training-manager
Manage and optimize your OpenClaw training workspace -- scaffold files, generate skills, log training sessions, and validate workspace structure.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/anova44/openclaw-training-managerWhat This Skill Does
The training-manager skill acts as the central control plane for your OpenClaw agent’s development lifecycle. It automates the maintenance of your agent's core cognitive files (SOUL.md, AGENTS.md, etc.), handles the scaffolding of new skill directories, and provides an interactive onboarding flow for new users. By centralizing workspace management, it ensures that your agent’s personality, operational rules, and historical logs remain structured and compliant with the OpenClaw architecture.
Installation
To install this skill, use the clawhub command-line interface provided in your OpenClaw installation:
clawhub install openclaw/skills/skills/anova44/openclaw-training-manager
Once installed, ensure your OPENCLAW_WORKSPACE environment variable is correctly configured to point to your preferred directory, or allow the skill to default to ~/.openclaw/workspace/.
Use Cases
- New Agent Onboarding: Quickly bootstrap a fresh environment using the interactive setup command, ensuring that IDENTITY.md and USER.md are populated with user-specific data.
- Behavioral Tuning: Regularly update AGENTS.md or SOUL.md when you want to shift the agent's tone or operational priorities without manually editing raw files.
- Session Logging: Maintain a consistent history of agent training sessions via automatically managed
memory/YYYY-MM-DD.mdlogs, helping to prevent catastrophic forgetting. - Workspace Auditing: Validate your current directory structure to ensure that all required metadata files are present, readable, and properly formatted.
Example Prompts
- "/training-manager setup"
- "/training-manager log-session 'Today we refined the agent's tone to be more professional.'"
- "/training-manager validate-workspace"
Tips & Limitations
- Security First: Always use the provided commands to modify files. The training-manager routes all file operations through
write-file.sh, which includes essential sanitization to prevent prompt injection attacks. - Automation: The auto-detection feature will initiate setup if it detects a missing workspace. If you prefer to manually scaffold files using templates, use the
scaffoldcommand directly. - Version Control: While this skill manages files, it is highly recommended to keep your
~/.openclaw/workspace/directory under Git version control to maintain a history of your agent's evolution.
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-anova44-openclaw-training-manager": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read