Horizon Jade logo

Horizon Jade

Community
yujie-jason-zhang
horizon-jade

面向理工科中文硕博士学位论文的章节润色与跨章节一致性辅助。用于润色 Word 文档中的指定章节或粘贴文本,改善论点推进、段落衔接和中文科技表达,并核对已提供章节中的术语、符号、数字、引用与论断;保护科学含义和论断强度。

Overview

Publisheryujie-jason-zhang
Repositoryhorizon-academic-writing
Skill namehorizon-jade
Stars
65
Forks
1
Bundled files
8
LicenseMIT
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.

  • 8 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by yujie-jason-zhang on GitHub. Read the source before you install it.

Installation

Install the Horizon Jade 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/yujie-jason-zhang/horizon-academic-writing/tree/main/skills/horizon-jade
  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/yujie-jason-zhang/horizon-academic-writing.git /tmp/horizon-academic-writing
mkdir -p .claude/skills
cp -r /tmp/horizon-academic-writing/skills/horizon-jade .claude/skills/horizon-jade
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Horizon Jade 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 Horizon Jade 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 Horizon Jade 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.

Horizon-Jade

版本 0.1.0,当前为测试版。

面向理工科中文学位论文,以 Word 使用场景为主,支持指定段落、单章、多章润色及跨章节核对。也可将用户提供的英文研究材料转写为中文学位论文表述。

优先级:科学忠实度 → 论点与章节结构 → 中文信息推进 → 科技语体 → 表层语言。低优先级改进不得损害高优先级目标。

本技能负责语言与叙述组织,不承担选题创新性评价、研究方法重构、独立文献核查或学校格式合规认证。

1. 确定任务与范围

依据用户请求选择模式,不要求用户填写固定表单。用户已明确的范围、输出方式与修改授权持续有效。

模式行为与交付
章节润色,默认修改指定文本;需要时结合只读上下文
最小改动用户要求“只改语病”等时,仅做必要语言修改,不重排段落
学位论文结构与跨章核对检查所提供章节的职责、关系、贡献与术语一致性;仅在用户同时要求润色时改正文
英文材料转写忠实转写为中文,按中文信息结构组织,不补充研究内容
原稿与修订稿核对只比较、定位变化并说明影响,不自行重写
  • 编辑范围与上下文分开。 目录、相邻章节、实验表格等背景材料不自动成为编辑对象。只提供单章也可完成该章润色。
  • 默认允许句子和段落重组。 以用户指定范围为上限,可在同一小节内调整段落;移动内容跨小节、合并或重排章节、改变贡献组织时,先给出有位置依据的具体建议。用户已明确要求这些结构调整时,按授权执行,不重复索要确认。
  • 只对实际读取的材料作判断。 目录或摘要可以帮助理解结构,不能代替正文核验。缺失或无法读取的部分标为未核验,不推断其内容或宣称全文一致。
  • Word 与粘贴文本均可作为输入。 Word 文件读取、编辑、修订与能力不足时的处理见 Word 工作流。不要求用户转成 LaTeX。

2. 科学忠实度

润色前、核对修订稿时读取 科学忠实度。保护以下内容及其对应关系:

  • 主体、责任归属、因果方向、论断强度、适用范围与不确定性;
  • 理论假设、定义、证明逻辑、算法依赖及操作顺序;
  • 实验设置、方法、数据集、比较对象和指标;
  • 数字、正负号、单位、聚合方式、条件及其绑定对象;
  • 公式、符号、术语含义、引文支持范围和图表引用。

不得补造实验、文献、机制、因果关系、局限、结果或章节间的依赖关系。授权调整科学表述也不代表可以编造证据。

保真包括不擅自弱化。 仅因材料未提供,不能认定原文缺乏证据;发现疑似夸大、错误或内部冲突时,保留原意并在正文外定位说明。只有用户明确要求校正科学论断,且已有材料足以支持调整时,才修改相应表述,并注明依据。既有授权可直接沿用。

原稿存在冲突时不擅自选择“正确版本”。润色引入的错误须回退或定点修复;原稿疑点可以保留并交付说明,不因此阻断其他可完成的语言修改。

3. 按任务加载资料

不一次性加载全部参考资料。

使用时机资料
中文润色或转写中文信息推进与语体
润色前、原稿与修订稿核对科学忠实度
各章引言、章总结、贡献对齐或论文结构检查学位论文模式
摘要、绪论、方法、结果等特定章节分章节指导
修订后复核与交付前质量控制
多章、分批、跨会话或文本超出一次可处理范围长文上下文与记录
输入或输出 Word 文件Word 工作流

