← Back to Skills Marketplace
442
Downloads
1
Stars
1
Active Installs
37
Versions
Install in OpenClaw
/install edu-claw
Description
Interactive English tutor with gamification - 互动式英语学习导师
README (SKILL.md)
Educlaw 多学科 Agent
多Agent学习系统,支持英语、数学等学科,每个学科由独立Agent处理,上下文完全隔离。
功能
- 多学科支持:英语(免费)、数学、语文
- Agent隔离:各科学记忆独立,互不干扰
- 智能路由:自动识别用户意图,路由到对应学科Agent
- 积分系统:完成练习获得积分,持续激励学习
使用方法
直接告诉我想学什么学科:
- "学英语" → 英语Agent
- "学数学" → 数学Agent
- "学语文" → 语文Agent
架构
用户输入 → 意图识别 → Agent路由 → 学科Agent → 回复
- 每个Agent有独立的instruction和memory
- 上下文完全隔离,避免记忆污染
配置
编辑 router/config.yaml 自定义路由规则。
版本
v2.0.1
Usage Guidance
This skill appears to do what it says (multi-agent tutoring) and does not request credentials or external installs, but it intentionally collects and persists basic student information (name, grade, interests) and learning history/points in its router/config.yaml and agent memory. Before installing: (1) confirm where the data will be stored on disk and who can read it; (2) if children are involved, ensure parental consent and avoid entering sensitive PII; (3) clarify the purpose of the hard-coded '管理员账号:xiaohuiing123' in math/agent.yaml and remove or secure any real admin credentials; (4) verify the referenced GitHub/ClawHub links if you want the source provenance; and (5) if you do not want the skill to persist names/interests, edit router/config.yaml and the agent instructions to disable or anonymize that storage.
Capability Analysis
Type: OpenClaw Skill
Name: edu-claw
Version: 2.44.0
The skill bundle implements a multi-agent educational system for English and Math tutoring with a functional routing logic in `router/config.yaml`. While `math/agent.yaml` and `VERSION.md` describe a monetization strategy that directs users to an external contact (ID: xiaohuiing123) for 'authorization' to access certain subjects, there is no evidence of technical malice, data exfiltration, or harmful prompt injection. The collection of student names and grades is contextually appropriate for a personalized tutor and no external network tools or suspicious execution commands are present.
Capability Assessment
Purpose & Capability
Name/description, router, and per-subject agent instructions align: the skill implements an LLM-based router and isolated subject agents (English, Math, future Chinese). There are no unexpected binaries or external service credentials requested.
Instruction Scope
Agent instructions explicitly direct the agents to remember student names, grades, interests and to award points; router/config.yaml contains fields (child_name, child_grade, history, points) for persistent state. This is coherent for a tutoring skill but is a privacy-relevant scope (collection and storage of PII). The math agent also contains an inline '管理员账号:xiaohuiing123' string which looks like an admin username referenced in-flow; its purpose/mechanism is not described and should be clarified.
Install Mechanism
Instruction-only skill with no install spec and no downloaded code. The README suggests a local copy step (cp -r . ~/.openclaw/agents/educlaw) and restarting the gateway, which is a normal local deployment action and matches the skill type.
Credentials
The skill declares no required environment variables, no external endpoints are invoked in the instructions, and no credentials are requested. The only credential-like artifact is the literal '管理员账号:xiaohuiing123' inside math/agent.yaml; it appears to be a static hint and is not declared as a required secret.
Persistence & Privilege
Skill does not request always:true and is user-invocable. It expects to read/write local config (router/config.yaml) and maintain per-agent memory/state (history, points, child info). That is reasonable for tutoring functionality but means personal data will be persisted locally — confirm storage location, retention, and access controls before use.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install edu-claw - After installation, invoke the skill by name or use
/edu-claw - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.44.0
- Updated version to 2.44.0.
- No user-facing feature or documentation changes in this release.
v2.43.0
- Updated agent configurations for English and Math in their respective YAML files.
- No changes to skill documentation or user-facing features.
v2.42.0
- Updated english/agent.yaml and math/agent.yaml with minor adjustments.
- No user-facing feature changes.
- Internal files updated to reflect version 2.42.0.
v2.41.0
- Enhanced documentation: updated SKILL.md with clarified feature descriptions and usage instructions.
- Improved subject support details, specifying English as free and emphasizing individual agent memory isolation.
- Updated router and agent configuration files for alignment with new features and structure.
- Versioning information synchronized across README, SKILL.md, and VERSION.md files.
v2.26.0
- Documentation update: README.md and SKILL.md content aligned for consistency.
- No changes to the code or features; functionality remains the same.
v2.25.0
edu-claw 2.25.0
- 改进 SKILL.md 文档:简化内容,优化功能、使用方法和架构描述
- english/agent.yaml 更新(内容未详述)
- 版本号更新
v2.24.0
- Added VERSION.md file for explicit version tracking.
- No other functional changes.
v2.0.3
**Major update: Now supports multi-subject learning with distinct agents and smart routing.**
- Added multi-agent architecture for English, Math, and Chinese, each with isolated memory.
- Introduced smart routing to automatically send user requests to the appropriate subject agent.
- Upgraded configuration system (now in YAML files).
- Removed legacy file formats and consolidated agent settings.
- Readme and documentation updated to reflect multi-subject and multi-agent features.
v2.2.3
更新中文名称:主动式英语家教
v2.2.2
Added Chinese version to SKILL.md with GitHub and Gitee links
v2.2.1
Added Chinese README with GitHub and Gitee links
v2.2.0
Added full features: personalization, interest-based learning, emotional support, parent reports, reward system
v2.1.4
Added GitHub and Gitee links to README and skill.json
v2.1.3
Removed all personal info collection descriptions
v2.1.2
Added safety info to skill.json
v2.1.1
Simplified README, removed privacy-related descriptions
v2.1.0
Full English version with all features, avoid storage keywords
v2.0.2
纯英文版,无中文,删除所有暗示存储的词
v2.0.1
极简版,删除所有信息收集描述
v2.0.0
完全重构,极简版,移除所有敏感内容
Metadata
Frequently Asked Questions
What is EduClaw - 主动式英语家教?
Interactive English tutor with gamification - 互动式英语学习导师. It is an AI Agent Skill for Claude Code / OpenClaw, with 442 downloads so far.
How do I install EduClaw - 主动式英语家教?
Run "/install edu-claw" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is EduClaw - 主动式英语家教 free?
Yes, EduClaw - 主动式英语家教 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does EduClaw - 主动式英语家教 support?
EduClaw - 主动式英语家教 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created EduClaw - 主动式英语家教?
It is built and maintained by huiing (@xiaohuiing); the current version is v2.44.0.
More Skills