Shenlun Dawenti logo

Shenlun Dawenti

Community
coffe-d
shenlun-dawenti

申论大作文批改与训练:袁东体系(累进四类文评分、双主题 AB/ABC 型模板、 标题等式、开头 6 种写法、分论点 5 步走、结尾 3 步走),并含无题干时的通用文章评改模式。 **重要:用户只要涉及申论大作文——议论文、文章写作、自选角度作文,或提交作文要求 批改、评分、看有没有偏题、要范文——都必须使用本 skill。** 覆盖关键词:申论、大作文、议论文、文章写作、自选角度、范文、批改、评分、 立意、偏题、跑题、分论点、总论点、袁东、标题、开头、结尾、卷面分。 图片输入(作文照片)由 shenlun-router 处理。

Overview

Publishercoffe-d
RepositoryShenlun.skill
Skill nameshenlun-dawenti
Stars
242
Forks
21
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by coffe-d on GitHub. Read the source before you install it.

Installation

Install the Shenlun Dawenti 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/coffe-d/Shenlun.skill/tree/master/skills/shenlun-dawenti
  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/coffe-d/Shenlun.skill.git /tmp/Shenlun.skill
mkdir -p .claude/skills
cp -r /tmp/Shenlun.skill/skills/shenlun-dawenti .claude/skills/shenlun-dawenti
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shenlun Dawenti 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 Shenlun Dawenti 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 Shenlun Dawenti 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.

申论大作文(袁东体系)

本 skill 只管大作文。小题见 shenlun-xiaoti;图片输入、真题识别、错题库、导出见 shenlun-router。

第一原则:文无定式。 袁东的公式只是想不出怎么写时的备用工具——用户有更好的衔接过渡/结构就用更好的,不因偏离公式扣分。批改永远先看「论证是否成立、结构是否自洽」,再看「像不像公式」。


一、批改规则(袁东阅卷口径)

必须读名师库:references/yuan-dong-methodology.md(第零节两档体系、6.5 双主题模板、7.5 问题对策型)。本文件不重复其内容。

⛔ 第一动作(强制,不得跳过):判主题类型 → 判 AB/ABC 型

单主题(1关键词)→ 多维度展开
双主题(2关键词)→ 再判:
  ├─ AB型  :A、B 互为对象(如"守正与创新")
  └─ ABC型 :A、B 共同作用于大目标 C(如"现代与传统"→社会文明)
             判据:题干有第三个"大目标"性质的词(共同富裕/社会文明/乡村振兴…)
多主题(一般3个)→ 打组合拳
两路式("缺A会…/缺B会…/A+B会…")→ 见名师库 6.5

再按对应模板逐段核对(模板见名师库 6.5):AB型 A→B/B→A/A+B;ABC型 A→C/B→C/A+B→C;两路式 缺A/缺B/A+B。

另需判文体:政论文(论影响)/策论文(论对策)/议论文(对策+影响)。

⛔ 禁止事项

禁止用"分分总/总分总/并列式/递进式"等通用文章学术语下判语——与袁东的双主题模板不对应,会直接误判(实例:ABC 型的 A+B→C 被读成"总结段、重复前两段")。

须用「主题类型 + 模板层次」说话: ❌"结构是分分总,第三段是总结" → ✅"用的是 ABC 型,但第4段作为 A+B→C 这一层段内自我重复"。

评分:袁东累进四类文(来源:26 专项班讲义)

档次分数判据
一类文30-40二类文基础 + 分论点论证写得好
二类文20-30三类文基础 + 开头、结尾写得好
三类文10-20标题 + 开头(前+后)+ 总论点 + 分论点正确
四类文0-10跑题

动作顺序:① 判主题类型与 AB/ABC 型(强制)→ ② 判跑题 → ③ 按模板逐段核对 → ④ 开头结尾 → ⑤ 分论点论证 → 定档给分。

"框架正确"指结构自洽、论点立得住,不是"符合公式";四类文的判据是跑题,不是"没按公式写"。

分值未知时:默认按 40 分计并标注"如实际为 35 分请告知,我按比例重算"。不得只给得分率或 100 分制。


二、无题干时的兜底评改模式

触发:用户提供不了题干(已由 shenlun-router 索取过)。不套真题采分点,改按"一篇议论文"评。

三条底线:

  1. 不输出"立意判定:准确/偏题"——无题干时"是否扣题"无从判断
  2. 只评文章内在自洽:论点是否明确、论点与标题是否一致、论据是否支撑论点、论证是否连贯
  3. 结果必须换算成真实分值(35/40 分),不得只给 100 分制

评分五维:论点明确性 25% + 论据贴合度 30% + 结构条理 20% + 语言表达 15% + 卷面分 10%

完整规则(评改四问、换算对照表、卷面分锚点与三项纪律)见 references/fallback-eval-rules.md。


三、反馈输出

「语言表达」:不做错别字检查;只判断是否影响语义传达;扣分时只给可替换的规范表述。

输出顺序(改进建议优先,不做诊断):

  1. 必须补的失分点(2-3 个,各附"影响哪个维度 + 怎么改")
  2. 表述升级(口语化 → 申论规范表述,见 ../shared/references/expression-upgrade-rules.md)
  3. 成语与名言可用之处
  4. 论证思路怎么改(分论点怎么改、材料怎么用、尾段怎么升华)
  5. 优化示范(挑 1-2 句改写对比)

格式模板见 ../shared/references/expression-upgrade-rules.md 第六节。


四、名师库索引

文件内容
references/yuan-dong-methodology.md袁东大作文(据 26 专项班讲义重建):第零节两档体系与第一原则;第一节阅卷规则/三种文体/主题类型/标题等式/开头 6 种写法/分论点模板/论证 5 步走/结尾 3 步走;第二节待核实项;7.5 问题对策型论证;第十、十一节范文验证与进阶档技法
references/fallback-eval-rules.md无题干兜底评改(四问、换算、卷面分)

五、批改收尾(不得跳过)

批改完成后必须走一遍 shenlun-router 的错题库流程:记录本次失分点类型、更新计数、 若累计 ≥2 则给出复发提醒。规则见 ../shared/references/error-bank-rules.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 Shenlun Dawenti AI skill do?

申论大作文批改与训练:袁东体系(累进四类文评分、双主题 AB/ABC 型模板、 标题等式、开头 6 种写法、分论点 5 步走、结尾 3 步走),并含无题干时的通用文章评改模式。 **重要:用户只要涉及申论大作文——议论文、文章写作、自选角度作文,或提交作文要求 批改、评分、看有没有偏题、要范文——都必须使用本 skill。** 覆盖关键词:申论、大作文、议论文、文章写作、自选角度、范文、批改、评分、 立意、偏题、跑题、分论点、总论点、袁东、标题、开头、结尾、卷面分。 图片输入(作文照片)由 shenlun-router 处理。

Why use Shenlun Dawenti on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coffe-d/Shenlun.skill/tree/master/skills/shenlun-dawenti. 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 Shenlun Dawenti?

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 Shenlun Dawenti?

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

Is the Shenlun Dawenti AI skill free?

Yes. It is published on GitHub by coffe-d 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 👇