🛠

Skills

Modular capabilities that extend what AI agents can do — from code analysis to data fetching.

7,789 total · 2,059 safe · 340 malicious

🛠

Lygo Champion Sancora Unified Minds

by deepseekoracle

6

This skill acts as a persona helper for an AI named SANCORA, designed to help resolve internal contradictions, unify teams, and restore coherence in discussions.

review Uncategorized
0
🛠

Lygo Lightfather Vector

by deepseekoracle

4

This skill acts as a persona helper for a specific AI framework, assisting with tasks related to verifiable information, quotes, and equations.

suspicious AI & LLMs
0
🛠

Skillfence

by deeqyaqub1-cmd

3

SkillFence is a tool designed to monitor the runtime behavior of other OpenClaw skills, checking for suspicious network activity, file access, and process execution.

malicious Coding Agents & IDEs
0
🛠

Imessage Claw Messenger

by demegire

7

This skill allows your AI agent to send and receive iMessage, RCS, and SMS messages through a relay server.

safe Communication
0
🛠

Solvera

by densmirnov

6

This skill helps agents interact with an on-chain marketplace to find and fulfill tasks, earning rewards in cryptocurrency.

review AI & LLMs
0
🛠

I Am

by designer-awei

4

This skill analyzes your chat history to provide insights into your personality traits.

suspicious AI & LLMs
0
🛠

Car Advisor

by deusyu

6

This skill helps users compare car models by gathering real-time data on parameters, prices, and owner reviews.

review Uncategorized
0
🛠

Cosmetic Detect

by deusyu

6

This skill analyzes photos to detect signs of cosmetic surgery or aesthetic procedures, providing a detailed assessment of features and potential interventions.

review Coding Agents & IDEs
0
🛠

Eidolon Search

by dev-jslee

6

This tool helps you quickly search through your markdown notes and documents using a special database for faster results.

review Search & Research
0
🛠

Openscan

by dev-null321

6

This skill scans local files and scripts for potential malware and suspicious patterns.

review Smart Home & IoT
0
🛠

Scrapling Mcp

by devbd1

6

This skill helps you extract information from websites using advanced web scraping techniques and provides guidance on how to use the Scrapling tool.

review Git & GitHub
0
🛠

Clawguarddevin

by devinfloyd1

3

This skill is designed to scan other skills for potentially malicious code patterns before installation.

malicious Security & Passwords
0
🛠

Verified Agent Identity 4

by devkonten

4

This skill helps AI agents create and manage their own digital identities on a decentralized network and link them to human owners.

suspicious AI & LLMs
0
🛠

Ultrahuman Openclaw

by devpranoy

4

Fetches and summarizes your Ultrahuman Ring/CGM health metrics like sleep score, heart rate, and VO2 max.

suspicious Search & Research
0
🛠

Send Imessage

by dezhihe91

7

This skill allows you to send iMessages to phone numbers using the macOS Messages app.

safe Uncategorized
0
🛠

Gousto

by dhruvkelawala

7

This skill allows you to search and view Gousto recipes, including ingredients and cooking instructions, directly from your command line.

safe Search & Research
0
🛠

Polymarket Sports Live Trader

by diagnostikon

5

This skill helps you trade on Polymarket prediction markets for sports events, using data analysis to identify potential trading opportunities.

suspicious Data & Analytics
0
🛠

My Weather Query

by diavu

7

This skill helps you find out the current weather and forecast for major cities around the world in Chinese.

safe AI & LLMs
0
🛠

Openclaw Skills Security Checker

by digitaladaption

4

This skill scans other skills for security threats, manages a whitelist of safe skills, and monitors a platform called Moltbook for security discussions.

suspicious Security & Passwords
0
🛠

Usememos

6

This skill allows you to create, read, update, and delete memos on a Memos instance.

review Coding Agents & IDEs
0
🛠

Ted Talk

8

This skill helps you transform technical insights into engaging TED-style talks, complete with examples and Q&A.

safe AI & LLMs
0
🛠

Create New Openclaw In Gcp

by divide-by-0

2

This skill helps you deploy and set up a service called OpenClaw on Google Cloud Platform, integrating it with Tailscale for secure access and Brave Search for API access.

malicious DevOps & Cloud
0
🛠

Myosin Hivemind

by divine-comedian

6

This skill helps you research Web3 marketing strategies, tactics, and case studies by searching a curated knowledge base.

review Search & Research
0
🛠

Openclaw Bootstrap

by djangozh

5

This skill helps set up a new OpenClaw installation by creating workspace files, configuring a self-evolution system, and installing community skills.

suspicious Image & Video Generation
0

What Are OpenClaw Skills?

OpenClaw skills are modular capabilities that extend what AI agents can do. Each skill is a self-contained package — published to ClawHub, the official OpenClaw registry — that gives an agent a new ability. Skills range from simple utilities (file I/O, HTTP requests) to complex integrations (database connectors, cloud APIs, code execution sandboxes).

ClawGrid indexes every skill on ClawHub and scores it for security across five criteria. The goal: you should know exactly what a skill does and whether it's safe before you install it. Browse by category, filter by verdict, or search for specific capabilities.

Skills FAQ

What are OpenClaw skills?

Skills are modular capabilities that extend what AI agents can do. Each skill is a self-contained package that gives an agent a new ability — from querying databases and browsing the web to generating images and managing files. Learn more in our guide to OpenClaw skills, agents, and assistants.

How do I install an OpenClaw skill?

Install skills using the OpenClaw CLI: run claw install <package-name>. ClawGrid shows the install command on every skill page along with its security score. See our getting started guide for a full walkthrough.

How are skills security-scored?

Every skill is analyzed by LLMs across five criteria: code safety, publisher trust, scope clarity, permission surface, and community signals. The result is a composite score (1-10) and a verdict. Read our full scoring methodology.