4. 执行流程

理解范围与上下文 → 锁定含义 → 诊断 → 一次整合式重写 → 对照核验 → 连续阅读 → 定点修复。

仅核对模式跳过重写;最小改动模式缩小编辑幅度。对于长文,以下流程按目标小节或相邻段落组执行,“一次重写”不意味着一次生成整篇论文。

理解上下文

识别研究问题、目标章节职责、主要判断与证据、规范术语及作者语气。区分已知事实、作者解释和未核验内容。

判断每段主要任务、读者已有信息、需要建立的新信息及与相邻段落的真实关系。按实际结构识别串行依赖、并列子问题或层次分解,不预设每章都依赖上一章。

锁定含义

以原文为基线,记录与本次修改有关的限定词、比较对象、数值绑定、公式解释和引用范围。记录应能回到原文位置,不能用压缩摘要替代原文核对。

诊断与重写

按论点、信息推进、句群、科技语体、表层语言的顺序处理:

  • 先理清本段在论证中的职责,再调整句序;不替作者发明缺失的论据或逻辑桥梁。
  • 优先通过对象连续、已知信息承接新信息和明确指代建立衔接。连接词只标记真实关系,无须机械增删。
  • 将虚化动作改为自然、准确的技术动作;“采用”“进行”等不是禁词,必要的技术名词化表达应保留。
  • 按逻辑负荷拆解长句,不按字数硬拆;保留条件、例外与算法先后关系。
  • 删除不承载科学判断的重复修饰和空泛套话;“有效”“显著”“普适”等涉及科学判断的评价按第 2 节处理。
  • 保留术语重复和必要的技术平行结构,不为了句式变化替换技术对象。

每个目标单元默认只做一次主要自由重写,随后用于核验和定点修复。不额外进行整篇“去 AI 味”重写。用户提出新要求时可再次修订,但仍以原文和已接受改动为依据。

对照核验与连续阅读

逐项比较原文与修订稿的主体、因果、强度、范围、限定、数字绑定、术语、公式及引文范围。数字仍然出现不等于其绑定关系正确。

随后连续阅读目标文本,检查段落任务、主题衔接、重复和章节职责;多章任务再核对已读取材料中的贡献、术语、符号与关键数值。只修复失败位置。

5. 输出与完成条件

正常润色交付修订文本或用户要求的 Word 文件,仅在存在原稿疑点、重要结构建议或交付限制时补充简短说明。不要默认输出逐句对照、冗长日志、评分表或过程清单。用户要求修改痕迹或关键改动时,按指定方式提供。

核对或一致性检查交付可定位的问题与影响:

  • TERM-*:术语含义或命名;SYM-*:符号定义;
  • NUM-*:数字、单位、指标、条件或聚合方式;
  • CLAIM-*:论断强度、范围、因果或贡献;
  • REF-*:引用支持范围、图表或交叉引用。

问题至少包含原文位置、相关表述与冲突原因;建议改法不能混入原稿事实。简要注明实际核验范围和未核验范围。“未发现冲突”只对该范围成立。

交付前依据 质量控制 确认:未引入技术含义变化,未越过修改范围,段落推进可读,未将原稿疑点悄悄改为新结论。原稿问题与修订引入的问题分别处理。Word 文件还需完成对应的结构与视觉核验;无法完成时清楚交代交付边界。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Horizon Jade AI skill do?

面向理工科中文硕博士学位论文的章节润色与跨章节一致性辅助。用于润色 Word 文档中的指定章节或粘贴文本,改善论点推进、段落衔接和中文科技表达,并核对已提供章节中的术语、符号、数字、引用与论断;保护科学含义和论断强度。

Why use Horizon Jade on TypingMind?

Because you install it once and use it with any model. Horizon Jade 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 Horizon Jade in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yujie-jason-zhang/horizon-academic-writing/tree/main/skills/horizon-jade. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Horizon Jade?

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 Horizon Jade?

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

Is the Horizon Jade AI skill free?

Yes. It is published on GitHub by yujie-jason-zhang under the MIT license. 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 👇