universal-agentThis skill should be used when the user needs to execute tasks through a complete automated workflow: understand natural language intent, dynamically generat...
Install via ClawdBot CLI:
clawdbot install wangjiaocheng/universal-agentGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
https://dashscope.aliyuncs.com/compatible-mode/v1Uses known external API (expected, informational)
api.openai.comAI Analysis
The skill's core functionality is to generate and execute arbitrary shell commands and Python scripts based on LLM interpretation, which inherently grants it broad and potentially destructive system access. While the external API calls (OpenAI, Alibaba) appear consistent with its stated purpose for LLM inference, the 'rm -rf /' example in the evidence demonstrates the tool's capability for unsafe operations, and the skill's architecture lacks clear, enforced safety boundaries or user consent steps before execution.
Generated May 13, 2026
A user requests to batch rename files, reorganize directories, or process data (e.g., convert CSV to JSON). The Universal Agent automatically generates and executes shell commands or Python scripts, handling errors and summarizing results.
A developer asks the agent to create a quick script for web scraping, data analysis, or image processing. The agent writes Python code on-the-fly, runs it, fixes any bugs, and provides a human-readable summary of the output.
An administrator describes a task like checking disk usage, restarting services, or updating packages. The agent executes the appropriate CLI commands, handles permission issues, and reports success or failure.
A user wants to fetch data from a public API (e.g., weather, stock prices) and format it into a report. The agent generates a Python script that calls the API, processes the response, and saves the output locally.
A user instructs the agent to turn on an LED or read a sensor using a Raspberry Pi. The agent generates a Python script that interfaces with hardware, executes it safely, and confirms the action.
Offer a web-based service where users describe tasks in natural language, and the agent executes them in a sandboxed environment. Free tier includes basic file operations; premium tier adds API calls, hardware control, and higher execution limits.
Deploy the agent within client infrastructure to automate repetitive IT and data workflows. Provide custom integration with existing tools (e.g., Slack, Jira) and on-premise execution.
Package the Universal Agent as a CLI plugin for frameworks like LangChain or as a standalone npm/pip package. Charge for extended features such as advanced error recovery, memory persistence, and multi-step workflows.
💬 Integration Tip
For bridge mode, ensure the external agent sets UA_THINK, UA_DEBUG_AND_FIX, and UA_SUMMARIZE environment variables correctly. The standalone mode requires a valid LLM API key in config.json.
Scored May 13, 2026
Audited Apr 16, 2026 · audit v1.0
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...