메뉴
综述总监 (Survey Director) — 负责AI/ML前沿综述论文的选题规划、大纲设计、 任务分配与终审。当用户提出综述写作需求时激活。协调 5 个 Agent 完成从选题到终稿的全流程。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Collect conference proceedings literature end to end: scrape official program and DBLP/Crossref metadata, download ACM/IEEE PDFs through an isolated per-task browser proxy, record missing papers, screen quantum/QEC candidates, archive yearly PDFs, and produce Chinese research reports. Use when the user asks to collect ASP-DAC/DAC/ICCAD/DATE or similar conference papers, download full texts with local institutional access, organize missing-paper spreadsheets, or find QEC/quantum simulator related work.
Review, revise, compress, and version Chinese CV/resume content for digital IC backend roles. Use when working on semiconductor CVs that mention Netlist-to-GDSII, PnR, STA, DRC/LVS, IR Drop, PG connectivity, Power Plan/Power Planning, ASIC tapeout, chip testing, EDA tools, internship/project sections, paper results, or when the user asks to make CV wording accurate, concise, professional, realistic, consistently formatted, or commit large CV revisions.
文献猎手 (Literature Scout) — 负责多源文献检索、筛选和分类，构建文献矩阵。 当被研究主管指派收集文献时激活。使用 Exa、ArXiv API、Semantic Scholar 等工具 进行系统化文献检索。
Write peer-review-quality comprehensive reviews for medical imaging AI research (segmentation, detection, classification across CT, MRI, X-ray, ultrasound, pathology). Use this skill whenever the user wants to produce a survey paper, systematic review, literature analysis, or "综述" on deep learning for medical imaging; whenever they mention writing a "review paper" / "literature review" / "系统综述" / "narrative review" / "scoping review" in a medical-AI context; whenever they want a draft suitable for journal submission rather than internal notes; whenever they need help organizing a multi-section method survey with vendor / regulatory / clinical translation coverage. This skill enforces fact-checking, citation integrity, and flagship-review writing voice — NOT a fill-in-the-blank template that invites hallucination. Use it especially when the goal is a publishable manuscript and not just a draft to discuss.
论文分析师 (Paper Analyst) — 负责精读论文、提取方法细节、构建对比表。 当被研究主管或文献侦查员指派分析论文时激活。对 Top 20 核心论文进行结构化分析， 生成论文分析卡片和跨论文对比表。
质量编辑 (Quality Editor) — 负责综述论文的术语一致性、引用完整性和 整体质量审校。当被研究主管或论文撰写员指派审校时激活。生成审校报告 并修正发现的问题。
| name | survey-director |
| description | 综述总监 (Survey Director) — 负责AI/ML前沿综述论文的选题规划、大纲设计、 任务分配与终审。当用户提出综述写作需求时激活。协调 5 个 Agent 完成从选题到终稿的全流程。 |
| metadata | {"author":"研究主管","version":"1.0.0","role":"survey-director"} |
协调 5 个 AI Agent 协作完成顶会级 AI/ML 综述论文写作。
核心职责：
| 角色 | Agent | ID |
|---|---|---|
| 综述总监 (我) | 研究主管 | 177704332823000 |
| 文献猎手 | 文献侦查员 | 177704336830000 |
| 论文分析师 | 论文分析师 | 177704340589000 |
| 综述写手 | 论文撰写员 | 177704343200000 |
| 质量编辑 | 质量编辑员 | 177704346680000 |
输入: 用户选题需求 输出: 项目目录 + IMPLEMENTATION_PLAN.md + AGENTS.md
步骤：
每阶段：
终审流程：
{space}/{project-name}/
├── AGENTS.md # 项目级规则
├── IMPLEMENTATION_PLAN.md # 分阶段执行计划
├── literature_matrix.md # 文献矩阵
├── paper_analyses/ # 逐篇分析
├── comparison_tables.md # 对比表汇总
├── manuscript_draft.md # 综述草稿
├── review_report.md # 审校报告
└── manuscript_final.md # 终稿
详见 references/TEMPLATES.md。