A comprehensive onboarding package that guides users through the initial setup, personality definition, and security hardening of their AI agent via an interactive dialogue.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-starter-kit
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install openclaw-starter-kit using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The OpenClaw Starter Kit is a foundational skill designed to simplify the transition for new users entering the ecosystem. It provides a structured, step-by-step onboarding process that transforms complex configurations into a conversational interface. By using this kit, developers can quickly establish a fully functional environment, ensuring their AI agent has a clear persona, organized memory, and robust security protocols from the very first interaction.
This package is a vital entry point for anyone looking to leverage Openclaw Skills effectively. It automates the creation of essential system files like SOUL.md and USER.md while providing clear roadmaps for advanced features such as web search integration and multi-channel communication. It ensures that your workspace follows best practices for data organization and agent behavior, making it the ideal starting point for building sophisticated automated workflows.
To deploy the starter kit within your environment, use the standard CLI command to fetch it from the Openclaw Skills library:
openclaw skills install starter-kit
Once installed, you can begin the interactive setup by simply asking your agent:
openclaw chat "start setup"
The skill organizes the agent workspace into a logical hierarchy to ensure data persistence and clear metadata taxonomy:
| File/Folder | Type | Description |
|---|---|---|
SOUL.md |
Markdown | Defines the agent's name, persona, primary role, and behavioral boundaries. |
USER.md |
Markdown | Stores user-specific context, including professional interests and timezone. |
MEMORY.md |
Markdown | The primary index for the agent's long-term memory system. |
memory/knowledge/ |
Directory | Stores learned data and specialized research materials. |
memory/projects/ |
Directory | Contains logs and records related to specific developer projects. |
HEARTBEAT.md |
Markdown | Configuration for automated daily tasks, reminders, and status checks. |
Loading
A systematic prompt injection toolkit designed to solve Lakera's Gandalf challenge through layered attack methodologies.

An intelligent wrapper that automatically refines and expands simple user instructions into professional-grade AI prompts.

A specialized skill for GrowthX members to automatically discover and submit their development projects to the Built at GrowthX community showcase.

A specialized AI agent skill that generates high-conversion Xiaohongshu titles by leveraging emotional hooks, platform-specific algorithms, and native style mapping.

A governance skill that enforces release quality and prevents version spam through strict pre-deployment checklists and mandatory cooldown periods.

An AI-driven platform that transforms academic reviewer feedback into actionable, structured revision suggestions for manuscripts.








































