Stc logo

Stc

Organization
daimonia-ai
stc

STC(Simplified Technical Chinese,简明技术性中文):写、改写或审阅自然、简短、准确的中文。用户要求中文审阅、精简表达、删除多余说明、统一术语或整理任务回执时使用。项目启用 STC 默认输出规则时,中文输出均适用。

Overview

Publisherdaimonia-ai
RepositorySTC-Simplified-Technical-Chinese
Skill namestc
Stars
115
Forks
2
Bundled files
43
LicenseCC-BY-4.0
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.

  • 43 bundled files

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

  • Open source

    Published by daimonia-ai on GitHub. Read the source before you install it.

Installation

Install the Stc 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/daimonia-ai/STC-Simplified-Technical-Chinese/tree/main
  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/daimonia-ai/STC-Simplified-Technical-Chinese.git \
  .claude/skills/stc
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Stc 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 Stc 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 Stc 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.

STC 简明技术性中文

本 skill 按规范生成、改写和审阅中文。默认表达自然、简短、准确,同一个意思使用同一个词。规则在 rules/,词表在 dictionary/,路径都相对于本 skill 所在的目录。

默认表达方式

每次使用 STC,都必须同时执行以下要求:

  • 用完整句子和自然语序,直接回答问题或交付结果。
  • 删除客套、重复和无关解释,信息足够时停止。
  • 保留事实、数字、名称、否定词、权限和真实不确定性。
  • 根据任务展开。完整文稿和详细说明必须满足用户要求。
  • 交付成品时,从采用的结果写起;制作与复核记录放在内部。
  • 任务回执按 for chat 的 C10 分成“做完了”“需要你”“知会”,把用户动作单独列出。

这些要求内置于 STC,具体规则为 G14、G15、G20、G21、G22,以及当前场景的规则。

安装后的首次使用

用户选择通过链接使用时,读取 WEB.md,按网页引导确认规则读取情况和生效范围。

安装后的引导必须按 ONBOARDING.md 执行:提供默认使用选项和文档审阅体验,等待用户选择。

用户可以提供材料,也可以授权 agent 从当前项目挑选一份文档。审阅范围和修改动作以用户授权为准。

第一步:判断场景

动笔前先判断这次写的是哪类文字。按读者和用途判断:

读者和用途场景规则文件
正在对话的人,读 agent 的回复for chatrules/for-chat.md
人,读来理解内容或照着操作:报告、方案、手册、周报、会议纪要、代码注释、提交说明for documentrules/for-document.md
产品的用户,在网页或应用界面上看到:按钮、标签、提示、报错、通知、空状态for web devrules/for-web-dev.md
agent,读来照着执行:系统提示词、AGENTS.md、CLAUDE.md、skill、给 agent 的工作流程for instruction writingrules/for-instruction-writing.md
  • 一次任务包含几类文字时,必须对每一类文字分别判断。例如一份需求文档按 for document 写,文档里给出的按钮文字按 for web dev 写。
  • 读者和用途都判断不清时,按读者判断:读者是模型,用 for instruction writing;读者是产品用户,用 for web dev;其余用 for document。
  • 场景选择用于内部执行。用户询问方法或判断存在分歧时,再说明所用规则。

第二步:读规则和词表

  1. 读 rules/for-all.md。通用规则对所有场景都适用。
  2. 读第一步选定的场景文件。场景规则和通用规则不一致时,以场景规则为准。
  3. 读 dictionary/avoid.yaml。只用 profiles 字段为空或包含当前场景的条目。
  4. 写界面文字,或写警告、注意、说明这类提醒时,读 dictionary/recommended.yaml,动作词和提醒级别照表里的意思用。
  5. 项目里有术语表时(文件名通常含 terms 或“术语”),必须照术语表写名称。

第三步:按用法处理

按用户请求生成、改写或审阅文字。

写

按规则写出文字,再完成语义复核。

改写

改写用户给的文字,保留原意:

  • 必须保留原文的事实、数字、专有名称和引语。
  • 必须保留表示把握程度的词:可能、也许、大概、通常。
  • 程度词必须换成数字。原文和上下文里没有这个数字时,不得编造数字。这时删掉程度词,或写成“【待补:提升了多少】”,并在改写结果后列出所有待补项。原因:编出来的数字比含糊的形容词危害更大。
  • 交付用户请求的内容。用户要求解释,或改动会影响使用判断时,再说明主要改动与依据。

