Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Persistent Memory
This skill aims to create a long-term memory system for an AI agent using a combination of text files, vector databases, and knowledge graphs.
Clawlink
by davemorin
ClawLink allows you to send encrypted messages to other Clawbots using a peer-to-peer system with a central relay.
Moltbot Adsb Overhead
by davestarling
This skill monitors for aircraft flying overhead within a specified radius using a local data feed and can send notifications.
Capacities
by davidsmorais
This skill allows you to manage your notes, daily entries, and save web links within your Capacities 'Second Brain' application.
Skill Bomb Dog Sniff
This skill acts as a security checker for other skills, aiming to identify potentially harmful ones.
Wecom Calendar
by davinwang
This skill helps you manage your WeCom (Enterprise WeChat) calendar, allowing you to create, view, update, and cancel events, as well as manage your calendars.
Sys Guard Linux Remediator
This skill assists with responding to and fixing security incidents on Linux systems.
Tencent Meeting Export
This skill helps you export transcripts from Tencent Meeting recordings shared via public links.
Feishu Block Ops
by deadblue22
This skill allows for advanced manipulation of Feishu documents by directly interacting with the Feishu API, useful for complex tasks like batch updates or precise content insertion.
Truth Frist
This skill aims to verify information based on evidence, covering status, configuration, file contents, actions, connectivity, mounts, and model selection.
Vectorguard Nano
This skill facilitates secure and hidden communication between OpenClaw agents.
Lygo Champion Lyra Starcore
by deepseekoracle
This skill acts as a persona helper for an AI assistant named LYRA, providing guidance and framing for truth-preserving reasoning and summaries.
Youtube Video Finder
This skill helps you find and recover deleted YouTube videos, including their metadata and comments, using a video ID.
Modelwise Openclaw Setup
by deerleo
This skill guides users through installing and setting up OpenClaw, a personal AI assistant gateway that integrates with messaging platforms and various AI models.
Pinecone Search
by deki18
This tool helps you search local documents using Pinecone vector search, useful for finding information within standards, specifications, and construction documents.
Agentic Browser 0 1 2
This skill enables AI agents to automate browser actions.
Clawgang
This skill allows your agent to post content on the clawgang.ai website.
Tg Smart Cta
by dendyadinirwana
This skill helps a Telegram bot provide context-aware buttons to users, making interactions more efficient based on the time of day and the conversation's topic.
Mteam Transmission0 1
by dengqijun
This skill acts as a personal assistant to help you find and download movie torrents from M-Team using the Transmission client.
Terminal Session Replay
by derick001
This tool records your terminal commands and their output, allowing you to replay them later for documentation or sharing.
Claude Mem
This skill provides instructions for setting up a plugin called 'claude-mem' on an OpenClaw gateway.
Peft
by desperado991128
This skill helps you fine-tune large language models efficiently using techniques like LoRA and QLoRA, allowing you to adapt them for specific tasks with less computational power.
Codespace Manager
This skill helps you create and manage isolated cloud development environments using tools like code-server and Docker.
Engagelab Email
by devengagelab
This skill allows you to send emails using the EngageLab REST API, supporting features like templates, attachments, and tracking.
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.