๐ŸŽ Get the FREE AI Skills Starter Guide โ€” Subscribe โ†’
BytesAgainBytesAgain
๐Ÿฆ€ ClawHub

Universal Agent

by @wangjiaocheng

This skill should be used when the user needs to execute tasks through a complete automated workflow: understand natural language intent, dynamically generat...

Versionv1.0.0
โšก When to Use
TriggerAction
- User describes a task in natural language that requires automated execution
- Task needs dynamic code generation (Python script) and immediate execution
- Task involves file operations, data processing, system administration, CLI tools, API calls
- User wants end-to-end automation without manual intervention
- Keywords: "ไธ‡่ƒฝagent", "universal agent", "่‡ชๅŠจๆ‰ง่กŒ", "ๅŠจๆ€็”Ÿๆˆไปฃ็ ", "็”Ÿๆˆๅนถๆ‰ง่กŒ", "ๅธฎๆˆ‘ๅšXX"
โš™๏ธ Configuration

Mode 1 (Standalone) โ€” Needs API Key

Option A โ€” Config File: Edit scripts/config.json and fill in your API key.

Option B โ€” Environment Variables:

set LLM_API_KEY=your-key-here
set LLM_MODEL=gpt-4o
set LLM_BASE_URL=https://api.openai.com/v1

Option C โ€” Local Ollama (Free):

ollama run llama3

Then select ollama_llama3 preset when starting the script

Configuration priority: Environment variables > config.json > Interactive input.

Mode 2 (Bridge) โ€” No API Key Needed

The external Agent provides all LLM capabilities. Configure only optional settings:

# Optional: change input source from env to file
set UA_INPUT_SOURCE=file

Optional: skip safety confirmations (not recommended)

Use --dangerous flag instead

Mode 3 (Simulation) โ€” No Configuration Needed

Agent uses its own native capabilities. Nothing to configure.

View on ClawHub
TERMINAL
clawhub install universal-agent

๐Ÿงช Use this skill with your agent

Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.

๐Ÿ” Can't find the right skill?

Search 60,000+ AI agent skills โ€” free, no login needed.

Search Skills โ†’