researchwrite
Skill0 starsChanged 2 months agoMITView on GitHub
Proposal-first scientific writing pipeline, installed under the compatibility trigger researchwrite and the repository package name nature-proposal-writer. Use for composing, revising, or auditing research proposals, opening reports, research plans, and evidence-grounded scientific writing. Three modes (compose/revise/hybrid) with a four-layer QA pipeline. Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs.
3 other projects use a version of this, 3 of them edited.
Adopted by
Most recently taken up by
- Luooops/skillsedited, first seen Oct 13, 2026
- Yuan1z0825/nature-skillsedited, first seen Aug 31, 2026
- zh123012/claude-skillsedited, first seen Jul 29, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 3
- Yuan1z0825/nature-skills★ 54k93% same
- Luooops/skills★ 193% same
- zh123012/claude-skills★ 196% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- journal-style-learnSkill
- nature-academic-searchSkill
- nature-citationSkill
- nature-dataSkill
- nature-downloaderSkill
- nature-experiment-logSkill
- nature-figure-prompt-onlySkill
- nature-figureSkill
- nature-image2pptSkill
- nature-literature-pipelineSkill
- nature-paper2pptSkill
- nature-paper-cardSkill
- nature-paper-to-patentSkill
- nature-polishingSkill
- nature-readerSkill
- nature-ref-verifierSkill
- nature-responseSkill
- nature-reviewerSkill
- nature-sharedSkill
- nature-statisticsSkill
- nature-writingSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 28
When the target is Expert Systems with Applications (ESWA or Expert Syst.
- Very specific: line 31
Use the shared contract for a manuscript or publication plan explicitly targeting ESWA.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
researchwrite — proposal-first 科研写作 pipeline
Additional configured journals
For Applied Soft Computing (ASC), Engineering Applications of Artificial
Intelligence (EAAI), ISA Transactions, Knowledge-Based Systems (KBS),
Measurement, Neurocomputing, or IEEE Transactions on Reliability, use
../nature-shared/journal-formats/index.md to resolve the exact journal.
Preserve this skill’s task workflow and evidence safeguards. Apply only the
selected reference’s relevant scope; do not impose flagship-Nature significance
or import another journal’s numerical, citation, or production defaults.
These seven profiles do not yet establish verified official submission limits;
verify the target’s current official source when such requirements affect work.
ESWA journal context
When the target is Expert Systems with Applications (ESWA or
Expert Syst. Appl., case-insensitive), read
../nature-shared/journal-formats/eswa.md before applying journal-specific defaults.
Use the shared contract for a manuscript or publication plan explicitly
targeting ESWA; record applicable constraints in the existing scope/style files.
For empirical ML/RUL writing, also read ../nature-shared/core/eswa-ml-rul-style.md.
Preserve proposal-mode deliverables when the user asks for a proposal; ESWA
submission numbering and bibliography style do not change an unrelated proposal.
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。
researchwrite 是为兼容既有安装保留的触发名称,仓库目录名仍为
nature-proposal-writer。不要在没有迁移方案时修改 frontmatter 名称。需要初始化模板、
按条件加载参考资料或执行导出脚本时,先读取 manifest.yaml,只加载与当前条件匹配的路径。
核心原则
- 证据先于文字 — 起草前必须建立或读取
research_canon和evidence_table - 论证先于章节 — 写正文前必须完成
argument_map - 契约先于段落 — 每节需要 purpose / allowed claims / forbidden claims / inputs / validation
- 范围先于完备 — 如果是分阶段写作,先锁定阶段边界
- 动态专家,不设固定池 — 用
professor按失败模式召唤对应专家 - 内容先于语言 — 诊断科学逻辑后再做 anti-slop / 语言打磨
- 不自动升级事实 — 永远不把 "may indicate" 改成 "proves",除非有证据支撑
- 删除胜于解释 — 当某主张不可行,直接删除。正文干净,解释留给答辩
- 该停就停 — 平台期、专家冲突、证据缺失是停止理由,不是润色理由
模式分派
| 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。
项目结构
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)新建项目时按 manifest.yaml 的 templates.on_demand 路由从 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。
Reference 文件索引
完整 reference 按任务需要加载,不要一次性注入全部文件:
| Reference | 加载时机 |
references/compose-mode.md | 模式 = compose(9 步流程) |
references/revise-mode.md | 模式 = revise(9 步流程) |
references/hybrid-mode.md | 模式 = hybrid |
references/evaluation-rubric.md | 使用 8 维 × 4 锚点评分体系时 |
references/research-anti-slop.md | 清理中文 proposal 的模板化和空泛表达时 |
references/chinese-review-writing-style.md | 撰写或修订中文综述时 |
references/stopping-rules.md | 判断继续迭代、拆分范围或停止时 |
references/professor-dispatch.md | 按失败模式分派动态专家时 |
references/foundation-files.md | 建立或修复 foundation 五文件时 |
references/project-structure.md | 初始化项目目录或维护 state.json 时 |
references/export-archive.md | 导出和归档 .md / .docx 时 |
references/partial-proposal-scope.md | 分阶段写作并防止范围蔓延时 |
references/ref-renumbering-cascade.md | 处理参考文献增删和编号级联时 |
references/review-paper-framework.md | 设计综述论文框架时 |
references/review-critique-methodology.md | 建立综述的批判性分析时 |
references/validation-checklist.md | 自动检查主张、引用、编号和可复现性时 |
references/gpt-handoff-revision-brief.md | 生成跨 agent 修订交接简报时 |
references/within-approved-proposal.md | 在已批准的 proposal 框架内扩写时 |
references/worked-example-quaternary-proposal.md | 需要查看完整 foundation 文件填写示例时 |
references/降承诺提案模式.md | 证据不足,需要降低承诺强度时 |
运行交付
每次运行结束时输出:
- 当前文件路径或修订后文本
- 当前分数/状态
- 剩余风险
- 一条建议的下一步
QA Mode — 四层质量保障 Pipeline
当用户说"审查这段/跑 QA/检查方案/过 pipeline"时,进入 QA 模式。
情境挡位
| 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 |
Pipeline 顺序(先内容后语言)
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
└── 文献综述 → 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。
使用方法
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 问题配置你的研究域
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。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

