Use for citation-quality audits in this repository: identify claims needing citations, flag unsupported or weakly supported claims, keep only strong sources, and conservatively update references/library.bib with verified entries for paper drafts and review-analysis chapters.
Use when ChatGPT/Codex needs to transform multiple Markdown working files for a single research paper chapter into a polished, journal-style chapter draft, create export-ready Markdown/HTML variants, and generate a single-chapter PDF.
Use for paper-first method design work in this repository: translate an implemented or existing graph substrate plus literature findings into a narrow, conceptual Method section centered on scenario memory, decision episodes, and decision-grade context without turning the paper into a system write-up.
Use for paper-first research positioning work in this repository: synthesize literature notes into a narrow problem framing, candidate research gap, strongest vs weakest thesis, contribution statements, and title options for decision-grade memory / SME decision support papers.