Discover skills built for AI agents.

An OpenClaw skill that creates new agent skills based on a provided natural language description. It generates the required SKILL.md file and main Python implementation for the new skill. The skill supports specifying the skill name, description, capabilities, and tools needed.

The cto-advisor OpenClaw skill enables agents to provide expert CTO advice on technology strategy, leadership, and decision-making. It covers capabilities such as strategic planning, technology roadmaps, tech stack evaluations, engineering team management, hiring, budgeting, vendor selection, and risk management.

An OpenClaw skill that enables agents to use Cursor, the AI-first code editor, to edit codebases. It supports opening a folder in Cursor, chatting with Cursor Composer, applying diffs from Cursor, running terminal commands in Cursor, and closing Cursor.

An OpenClaw skill named debug-pro that provides professional debugging capabilities for Python code. It includes tools such as debug_start to initiate a debugging session on a Python file, debug_step to advance execution line-by-line, debug_next to step over functions, debug_continue to resume until a breakpoint or end, debug_break to set or list breakpoints, debug_vars to inspect local variables, debug_eval to evaluate expressions in the current context, and debug_stack to view the call stack. The skill integrates with pdb for interactive debugging control.

An OpenClaw skill that allows agents to coauthor documents with users. Agents can read, analyze, suggest edits, generate content, and apply changes to markdown documents.

An OpenClaw skill that provides agents with tools to manage Docker containers, images, volumes, and networks. It includes commands such as docker ps, docker images, docker run, docker volume ls, and docker network ls. The skill enables essential Docker operations directly within agent workflows.

An OpenClaw skill that provides a secure Docker-based sandbox for executing untrusted shell commands and code. It enforces resource limits on CPU and memory, disables network access, and uses ephemeral containers with no persistent storage. Containers are automatically cleaned up after execution.

An OpenClaw skill that embeds an Excalidraw canvas directly into conversations. It enables users and AI agents to collaboratively draw, edit, and interact with diagrams in real-time. Diagrams can be exported in PNG or SVG format.

An OpenClaw skill that provides a framework for orchestrating multi-agent task execution. It enables a lead agent to decompose complex tasks into subtasks, delegate them to specialist agents, track progress, and synthesize final outputs from results.