Stem Writing Disciplines logo

Stem Writing Disciplines

Community
ahang1598
stem-writing-disciplines

理工与医学学科论文写作专项参考。当用户写工程、计算机、控制、材料、机械、电子、农工、自然科学实验、算法模型,或医学、生物、临床、护理、公共卫生、药学论文,需要学科结构、方法可复现性、实验证据链、图表要求、报告规范、术语规范和学科合规检查时,使用此参考;重点避免把通用论文模板误套到有明确学科规范的理工或医学论文中。人文社科与法学不走本参考,改用同级 `../hss/SKILL.md`。

Overview

Publisherahang1598
Repositorydoubao-workbuddy-qwenwork-skills
Skill namestem-writing-disciplines
Stars
90
Forks
35
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ahang1598 on GitHub. Read the source before you install it.

Installation

Install the Stem Writing Disciplines AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ahang1598/doubao-workbuddy-qwenwork-skills/tree/main/doubao/archive/deleted/2026-08-14-222038/skills/doubao-academic-polish/sub-skills/paper-write-zh/references/stem
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ahang1598/doubao-workbuddy-qwenwork-skills.git /tmp/doubao-workbuddy-qwenwork-skills
mkdir -p .claude/skills
cp -r /tmp/doubao-workbuddy-qwenwork-skills/doubao/archive/deleted/2026-08-14-222038/skills/doubao-academic-polish/sub-skills/paper-write-zh/references/stem .claude/skills/stem-writing-disciplines
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Stem Writing Disciplines in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Stem Writing Disciplines on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Stem Writing Disciplines is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

理工与医学学科写作专项

本参考承载理工科与医学两类学科的高差异写作规则。它是主入口 paper-write-zh/SKILL.md 在 S0 判定为“技术理工”或“医学与生物”分支后的学科规范层,不替代主入口的 S0-S5 阶段门控、S1 文献真实性门控和 S5 状态交付。

通用能力不在本参考重复:文献检索与真实性走 ../literature-search/SKILL.md,文献综述组织走 ../literature-review/SKILL.md,证据图与图表/实验协议走 ../evidence-driven-writing/SKILL.md,章节写作方法走 ../writing-chapters/SKILL.md,中文语言与去 AI 味走 ../writing-core/SKILL.md。本参考只写“理工/医学与其他学科不同”的那部分。

使用时先判断论文所属学科和任务类型,再只读取对应小节;不要把医学结构和术语套到普通理工论文,也不要把理工话语套到医学临床论文。

一、适用范围与分流

命中条件分支读取小节
工程、计算机、控制、材料、机械、电子、农工、自然科学实验或算法模型技术理工第二节
医学、生物、临床、护理、公共卫生、药学医学与生物第三节

法学(法条、判例、司法解释、制度规范)与人文社科(文史哲、政经管社教传艺、马克思主义理论等)不走本参考,改用 ../hss/SKILL.md。学科交叉时按研究方法判定:有实验、基准、模型、算法、临床数据走本参考;有文本、史料、概念辨析、问卷、访谈、法条走 hss。

二、技术理工论文

2.1 学科特点

技术理工论文以问题定义、方法设计、实验验证为核心链条。可信度来自方法可复现、实验证据充分、强判断有边界,而不是宏大叙事或成果宣传。默认建立真实中英文文献池,英文基础文献不可缺位。

2.2 结构选择

类型默认结构
技术类期刊论文题目;摘要;关键词;1 Introduction(通常连续段落,不拆过多小节);2 Related Work;3 Proposed Method;4 Experiments and Results;5 Discussion;6 Conclusion;References
技术类毕业/学位论文摘要;Abstract;第1章 绪论;第2章 相关理论与研究现状;第3章 方法设计;第4章 实验与结果分析;第5章 讨论;第6章 结论与展望;参考文献;致谢(如需要)

期刊论文不默认写成毕业论文六章结构;引言通常以连续段落推进,不默认拆成大量小节。用户提供学校、期刊或导师模板时,模板优先。

2.3 方法章节:可复现与本文决策

  • 方法章节按输入到输出的数据流写,不只罗列模块名称;每个模块说明输入、处理、输出和设计理由。
  • 每个模块必须能说明“本文决策”:为什么选它、放在流程哪个位置、针对本文数据或任务的哪类具体问题、对应哪项实验或图表验证。只能写通用原理时,说明它还是背景介绍,不是本文方法。
  • 公式使用可渲染数学格式,规范见 ../writing-core/SKILL.md 与 ../writing-chapters/SKILL.md 的公式输出小节。

2.4 实验证据链

实验结论可信至少需要部分证据链。缺少材料时不得写“全面验证”“显著优于多种主流算法”“满足工业实时检测需求”等强结论。完整的证据图、实验协议、Mock/PLANNING DATA 边界和图表生成协议见 ../evidence-driven-writing/SKILL.md;本节只固定理工分支必须具备的材料。

检查项必须具备的材料不足时处理
数据划分训练/验证/测试划分方式或样本来源说明标为待补,不写泛化结论
指标定义每个指标的计算公式或定义来源先解释指标用途,不给效果判断
对比基线对比方法名称、来源、参数设置只写计划对比,不写优于基线
结果数值结果表或数值来源,非凭空生成Draft Mode 用 PLANNING DATA,Final Mode 不写“实验结果表明”
可视化/日志训练曲线、检测图、日志或用户说明不把可视化示意写成解释性验证

