From yuque-personal
Refines rough notes into structured documents with headings, improved phrasing, and formatting via Yuque tools. Handles links or pasted text; preserves original meaning for personal use.
npx claudepluginhub yuque/yuque-ecosystem --plugin yuque-personalThis skill uses the workspace's default tool permissions.
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.
Refines scattered Yuque notes into organized, deduplicated, enriched documents via yuque-mcp tools. Searches repos/docs, analyzes themes/duplicates, restructures for personal knowledge bases.
Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to format markdown, beautify article, add formatting, or improve layout. Outputs {filename}-formatted.md.
Mechanically tightens prose by restructuring sections by dependency order, splitting/merging paragraphs, and removing redundancy. Use to compress READMEs, ADRs, plan files, design docs without changing voice, tone, or phrasing.
Share bugs, ideas, or general feedback.
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.
All tools are from the yuque-mcp server:
yuque_get_doc — Read the original document contentyuque_update_doc — Update the document with refined contentCase 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.
Before refining, assess the notes on these dimensions:
| Dimension | What to Check |
|---|---|
| Structure | Are there headings? Is there a logical flow? |
| Completeness | Are sentences complete? Are there dangling thoughts? |
| Formatting | Consistent use of lists, code blocks, emphasis? |
| Readability | Paragraph length, sentence clarity, jargon usage? |
| Organization | Is related content grouped together? |
Mentally categorize the refinement level needed:
Apply the following improvements while strictly preserving the original meaning:
Structure improvements:
Expression improvements:
Formatting improvements:
What NOT to change:
Show the user a comparison summary and the refined document:
## ✨ 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]
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.
<!-- TODO --> if needed)| Situation | Action |
|---|---|
| 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 empty | Inform user: "该文档内容为空,没有可优化的内容" |
yuque_update_doc fails | Present the refined content in chat and suggest the user copy-paste it manually |
| Content is already well-structured | Tell 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 |