Note Refine logo

Note Refine

Organization
yuque
note-refine

Polish rough Yuque notes into structured, readable documents while preserving their meaning. Use when the user wants to clean up a draft, improve layout, or turn fragments into a document; trigger phrases include “帮我整理一下这篇笔记”, “把这个文档排版优化一下”, and “polish my notes”.

Overview

Publisheryuque
Repositoryyuque-ecosystem
Skill namenote-refine
Stars
238
Forks
20
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

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

Installation

Install the Note Refine 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/yuque/yuque-ecosystem/tree/main/skills/note-refine
  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/yuque/yuque-ecosystem.git /tmp/yuque-ecosystem
mkdir -p .claude/skills
cp -r /tmp/yuque-ecosystem/skills/note-refine .claude/skills/note-refine
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Note Refine 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 Note Refine 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 Note Refine 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.

Note Refine — Polish Rough Notes into Quality Documents

Transform rough, unstructured notes into well-organized, readable documents. Adds proper headings, table of contents, improves expression, and enhances formatting — all while preserving the original meaning.

When to Use

  • User has a rough draft or messy notes they want to clean up
  • User says "帮我整理一下这篇笔记", "polish my notes", "把这个文档排版优化一下"
  • User wants to improve readability of an existing Yuque document
  • User has bullet points or fragments they want turned into a proper document

Required MCP Tools

All tools are from the yuque-mcp server:

  • yuque_get_doc — Read the original document content
  • yuque_update_doc — Update the document with refined content

Workflow

Step 1: Get the Source Notes

Case A — Yuque document link: Extract repo_id and doc_id from the URL and fetch the content:

Tool: yuque_get_doc
Parameters:
  repo_id: "<namespace>"
  doc_id: "<slug>"

Case B — User pastes text directly: Use the provided text as the source content. No tool call needed.

If the document is not found (404) or permission denied (403), inform the user and stop.

Step 2: Analyze the Current State

Before refining, assess the notes on these dimensions:

DimensionWhat to Check
StructureAre there headings? Is there a logical flow?
CompletenessAre sentences complete? Are there dangling thoughts?
FormattingConsistent use of lists, code blocks, emphasis?
ReadabilityParagraph length, sentence clarity, jargon usage?
OrganizationIs related content grouped together?

Mentally categorize the refinement level needed:

  • Light polish — Good structure, just needs formatting and minor wording fixes
  • Medium refine — Has content but needs reorganization and better headings
  • Heavy restructure — Fragments and bullet points that need to become a proper document

Step 3: Refine the Content

Apply the following improvements while strictly preserving the original meaning:

Structure improvements:

  • Add a clear title if missing
  • Add hierarchical headings (H2, H3) to break content into logical sections
  • Reorder content so related ideas are grouped together
  • Add a brief introduction paragraph if the document jumps straight into details

Expression improvements:

  • Complete sentence fragments into full sentences
  • Fix grammatical errors and typos
  • Replace vague language with precise terms
  • Smooth transitions between sections
  • Keep the author's voice and tone — don't make casual notes sound like academic papers

Formatting improvements:

  • Use bullet lists for parallel items
  • Use numbered lists for sequential steps
  • Use code blocks for code, commands, or technical content
  • Use tables for structured comparisons
  • Use bold for key terms on first mention
  • Use blockquotes for important callouts
  • Ensure consistent formatting throughout

What NOT to change:

  • Do not add new information or opinions not present in the original
  • Do not remove content the author wrote (unless it's clearly a duplicate)
  • Do not change technical terms or proper nouns
  • Do not alter the author's conclusions or viewpoints
  • Do not over-formalize casual notes if the user didn't ask for it

Step 4: Present the Refined Version

Show the user a comparison summary and the refined document:

markdown
## ✨ 笔记优化完成

### 优化概览

| 项目 | 优化前 | 优化后 |
|------|--------|--------|
| 结构 | [e.g., 无标题,纯文本] | [e.g., 3 个章节,层级清晰] |
| 段落数 | X | Y |
| 字数 | ~X 字 | ~Y 字 |

### 主要改动

1. [改动 1:e.g., 添加了三级标题结构]
2. [改动 2:e.g., 将零散要点整合为完整段落]
3. [改动 3:e.g., 统一了列表格式]

---

[完整的优化后文档内容]

Step 5: Save Changes (Optional)

Ask the user: "要把优化后的内容更新到原文档吗?"

If the user confirms and the source was a Yuque document:

Tool: yuque_update_doc
Parameters:
  repo_id: "<namespace>"
  doc_id: "<slug>"
  body: "<refined content in markdown>"

After saving, confirm: "文档已更新:[文档链接]"

If the user wants to keep the original and save as a new version: Inform the user: "语雀会自动保留历史版本,更新后你仍然可以在版本历史中查看原始内容。"

If the source was pasted text: Just present the refined version in chat. If the user wants to save it, ask which knowledge base and use yuque_create_doc.

Guidelines

  • Always answer in the same language as the original notes (Chinese or English)
  • The golden rule: preserve meaning, improve form
  • Show the user what you changed and why — transparency builds trust
  • For light polish, don't over-engineer — sometimes notes just need minor fixes
  • For heavy restructure, confirm the proposed structure with the user before saving
  • If the notes contain TODO items or unfinished thoughts, preserve them as-is (mark with <!-- TODO --> if needed)
  • Respect the author's writing style — don't turn informal notes into formal reports unless asked

Error Handling

SituationAction
Document not found (404)Inform user the document may have been deleted or the link is incorrect
Permission denied (403)Tell user they may lack permission to access or edit this document
Document content is emptyInform user: "该文档内容为空,没有可优化的内容"
yuque_update_doc failsPresent the refined content in chat and suggest the user copy-paste it manually
Content is already well-structuredTell the user: "这篇文档结构已经很清晰了,只做了少量微调" — don't force unnecessary changes
Content is too short (< 50 chars)Inform user the content is too brief to meaningfully refine, ask if they want to expand it instead

Frequently asked questions

What does the Note Refine AI skill do?

Polish rough Yuque notes into structured, readable documents while preserving their meaning. Use when the user wants to clean up a draft, improve layout, or turn fragments into a document; trigger phrases include “帮我整理一下这篇笔记”, “把这个文档排版优化一下”, and “polish my notes”.

Why use Note Refine on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yuque/yuque-ecosystem/tree/main/skills/note-refine. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Note Refine?

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 Note Refine?

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

Is the Note Refine AI skill free?

Yes. It is published on GitHub by yuque 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 👇