审查

审查用户指定的材料。先给报告和具体改法;用户要求改写时再给修改稿,写回文件按用户已有授权执行。

报告必须按以下顺序写:

  1. 用一句话说明主要问题,区分需修改项与待确认项。
  2. 按原句分组,给出位置、原句、问题原因和具体改法。规则编号放在说明后面。
  3. 单独列出需要用户补充的事实。缺少的数据和主体名称必须用“【待补:…】”标记。
  4. 用户可以选择采用哪些改法。已选定的修改可以直接执行,不必再次询问。

汇报审阅任务的执行结果时,按 C10 写回执。审阅报告本身使用本节的结构。

不得直接把命令输出的逐行诊断当作交付报告。机器输出是审阅依据;agent 必须结合上下文判断指代、术语、事实和句意。警告只有经上下文确认后才能判定为问题。

检查命令默认提供可读报告。--format markdown 可生成 Markdown 报告;--json 为程序和 agent 提供结构化依据。

第四步:自查

普通对话按 C8 在发出回复前自查。对本次任务内写出的文件或用户指定的材料,能运行 Node.js 18 以上版本时,使用检查命令:

bash
node <本 skill 目录>/tools/cli.mjs check <文件> --profile <场景> --anti-echo

用 npx @daimonia/stc init 安装时,本 skill 目录是 .claude/skills/stc/。文字不在文件里时,可以通过标准输入传给检查命令。检查命令报的错误必须全部改掉。Anti-Echo 疑点必须结合读者和页面复核:删除多余内容,或为必要内容记录具体保留理由。复核文件的格式见 tools/README.md。文本变动后必须重新核对。其他警告宜逐条判断。

语义复核

交付前必须逐项检查:

  • 每句话都帮助当前读者理解、判断或操作;多余排除、制作说明和自证已删除(G20)。
  • 页面实际显示的标题、正文、按钮、提示、图注和角标均已逐项审阅(W9)。
  • 同一个东西只用了一个叫法(G1)。
  • 没有“进行、加以、予以、作出、开展”加名词(G4)。
  • 程度词和模糊量词已换成数字或具体事实;数据均有原文或上下文依据(G5)。
  • 没有营销词、行话、套话和口号句式(G6、G7)。
  • 一句只讲一件事,一句不超过 40 个字(G9、G12)。
  • 表示把握程度的词没有被删掉(G15)。
  • 句子自然、语法完整,长短随内容变化(G21)。
  • 篇幅满足任务,必要步骤和风险信息没有被压掉(G22)。
  • 对话没有重复结论、工具旁白或不必要的模板(C7、C8、C9)。
  • 任务回执分清完成结果、用户动作和知会;用户动作有真实依据,交付物有入口(C10)。
  • 人称符合场景:for document 和 for web dev 里没有“我们”“你们”;for web dev 里也没有“他”“她”“它”“大家”(D1、W1)。
  • for instruction writing 里,强度词只有“必须、不得、宜、不宜、可、不必、能、不能”(I1)。
  • 数字用阿拉伯数字并带单位;中文与英文、数字之间有空格(G18、G19)。

不改动的内容

  • 引语和用户的原话,包括其中的人称。
  • 代码、命令、文件路径、接口名。
  • 品牌口号、法律文本。
  • 英文文字。STC 只管中文;英文可以参照 ASD-STE100。

参考

  • 规则总览与编号一览:rules/README.md
  • 词表格式与类别:dictionary/README.md

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 Stc AI skill do?

STC(Simplified Technical Chinese,简明技术性中文):写、改写或审阅自然、简短、准确的中文。用户要求中文审阅、精简表达、删除多余说明、统一术语或整理任务回执时使用。项目启用 STC 默认输出规则时,中文输出均适用。

Why use Stc on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/daimonia-ai/STC-Simplified-Technical-Chinese/tree/main. 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 Stc?

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 Stc?

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

Is the Stc AI skill free?

Yes. It is published on GitHub by daimonia-ai under the CC-BY-4.0 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 👇