agent-teacher
教授新 agent 掌握工作室基础能力的技能。触发时机：(1) 创建新 agent 后需要初始化配置时 (2) 教现有 agent 掌握某项技能时 (3) 新 agent 上岗培训。课程分"行为准则→基础→进阶"三大类，行为准则必须优先于一切技能学习。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/axelhu/agent-teacherWhat This Skill Does
The agent-teacher skill is an essential framework for onboarding, training, and maintaining the operational integrity of agents within the OpenClaw ecosystem. It acts as the primary instructor for new agents, ensuring they are fully aligned with the studio's culture, workflows, and technical standards. The skill enforces a strict curriculum hierarchy, emphasizing that behavior and ethics (Rules of Conduct) take precedence over technical proficiency. By automating the instruction process, it ensures that every agent in your studio starts with the same foundational knowledge, reducing the risk of errors and operational silos.
Installation
To add the teacher capability to your environment, use the following command:
clawhub install openclaw/skills/skills/axelhu/agent-teacher
Ensure that you have sufficient permissions to modify the workspace directory of the target agents, as this skill performs file-based installation of sub-skills and configuration templates.
Use Cases
- New Agent Initialization: Standardizing the onboarding process for freshly created agents to ensure they are immediately productive.
- Upskilling Existing Agents: Transitioning an agent from basic task-handling to specialized roles by introducing advanced modules like browser-automation or external API integrations.
- Compliance Reinforcement: Regularly refreshing agent knowledge regarding behavior and studio conduct, especially after system updates or policy changes.
Example Prompts
- "教 zero-producer 上岗培训，请严格按照课程体系执行。"
- "新 agent 上岗，请从行为准则开始教学，完成确认后进行基础技能安装。"
- "给 programmer 补课，重点复习行为准则中关于隐私的部分，并检查基础技能掌握情况。"
Tips & Limitations
- Prioritize Rules: Never bypass the 'Rules of Conduct' section. An agent that lacks ethical alignment is dangerous, regardless of its technical capabilities.
- Avoid Duplication: The teaching algorithm is designed to recognize existing knowledge; if an agent has already mastered a skill, the system will optimize by focusing on refinement rather than re-instruction.
- Environment Requirements: Ensure the target agent workspace (
/home/axelhu/.openclaw/workspace/[agent-name]) exists before initiating the teaching process. The skill relies on standard Unix file structures to deploy configurations correctly.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-axelhu-agent-teacher": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
Openclaw Sleep
Skill by axelhu
superpowers-overview
Use when starting any development work or when unsure which superpowers development skill to use - provides entry point and navigation to the full superpowers skill suite for OpenClaw agents
superpowers-subagent-dev
Use when executing implementation plans with independent tasks - coordinates task execution by dispatching subagents per task with verification checkpoints, adapted for OpenClaw's isolated session model
contacts
通讯录查询与维护技能。用于查找联系人信息（open_id、chat_id、account_id 等）、记录新联系人、或查询历史沟通偏好。触发时机：(1) 需要 @某人或向某渠道发消息时 (2) 认识新联系人后需要录入通讯录时 (3) 查询某人的联系方式或交流偏好时 (4) 询问"谁知道xxx的飞书ID"或"怎么联系xxx"时。
superpowers-executing-plans
Use when executing a written implementation plan in the current session with sequential task execution and review checkpoints - for when subagent-driven mode is not available