← 返回 Skills 市场
buiphuc

Daily Tutor

作者 buiphuc · GitHub ↗ · v1.0.4 · MIT-0
cross-platform ✓ 安全检测通过
94
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install daily-tutor
功能描述
Get new study items for any subject. Use when: user asks for a daily lesson or new learning content. Supports any data format (language vocab, math formulas,...
使用说明 (SKILL.md)

Daily Tutor Skill

📖 For full user instructions, data setup guides, and Quizbuild MCP configurations, please read the Official README on GitHub.

This skill retrieves new learning items from the user's study list (data/data.json) that they have not learned yet. It works with any subject — the data structure is automatically detected.

When to Use

USE this skill when:

  • The user asks for their daily lesson.
  • The user wants to learn new vocabulary, formulas, concepts, or any study content.
  • The daily cron job asks for new items.

Data Format

Place your study data in data/data.json as a JSON array. Each item can have any fields you want — the script will auto-detect and display them all. There is no fixed schema; you define the fields that make sense for your subject.

For example formats, see references/EXAMPLES.md.

Optional Configuration

Edit data/config.json to customize behavior (all fields optional):

{
  "primary_key": "word",
  "num_items": 10,
  "subject_name": "Hiragana/Katakana N5"
}
Field Default Description
primary_key First key of first item Field used to track progress
num_items 10 Number of items per session
subject_name (none) Display name for the subject

Commands

# Get new items (automatically prevents duplicates)
python3 ${OPENCLAW_SKILL_ROOT}/scripts/get_words.py

How to Handle Output

The output of get_words.py will be a raw list of items with all their fields. When you receive the output:

  1. Process the items exactly as instructed by the user's prompt or the automated Cron job orchestrating this skill.
  2. OPTIONAL: If you have access to the quizbuild tool, you can generate a short practice quiz based on the newly retrieved study items. When calling quizbuild__auto_create_exam, you follow this parameter structure:
{
  "title": "Quick Review Practice Exam",
  "questions": [
    {
      "content": "Question goes here?",
      "type": "multiple_choice",
      "answers": [
        {"content": "Answer 1", "correct": true},
        {"content": "Answer 2", "correct": false}
      ]
    }
  ]
}

If you do not have quizbuild, simply list out the practice items and act as a friendly tutor!

File Structure

File Purpose
data/data.json Study data (required)
data/config.json Configuration (optional)
data/learned_items.json Progress tracking (auto-generated)
scripts/get_words.py Main script
references/EXAMPLES.md Data formatting examples
安全使用建议
This skill appears coherent and low-risk: it only needs python3 and operates on local files (data/data.json, data/config.json, data/learned_items.json). Before installing, check that your study data does not include sensitive information (it will be recorded into learned_items.json). If you do not want any network interactions, do not configure the optional `quizbuild` MCP integration (that requires you to place an API token in your OpenClaw config). If you want extra assurance, review scripts/get_words.py (it contains only local file reads/writes and random sampling).
能力评估
Purpose & Capability
Name/description (provide daily study items, avoid repeats) matches what is present: a small Python script that reads data/data.json, selects new items, and writes data/learned_items.json. The only required binary is python3, which is appropriate.
Instruction Scope
SKILL.md instructs running scripts/get_words.py and optionally using a separate MCP `quizbuild` tool if configured. The runtime instructions and script operate on local files under the skill directory; they do not read unrelated system files or environment variables.
Install Mechanism
There is no install spec or external download; the skill is instruction-only with an included Python script and data files. Nothing is fetched from external URLs during install.
Credentials
The skill requests no environment variables or credentials. README documents an optional MCP integration that would require the user's Quizbuild token in their OpenClaw config — that is optional and user-supplied, not required by the skill.
Persistence & Privilege
always:false (default). The script creates/updates data/learned_items.json in the skill directory to track progress, which is expected and scoped to the skill; it does not modify other skills or system-wide configs.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install daily-tutor
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /daily-tutor 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.4
daily-tutor 1.0.4 - Removed requirement to present output in Vietnamese. - Updated instructions to be language-agnostic when handling new study items. - No changes to commands, configuration, or workflow.
v1.0.3
- Updated skill metadata emoji to 📚. - Bumped version number to 1.0.3.
v1.0.2
- Added a prominent link to the Official README on GitHub for complete user instructions and setup details. - No changes to functionality or configuration; documentation update only.
v1.0.1
- Removed instructions about modifying quiz URLs from the documentation. - Simplified the quiz creation steps and clarified fallback if "quizbuild" is not available.
v1.0.0
- Initial release of the Daily Tutor skill. - Retrieve new, never-repeated study items from a user's custom data list across any subject. - Auto-detects data structure with no fixed schema required. - Tracks user progress and prevents duplicates. - Allows easy configuration of primary key, session size, and subject name via config file. - Supports optional quiz generation if integrated with quizbuild.
元数据
Slug daily-tutor
版本 1.0.4
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 5
常见问题

Daily Tutor 是什么?

Get new study items for any subject. Use when: user asks for a daily lesson or new learning content. Supports any data format (language vocab, math formulas,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 94 次。

如何安装 Daily Tutor?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install daily-tutor」即可一键安装,无需额外配置。

Daily Tutor 是免费的吗?

是的,Daily Tutor 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Daily Tutor 支持哪些平台?

Daily Tutor 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Daily Tutor?

由 buiphuc(@buiphuc)开发并维护,当前版本 v1.0.4。

💬 留言讨论