2.5 图表要求

技术类论文图表数量目标与图占位/表格生成协议以 ../evidence-driven-writing/SKILL.md 为准:期刊论文通常至少 3-5 个图占位、2-4 个表格;毕业/学位论文通常至少 6-8 个图占位、5-7 个表格。YOLO/CV/缺陷检测常用图表清单同样在该参考中给出。本节只提醒:正文提到的每个图表编号都要有内容或明确占位,不写“注:实际论文中需插入”。

2.6 术语与事实核查

  • “最新版本”“当前主流”等表述给出具体版本号或时间边界;无法核实改为限定表达。例如“YOLOv8 是最新版本”改为“YOLOv8 是 YOLO 系列中被广泛使用的版本之一;若讨论最新进展,需结合后续版本或最新文献核验”。
  • 方法全称、指标含义、损失函数名称核对原始论文或权威资料,错误则更正。
  • 数据集描述标注来源,不夸大代表性、样本规模或覆盖范围。
  • “主流选择”“最具代表性”“显著优于”等领域地位判断必须有来源或边界;无法核实改为“已有研究中较常使用”“在本文资料范围内”等限定表达。

2.7 检查清单

  • 已按论文类型选择正确结构,期刊论文未默认套六章。
  • 方法章节有数据流和本文决策,不只罗列模块名。
  • 实验强结论都绑定数据划分、指标、基线、结果或日志。
  • 图表编号都有内容或占位;数量达到目标或已说明缺口。
  • “最新/主流/显著/代表性/全面验证”等强判断有证据或边界。
  • 英文基础文献池已建立,未只用中文文献支撑方法与相关工作。

三、医学、生物与临床论文

3.1 学科特点

医学论文通常采用 IMRaD 结构,并额外强调伦理审批、知情同意、统计方法、研究注册和报告规范。不同研究类型对应不同报告指南:随机对照试验参考 CONSORT,观察性研究参考 STROBE,系统综述参考 PRISMA,诊断准确性研究参考 STARD,病例报告参考 CARE,动物研究参考 ARRIVE。

3.2 专用结构

  • 随机对照试验:引言、方法、随机化与盲法、参与者流程、结果、讨论。
  • 队列/病例对照/横断面研究:研究对象、变量定义、偏倚控制、统计分析、结果。
  • 系统综述/Meta 分析:检索策略、筛选流程、纳入排除标准、质量评价、合并分析。
  • 病例报告:时间线、诊断推理、干预、随访、讨论。

3.3 引用与报告规范

  • 伦理声明应包含批准机构、批准号、知情同意和遵循原则;没有用户提供材料时,不能编造伦理批准号。
  • 临床试验注册号、样本量计算、统计软件和版本必须来自用户材料或明确标为待补。
  • 结果报告优先给出效应量、置信区间和精确 P 值;不要只写“差异显著”。

3.4 术语规范

  • P=0.000 改为 P<0.001。
  • 计量资料需区分正态分布与非正态分布,分别使用均数±标准差或中位数(四分位距)。
  • 分类变量使用例数和百分比;小数位、百分比、置信区间保留位数应全文一致。

3.5 检查清单

  • 研究类型对应的报告规范已选定。
  • 伦理审批、知情同意、注册号和利益冲突状态已说明或标为待补。
  • 统计方法与数据类型匹配。
  • 样本量、纳入排除标准和数据缺失处理有说明。
  • 表格包含必要的基线特征、效应量、置信区间和 P 值。

四、学科附录资源

以下数据库和规范只能作为检索目标或格式依据;需要引用具体文献、病例或指南时,仍必须通过 ../literature-search/SKILL.md 的门控获取页面可见来源,或由用户提供可核验材料,不能用搜索/API 元数据替代。

  • 医学报告规范:EQUATOR Network、CONSORT、STROBE、PRISMA、STARD、CARE、ARRIVE。
  • 临床试验注册:中国临床试验注册中心、ClinicalTrials.gov。
  • 理工与医学英文文献池:优先基础方法原始论文、经典综述、标准指南和近年代表性研究;获取与核验层级见 ../literature-search/SKILL.md。

五、交付提醒

使用本参考后,在回复中简要说明所采用的学科规则、仍缺的材料和需要用户确认的风险点。学科规范不能替代文献真实性、事实准确性和实验证据核查;涉及这些问题时仍应回到主入口 S1 和 ../evidence-driven-writing/SKILL.md、../literature-search/SKILL.md 的门控。

Frequently asked questions

What does the Stem Writing Disciplines AI skill do?

理工与医学学科论文写作专项参考。当用户写工程、计算机、控制、材料、机械、电子、农工、自然科学实验、算法模型,或医学、生物、临床、护理、公共卫生、药学论文,需要学科结构、方法可复现性、实验证据链、图表要求、报告规范、术语规范和学科合规检查时,使用此参考;重点避免把通用论文模板误套到有明确学科规范的理工或医学论文中。人文社科与法学不走本参考,改用同级 `../hss/SKILL.md`。

Why use Stem Writing Disciplines on TypingMind?

Because you install it once and use it with any model. Stem Writing Disciplines is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Stem Writing Disciplines in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ahang1598/doubao-workbuddy-qwenwork-skills/tree/main/doubao/archive/deleted/2026-08-14-222038/skills/doubao-academic-polish/sub-skills/paper-write-zh/references/stem. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Stem Writing Disciplines?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Stem Writing Disciplines?

As many as you like. As long as a model supports skills, you can use Stem Writing Disciplines with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Stem Writing Disciplines AI skill free?

It is published on GitHub by ahang1598. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