메뉴
Proposal-first scientific writing pipeline. Three modes (compose/revise/hybrid) with four-layer QA pipeline. Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs.
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
Multi-source literature search, citation verification, strict independent other-citation audits, article-level citation metric tables, influential citer profiling with citation-context extraction, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv, Scopus, ScienceDirect). Use for coordinated literature workflows beyond one MCP call, including 文献检索、 查文献、找文献、文献综述检索、查论文、引文核对、参考文献管理、文献去重、 严格他引、他引判定、排除自引、谁引用了我的文章、引用我的文章的人有没有大牛、 院士引用、校长引用、院长引用、杰青引用、长江学者引用、Fellow引用、文章引用表、 指定文章引用数、严格他引数、整理成表格.
Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default. Use this skill whenever the user asks to input text and automatically get references, add citations to a paragraph/manuscript, find Nature-series or CNS support for statements, create text-to-reference correspondence, "分段引用", "自动给出引用", "Nature系列引用", "CNS及子刊", "支撑文献", "补引用", "找引用", or export EndNote/RIS/ENW/Zotero RDF. Also trigger on general academic-writing citation needs even without the word "Nature", such as adding references while writing a paper, finding sources/literature for a claim, building a reference list, citation/referencing for academic writing, and Chinese phrasings like 学术写作引用、写论文加引用、写paper找文献、加参考文献、配文献、引用文献、文献支撑.
Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data, supplementary datasets, DataCite-style dataset references, FAIR metadata for academic publication, or Chinese-to-English data availability wording for Chinese-speaking authors preparing Nature-family submissions. Also trigger on general academic-writing data needs even without the word "Nature", such as writing a data availability statement for any journal, code/data sharing sections, repository selection while writing a paper, and Chinese phrasings like 数据可用性声明、数据可用性、 数据共享、代码可用性、学术写作数据声明、写数据声明、数据存放、数据仓库选择.
Use this skill whenever the user wants to configure school/library access, reuse a logged-in Chrome institutional session, search library databases, download legitimate open-access or institution-authorized academic full text/PDFs, handle missing library permission, organize papers, or read PDFs and supporting information.
标准化实验日志记录——接收原始材料（图/语音/文字），产出带 YAML frontmatter 的标准日志到 Obsidian vault。需配合飞书 CLI 或手动输入使用。
Submission-grade Nature/high-impact journal figure workflow for Python or R, plus optional OpenRouter GPT Image 2 manuscript schematic generation when the user explicitly asks for AI-generated graphical abstracts, concept schematics, mechanism diagrams, or paper schematic illustrations. Use whenever the user asks to create, revise, audit, or polish manuscript figures, multi-panel scientific plots, figures4papers-style matplotlib plots, journal-ready SVG/PDF/TIFF outputs, or OpenRouter/API-generated schematic drafts, especially for Nature-family or other high-impact journals. Before plotting or image generation, define the figure's conclusion, evidence logic, export needs, and review risks. For plotting tasks, honor an explicit Python/R choice, otherwise reuse the saved nature-figure backend preference; if no preference exists, ask once whether the user prefers Python or R and save that answer for future calls. For explicit OpenRouter/GPT Image 2 schematic generation, do not ask Python or R; use the AI-schemat
| name | researchwrite |
| description | Proposal-first scientific writing pipeline. Three modes (compose/revise/hybrid) with four-layer QA pipeline. Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs. |
| version | 1.0.0 |
| author | 十五 (JL Lab) |
| license | MIT |
| metadata | {"hermes":{"tags":["research","writing","proposal","revision","qa","multi-agent"],"related_skills":["brainstorming","professor","avoid-ai-writing","docx"]}} |
受 autonovel（状态机+打分）、professor（动态专家）、brainstorming（入口追问）、anti-AI-writing（语言清理）启发的科研写作状态机。不是通用"帮我写论文"prompt。
research_canon 和 evidence_tableargument_mapprofessor 按失败模式召唤对应专家| 输入 | 模式 |
|---|---|
| 题目、方向、模糊想法 | compose — 加载 references/compose-mode.md |
| 已有段落/章节/完整 proposal | revise — 加载 references/revise-mode.md |
| 已有草稿 + 扩写/补写/重构 | hybrid — 加载 references/hybrid-mode.md |
模糊时推断默认模式。只在选择会改变工作流时才问用户。
工作目录：<outputs>/researchwrite/<project-slug>/
标准文件：
00_scope.md 写作任务边界
01_research_canon.md 硬事实和约束
02_evidence_table.md claim → evidence 映射表
03_argument_map.md 论证架构
04_section_contracts.md 每节的 purpose / inputs / allowed & forbidden claims
05_style_guide.md 风格、术语、禁用表达
state.json 项目状态（mode、round、scores、technical_debts）
sources/ 用户材料、文献、数据
drafts/ 草稿和分节文件
revision_briefs/ 修订简报
qa_logs/ 诊断、专家审查、anti-slop、打分记录
exports/ 最终输出（.md + .docx）
新建项目时从 templates/ 取空模板。references/worked-example-quaternary-proposal.md 提供了基于通用材料科学领域的完整填写示例。
公开版本包含四个关键 reference：
| Reference | 用途 |
|---|---|
references/evaluation-rubric.md | 8 维 × 4 锚点评分体系 + 评分流程 |
references/stopping-rules.md | 迭代循环终止条件 |
references/foundation-files.md | 建立 foundation 五文件 |
references/validation-checklist.md | 自动校验清单 |
完整 reference 文件（compose/revise/hybrid 模式详解、专家分派、导出归档、综述框架等 12 份）未包含在公开版本中。如需获取，请通过 GitHub issue 或邮件联系作者。
每次运行结束时输出：
当用户说"审查这段/跑 QA/检查方案/过 pipeline"时，进入 QA 模式。
| 挡位 | 适用场景 | 阈值 |
|---|---|---|
paper | 投稿论文 | 7.0 |
proposal | 研究方案/开题 | 7.0 |
internal | 内部汇报/周报 | 5.0 |
quick | 快速扫读 | 无 |
Gate 2: professor Convener（内容层）
├── 论文 → 方法论专家 + 领域专家
├── proposal → 可行性专家 + 创新性专家
└── 文献reviews → 覆盖面专家 + 批判深度专家
│
▼
Gate 1: avoid-ai-writing 模式 detect-only
└── 只对英文有效，中文跳过或降级为手工扫读
│
▼
Gate 3: auto-validation（格式/完整性层）
└── 每个 claim 有 citation？方法可复现？编号连续？
│
▼
Gate 4: 评分阈值（分维度打分）
├── 总分≥阈值 → 通过 ✅
└── 总分<阈值 → 按低分维度定向回退（不超过 3 轮）
Gate 2 在 Gate 1 之前 — 避免改了句子后被专家打回重写。
用户: "用 researchwrite 审查这段 discussion，paper 挡位"
→ 自动走 Gate 2 → Gate 1 → Gate 3 → Gate 4
→ 返回审查报告 + 定向修改建议
用户: "快速扫一下这个邮件"
→ 走 quick 挡位，只标记 P0 问题
首次使用告诉 agent 你的研究背景，agent 会调用 professor 建立领域专家知识。后续写作中专家审查会基于你的领域。