A comprehensive toolset for discovering, security vetting, and managing Openclaw Skills from multiple registries and catalogs.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install skill-hub
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 skill-hub using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Skill Hub serves as the primary gateway for expanding the capabilities of your AI agent. It acts as a bridge between your local environment and the vast ecosystem of Openclaw Skills, providing a unified interface to search through thousands of curated tools. By integrating with the ClawHub registry and GitHub catalogs, it ensures developers have access to the latest extensions for their agent workflows.
Beyond simple discovery, Skill Hub prioritizes ecosystem security. It performs deep scans for malicious patterns, code-level vulnerabilities, and complex prompt injections. This ensures that every one of the Openclaw Skills you add to your agent is safe, reliable, and adheres to technical best practices, providing a trusted foundation for automated workflows.
To begin managing your Openclaw Skills, ensure you have the necessary scripts and dependencies in your local environment.
# Search for available skills
python3 scripts/skill-hub-search.py --query "spreadsheet"
# Install a specific skill from the registry
npx clawhub@latest install <skill-slug>
# Sync the local catalog with the latest updates
python3 scripts/skill-hub-sync.py
Skill Hub categorizes Openclaw Skills based on a granular credibility system and technical metadata.
| Tier | Score Range | Definition |
|---|---|---|
| Trusted | 85-100 | Fully curated, vetted, and mature tools. |
| Good | 60-84 | Curated or vetted with positive community signals. |
| Unvetted | 30-59 | Available in the registry but not yet scanned for security. |
| Caution | 0-29 | Missing metadata or flagged with security warnings. |
Security scans check for both code-level risks (eval/exec) and NLP-level risks (role hijacking, exfiltration prompts).
Loading
A comprehensive diagnostic, error-fixing, and skill recommendation toolkit designed to streamline Openclaw Skills management and troubleshooting.

A high-performance, cost-effective tool for generating AI images directly through your AI agent using the EvoLink API.

A professional-grade image generation and editing skill powered by the EvoLink Nano Banana Pro API for high-resolution visual creation.

A collection of high-performance Python scripts for offline data format conversion and text normalization without external API dependencies.

A diagnostic utility that identifies prompt context bloat and generates a safe, reversible plan to reduce token costs and improve response speed.

A portable tagging protocol that defines explicit context boundaries and memory persistence rules for AI chat sessions.








































