Daily Capture logo

Daily Capture

Organization
yuque
daily-capture

Capture fleeting ideas in Yuque and periodically organize them into structured thematic notes. Use when the user wants to jot down or review fragments; trigger phrases include “记一下”, “随手记”, “整理一下我最近的想法”, “capture this”, and “organize my captures”.

Overview

Publisheryuque
Repositoryyuque-ecosystem
Skill namedaily-capture
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 Daily Capture 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/daily-capture
  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/daily-capture .claude/skills/daily-capture
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Daily Capture 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 Daily Capture 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 Daily Capture 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.

Daily Capture — Fleeting Ideas to Structured Notes

Capture random thoughts, inspirations, and fragments throughout the day. Periodically organize and merge them into structured thematic notes saved to your Yuque knowledge base.

When to Use

  • User wants to quickly jot down an idea or thought
  • User says "记一下", "随手记", "我有个想法", "capture this", "先记着"
  • User wants to review and organize accumulated captures
  • User says "整理一下我最近的想法", "把碎片笔记归类", "organize my captures"

Required MCP Tools

All tools are from the yuque-mcp server:

  • yuque_search — Search for existing capture documents or thematic notes
  • yuque_get_doc — Read existing capture log or thematic notes
  • yuque_create_doc — Create new capture log or thematic notes
  • yuque_update_doc — Append to capture log or update thematic notes
  • yuque_list_books — List knowledge bases to find the target repo

Workflow

Phase A: Quick Capture

When the user shares a fleeting idea or thought:

Step 1: Receive the Input

Accept the user's input as-is. It can be:

  • A sentence or fragment
  • A question they want to explore later
  • A link with a brief comment
  • A random observation or insight
Step 2: Classify the Capture

Assign a lightweight tag based on content:

TagWhen to Use
💡 想法Original ideas, hypotheses, "what if" thoughts
📌 待办Things to do or follow up on
🔗 参考Links, references, things to read later
💬 摘录Quotes or snippets from conversations
❓ 问题Questions to research or think about
🎯 灵感Creative sparks, project ideas
Step 3: Append to Capture Log

Find or create a daily capture log document:

Tool: yuque_search
Parameters:
  query: "每日碎片 YYYY-MM-DD"
  type: "doc"

If no log exists for today, create one:

Tool: yuque_create_doc
Parameters:
  repo_id: "<target namespace>"
  title: "📝 每日碎片 — YYYY-MM-DD"
  body: "<capture log template>"

If the log exists, append the new capture:

Tool: yuque_update_doc
Parameters:
  repo_id: "<namespace>"
  doc_id: "<slug>"
  body: "<existing content + new capture entry>"

Each capture entry format:

markdown
### [HH:MM] [Tag] 简短标题

[用户的原始内容]

---

Confirm to the user: "已记录 ✅ — [tag] [简短标题]"

Phase B: Organize and Merge

When the user asks to organize their captures, or when there are enough accumulated entries:

Step 1: Gather Recent Captures

Search for recent capture logs:

Tool: yuque_search
Parameters:
  query: "每日碎片"
  type: "doc"

Fetch the content of recent capture logs (last 7 days or as specified by the user).

Step 2: Analyze and Group

Read through all captures and group them by theme:

  1. Identify themes — Find captures that relate to the same topic, project, or idea
  2. Detect connections — Note captures that build on each other or are complementary
  3. Flag actionable items — Separate TODO items from reflective thoughts

Present the grouping to the user:

markdown
## 📊 碎片整理预览

过去 [N] 天共 [X] 条碎片,归为 [Y] 个主题:

### 主题 1:[主题名称]([N] 条相关)
- [碎片摘要 1]
- [碎片摘要 2]
- [碎片摘要 3]

### 主题 2:[主题名称]([N] 条相关)
- [碎片摘要 1]
- [碎片摘要 2]

### 🔮 未归类([N] 条)
- [碎片摘要]

要把哪些主题合并成正式笔记?
Step 3: Generate Thematic Notes

For each theme the user confirms, generate a structured note:

markdown
# [主题标题]

> 📅 整理自 YYYY-MM-DD ~ YYYY-MM-DD 的碎片笔记
> 📝 包含 [N] 条相关想法

## 核心想法

[将相关碎片整合成连贯的叙述,保留原始洞察]

## 关键要点

1. **[要点 1]**:[展开说明]
2. **[要点 2]**:[展开说明]
3. **[要点 3]**:[展开说明]

## 待探索

- [ ] [从碎片中提取的待办或待研究项]
- [ ] [延伸问题]

## 原始碎片

<details>
<summary>查看原始记录</summary>

[按时间排列的原始碎片内容]

</details>
Step 4: Save Thematic Notes
Tool: yuque_create_doc
Parameters:
  repo_id: "<target namespace>"
  title: "[主题标题]"
  body: "<structured thematic note>"

Confirm: "主题笔记「[主题标题]」已保存到「[知识库名称]」:[文档链接]"

Guidelines

  • Always answer in the same language the user used (Chinese or English)
  • Quick capture should be instant — don't over-process, just record and confirm
  • Preserve the user's original wording in captures — don't rephrase their thoughts
  • When organizing, respect the user's intent — ask before merging if themes are ambiguous
  • Don't force organization — some captures are standalone and that's fine
  • The "未归类" category is valid — not everything needs a theme
  • Suggest organizing when captures accumulate (e.g., > 15 unorganized items)

Error Handling

SituationAction
Document not found (404)Create a new capture log for today
Permission denied (403)Tell user they may lack permission to access or edit this document
Target repo not foundList user's repos with yuque_list_books and ask them to pick one
yuque_create_doc failsPresent the capture/note in chat and suggest manual saving
No captures found for organizationInform user: "最近没有找到碎片记录,先随手记几条吧!"
Capture content is emptyAsk user: "你想记录什么?"

Frequently asked questions

What does the Daily Capture AI skill do?

Capture fleeting ideas in Yuque and periodically organize them into structured thematic notes. Use when the user wants to jot down or review fragments; trigger phrases include “记一下”, “随手记”, “整理一下我最近的想法”, “capture this”, and “organize my captures”.

Why use Daily Capture on TypingMind?

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

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

Which AI models can use Daily Capture?

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 Daily Capture?

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

Is the Daily Capture 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 👇