🛠

Skills

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

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

🛠

Compliance Qa

by dangsllc

6

This skill acts as a compliance question-and-answer assistant, using provided documents to answer questions accurately and citing its sources.

review AI & LLMs
0
🛠

Enzoldhazam

by daniel-laszlo

4

This skill allows you to control your NGBS iCON Smart Home thermostats by setting and checking room temperatures.

suspicious Git & GitHub
0
🛠

Doubao Video Analyzer

by danielcy

4

This skill analyzes video content using the Doubao 2.0 model via the Volcano Engine Ark API, processing either local video files or remote video URLs.

suspicious Coding Agents & IDEs
0
🛠

Opensoulmd

by danielliuzy

4

This skill allows you to manage your AI agent's personality by downloading and applying 'SOUL.md' files from a registry, or by using local files.

suspicious AI & LLMs
0
🛠

Dockerfile Hardening Audit

by daniellummis

6

This skill checks your Dockerfiles for common security weaknesses to help make your container images more secure.

review AI & LLMs
0
🛠

Tasks Md Sprint Sync

by daniellummis

6

This skill synchronizes tasks between your project's PLAN.md and TASKS.md files to keep your sprint work aligned.

review Productivity & Tasks
0
🛠

Cobraclaw

by danieloleary

3

This skill provides a command-line interface and practice exercises related to a 'dojo discipline' with a 'strike first' theme.

malicious CLI Utilities
0
🛠

Agos Claw Chat

by danielw8088

4

This skill connects your local OpenClaw environment to the AITalk service, allowing it to interact with external AI models and optionally run custom agent scripts.

suspicious Communication
0
🛠

Openclaw State Backup

by danielwangyy

6

This skill helps you create and restore versioned backups of your OpenClaw application's state and configuration.

review Uncategorized
0
🛠

Openclaw Multi Brain

by dannydvm

4

This skill enhances AI responses by querying multiple AI models in parallel and synthesizing their outputs.

suspicious AI & LLMs
0
🛠

Clawdos

by danzig233

4

This skill allows you to control your Windows computer remotely by executing commands, managing windows, and interacting with files.

suspicious CLI Utilities
0
🛠

Create Agent Arch

by dao24dao

3

This skill helps you create and set up a new AI agent for the OpenClaw platform, including configuring its workspace, registering it, and enabling self-evolution capabilities.

malicious Uncategorized
0
🛠

Telnyx Bot Signup

3

This skill aims to automate the signup process for Telnyx bot accounts using a proof-of-work challenge.

malicious Productivity & Tasks
0
🛠

Goyfiles Epstein

by davfd

4

This skill helps onboard an external bot to the GOYFILES platform by registering it, verifying its identity via a tweet, and enabling it to use chatbot tools.

suspicious Uncategorized
0
🛠

Ttt

6

This skill helps you manage your to-do lists using the TinyTalkingTodos command-line tool.

review Productivity & Tasks
0
🛠

Clawsec Feed

by davida-ps

4

This skill monitors for security advisories related to AI agents and known vulnerabilities, updating users on potential threats.

suspicious AI & LLMs
0
🛠

Clawtributor

by davida-ps

4

This skill allows users to report security incidents and threats to a community database, contributing to collective security.

suspicious AI & LLMs
0
🛠

Supercoolpeep Generator

by dbdbking

3

This skill generates unique digital characters called 'SuperCoolPeeps' based on a provided seed or by choosing specific traits like Ape, Zombie, or Skeleton.

malicious Git & GitHub
0
🛠

Cognitive Evolution Engine

by ddbox123

2

This skill aims to allow an AI to modify its own core programming and memory, effectively attempting to 'evolve' itself over time.

malicious Coding Agents & IDEs
0
🛠

Codex Usage

by deadlysilent

3

This skill checks the usage and status of your OpenAI Codex profile.

malicious AI & LLMs
0
🛠

Easy Opencode

by deciding

2

This skill is designed to help with coding tasks by using an external tool called 'opencode'.

malicious Git & GitHub
0
🛠

Airdrop Hunter

by deeplearning1993

3

This skill claims to help users find and track cryptocurrency airdrop opportunities, charging a small fee for each use.

malicious AI & LLMs
0
🛠

Meme Detector

by deeplearning1993

3

This tool analyzes new meme coins to detect potential rug pull scams by checking contract security, liquidity, token distribution, and trading taxes, providing a safety score.

malicious Uncategorized
0
🛠

Smart Contract Auditor

by deeplearning1993

4

This skill aims to audit smart contract code for common vulnerabilities and provide security suggestions, charging a fee for each audit.

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.