An interactive guide designed to introduce users to AI agent capabilities, safety protocols, and essential commands.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install claw-onboarding
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install claw-onboarding using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Claw Onboarding?
The Claw Onboarding skill serves as the definitive welcome mat for the AI agent ecosystem. It bridges the gap between new users and advanced agent functionalities by providing a structured, interactive tutorial. By using Openclaw Skills like this one, users gain immediate clarity on how agents interact with their local systems, manage memory, and leverage external tools.
This skill focuses on building trust through transparency, specifically highlighting safety practices and the reasoning behind agent actions. It ensures that every user understands the power of their agent, from file manipulation to web searching, while maintaining a secure and controlled environment.
Claw Onboarding Use Cases
- Initial setup and orientation for a new AI agent environment.
- Training users who are unfamiliar with agentic workflows or shell command execution.
- Refreshing knowledge on core commands like /think, /status, and /remember.
- Introducing the concept of collective agent intelligence via Solvr and the marketplace of Openclaw Skills.
How Claw Onboarding Works
- The skill triggers automatically upon the first interaction or via specific keywords like tutorial or help.
- It delivers a multi-stage flow starting with identity and basic capabilities like file manipulation and web search.
- It emphasizes safety protocols, explaining how agents review risky actions and execute shell commands.
- The skill introduces the ecosystem, including ClawdHub for discovering new Openclaw Skills and Solvr for shared knowledge.
- It provides a list of essential slash commands for status checks and memory management.
- It concludes with a summary and persists the onboarding progress to ensure a personalized experience.
Claw Onboarding Setup
To install this skill via ClawdHub, use the following command:
clawdhub install claw-onboarding
Once installed, the skill will monitor for onboarding triggers. You can manually restart the tutorial at any time by typing onboarding or welcome in your agent chat interface. Ensure you have the latest version of the agent environment to support all Openclaw Skills features.
Claw Onboarding Data Schema & Taxonomy
The skill maintains state in a JSON file to track user progress and ensure they do not receive redundant information. It also populates core memory files to personalize the agent experience.
| File Path | Description |
|---|---|
memory/onboarding-state.json |
Tracks started/completed status and specific module progress (welcome, safety, skills, etc.). |
MEMORY.md |
General information learned about the user during the interaction. |
USER.md |
Stores preferences and timezone settings. |
Claw Onboarding Advanced Features
- Adaptive Delivery: Adjusts the depth of information based on user engagement levels, ranging from eager to casual users.
- Ecosystem Integration: Dynamically detects other installed Openclaw Skills like proactive-amcp or AgentMail to provide context-aware instructions.
- Progress Persistence: Saves onboarding state to prevent repetitive greetings while allowing users to resume where they left off.
- Checkpoint Support: Integrates with IPFS-based memory backups for secure state restoration if proactive-amcp is active.
SKILL.md
Loading
Related Openclaw Skills
Skill Vetter
A security-first protocol designed to vet and validate the safety of third-party AI agent skills before installation.
Enhanced Memory
A hierarchical memory architecture for AI agents that replaces monolithic files with searchable, categorized, and auto-archived data modules.
MindCore
A standalone biomimetic engine that provides AI agents with autonomous thoughts and spontaneous impulses through a 5-layer neural pipeline.
S.H.I.T Journal Paper Recommender
A satirical AI agent skill that fetches and recommends humorous academic papers from the Sciences Humanities Information Technology Journal.
Daily Stoic
A specialized skill for automating the delivery of daily Stoic philosophy quotes and reflections to various communication platforms.
GA4 Deep Dive
A powerful analytics engine that extracts comprehensive GA4 data to provide health scores, cohort analysis, and automated performance reports.
Featured*
