SDP 双模型 6 审稿人 + 交叉审核系统。含拒稿信预演。当用户说"审稿"、"review"、"帮我看看这篇论文写得怎么样"时触发。
Nexus 统一入口。意图识别 + 模式路由 + 首次引导 + Autopilot 模式。当用户提出任何学术研究相关请求时触发（调研、找论文、构思 idea、写论文、审稿、做实验等）。
基于 Evidence Graph + Knowledge Graph 进行学术 idea 构思与评估。双阶段流程：Phase 1 用 ToT 思维树系统性探索，Phase 2 用 SDP 跨模型红队攻击。当用户说"帮我想 idea"、"brainstorm"、"研究方向"、"有什么可以做的"时触发。
Review code changes for correctness, regressions, edge cases, style issues, and unnecessary churn. Use when checking diffs, reviewing pull-request-like changes, or doing independent quality review. Triggers on "review this", "check my changes", "code review", "代码审查".
Perform safe, reviewable refactors. Use when restructuring code, moving responsibilities, renaming across modules, or reducing duplication without intended behavior changes. Triggers on "refactor X", "rename Y across the project", "extract helper", "重构".
typed knowledge-graph 抽象层 (Wave B.3)。把分散在 evidence_graph / corpus_ledger / story_skeleton 的结构升级成 paper / idea / claim / experiment / mechanism / baseline 节点 + supports / contradicts / derives_from / cites / replicates / falsifies 边。通过 4 个 MCP tool 维护 artifacts/research_wiki.json，并用 export_to_evidence_graph 投影回 evidence_graph schema。
Generate a point-by-point reviewer response letter in Nature house style (complements `rebuttal-writer` which targets conference rebuttals).
Auto-suggest SKILL.md改进。读 evolution-memory event log (~/.nexus/evolution_memory/.event_log.jsonl)，找出反复 rollback / 反复 blocked / 反复 manual override 的 stage，生成人工审阅用的 markdown 建议。从不直接改 SKILL.md。