sub-agents for literature review, mathematical validation, and academic prose polishing while preserving files until explicit user approval.

Support rigorous academic research workflows including literature discovery, paper triage, reading notes, evidence synthesis, citation hygiene, research planning, reproducible writing, reviewer responses, and safe handling of original data. Use when Codex is asked to find, evaluate, summarize, compare, cite, organize, or write about scholarly sources, research questions, methods, experiments, datasets, or academic manuscripts.

Use when a Codex task is complex, long-running, high-value, adversarial, repetitive, parallelizable, or likely to suffer from partial completion, self-review bias, or goal drift. Provides a reusable dynamic workflow harness for planning, delegation, verification, synthesis, and completion discipline across coding, research, analysis, review, triage, refactoring, debugging, writing, and decision tasks.

Create, redesign, or audit publication-ready scientific figures with deterministic Python, especially Matplotlib and NetworkX. Use for journal or conference plots, directed-network diagrams, theory schematics, multi-panel figures, IEEE-width redraws, vector export, visual hierarchy, color-accessibility, and final-size figure QA. Trigger when exact data, equations, topology, geometry, or scientific meaning must be preserved; do not use generative imagery for quantitative evidence.

Revise English academic manuscript prose so it reads like careful human scholarship rather than generic AI-polished text. Use when Codex drafts, translates, rewrites, edits, polishes, compresses, or de-AI's research-paper text, LaTeX passages, abstracts, introductions, related work, methods, results, discussion, conclusions, captions, reviewer responses, or any manuscript section where the user asks for a less AI-sounding, more natural, precise, evidence-bound academic voice. Use alongside research-paper-writing, academic-research, and academic-manuscript-agents when those broader skills also apply.

Rigorous literature review workflow for complex networks, nonlinear dynamics, mathematical epidemiology, multi-agent systems, and adjacent physics, mathematics, and data science research. Use when Codex needs to perform early-stage scoping, mid-stage argument refinement, or late-stage paper-writing literature review with verified bibliographic metadata, DOI/author/title/journal/URL cross-checking, citation and journal impact constraints, milestone contributions, hot topics, open problems, evidence grading, and explicit uncertainty marking.

General-purpose rigorous literature review workflow for any research field or interdisciplinary topic. Use when Codex needs to perform early-stage scoping, mid-stage argument refinement, or late-stage paper-writing literature review with current source lookup, verified bibliographic metadata, field-appropriate databases and venues, DOI/author/title/venue/URL cross-checking, citation and quality constraints when provided, milestone contributions, latest progress, hot topics, unresolved problems, evidence grading, and explicit uncertainty marking.

Grade or review student assignments from course folders using assignment criteria, course outlines, rubrics, and grade sheets. Use when Codex is asked to mark essays, exams, coding assignments, problem sets, presentations, reports, projects, or whole assignment folders; create grade tables with student name, ID, mark out of 100, short comments, remarks about inaccessible content, and an overall marking report.

Rigorous mathematical reasoning, verification, proof checking, and human-guided problem solving. Use when Codex needs to verify provided mathematical material, inspect theorem/proposition statements, check derivations, identify missing assumptions or counterexamples, develop proofs, solve symbolic or abstract math problems, or guide a user through mathematical derivations step by step.

Build, run, validate, and document reproducible mathematical and scientific simulations in Python using NumPy, SciPy, pandas, Matplotlib, and Seaborn. Use when Codex needs to load raw tabular or numerical data, design numerical experiments, solve ODEs or optimization problems, compute statistics or sensitivity analyses, and output publication-quality scientific graphs from explicit plotting instructions while preserving original data.

Plan, draft, revise, and polish rigorous academic research papers, including abstracts, introductions, related work, methods, theory, experiments, discussion, conclusions, response-to-reviewer material, and journal/conference resubmissions. Use when Codex is asked to write or improve scholarly manuscripts, strengthen research arguments, restructure sections, align claims with evidence, improve academic tone, prepare revision plans, synthesize literature into manuscript prose, or produce publication-focused editing.