A comprehensive development pipeline for designing, testing, and publishing high-performance AI agent skills with built-in best practices.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install skill-creator-v2
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 skill-creator-v2 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 Skill Creator?
Skill Creator is a specialized development utility designed to streamline the entire lifecycle of creating Openclaw Skills. Born from practical engineering lessons, this tool provides a standardized pipeline for transforming concepts into functional agent capabilities. It ensures that every new skill adheres to strict technical standards regarding security, modularity, and agent-focused output formats.
By utilizing the Skill Creator framework, developers can build tools that are robust, safe, and highly actionable for AI agents. The skill emphasizes a dynamic architectural approach, moving away from hardcoded paths toward flexible, environment-aware logic that integrates seamlessly into any workspace environment.
Skill Creator Use Cases
- Designing new AI agent capabilities from scratch using a proven, success-oriented architectural template.
- Standardizing the development of custom Openclaw Skills across a team to ensure consistent documentation and logic.
- Implementing rigorous testing protocols to reduce false positives and improve agent trust in automated analysis.
- Packaging and publishing specialized skills to repositories while ensuring no sensitive data is leaked.
How Skill Creator Works
- Define the problem space and success criteria to establish clear functional boundaries and security constraints.
- Scaffold the directory structure including the mandatory SKILL.md documentation and core Python logic.
- Implement dynamic discovery logic that analyzes data and generates structured recommendations rather than monolithic text.
- Execute a multi-stage testing protocol covering accuracy, false-positive validation, and agent-specific actionability.
- Document the skill using progressive disclosure to keep the context window efficient for the agent.
Skill Creator Setup
To begin developing your own Openclaw Skills, ensure you have Python 3 installed and initialize your workspace structure:
# Create the standard skill directory structure
mkdir -p skills/[skill-name]/scripts
mkdir -p skills/[skill-name]/tests
# Initialize the required documentation file
touch skills/[skill-name]/SKILL.md
# Verify your development environment
python3 --version
Skill Creator Data Schema & Taxonomy
Skill Creator promotes a data-first approach where analysis results are delivered in structured JSON to enable autonomous agent actions.
| Field | Description | Requirement |
|---|---|---|
| action | The specific operation the agent should perform | Required |
| file | The target file path relative to the workspace | Required |
| reason | Justification for the recommended action | Required |
| severity | Urgency level (e.g., INFO, WARN, CRITICAL) | Required |
| category | The specific subsystem or domain being analyzed | Required |
Skill Creator Advanced Features
- Category-specific performance thresholds that allow for fine-tuned analysis across different file types.
- Dynamic pattern detection logic that avoids hardcoded paths to ensure cross-platform compatibility for Openclaw Skills.
- Automated publishing checklists including integrated secret scanning to prevent API key leaks.
- Skill graph integration to enable discovery and linking between related agent capabilities.
SKILL.md
Loading
Related Openclaw Skills
Remotion Video Generator
An AI-driven video production workflow that generates professional motion graphics programmatically using React and Remotion.
Minimal Memory Management
A structured two-tier memory system for AI agents that categorizes learnings into GOOD, BAD, and NEUTRAL entries to ensure a lean and searchable knowledge base.
Workspace Anchor
A multi-agent workspace awareness and safety system that prevents agent drift by anchoring contexts through environment-based naming.
Doc - Sysadmin Ubuntu 24.04
An automated IT specialist skill for Ubuntu 24.04 designed to monitor system health, optimize performance, and perform safe disk maintenance.
Skill Install Guardian
A security and due diligence layer that performs deep content scanning and malicious pattern detection before installing external skills.
Workspace Analyzer
A diagnostic utility that scans OpenClaw workspaces to identify maintenance needs, file bloat, and organizational issues for AI agents.
Featured*
