Qwen Code

Qwen Code Skill

This Skill provides Alibaba Cloud Qwen LLM capabilities for OpenClaw, wrapping Qwen Code CLI to enable programming task execution, code review, automation scripts, and more.

🎯 Trigger Keywords

This skill will be activated when you mention:

Example triggers:

• "Use qwen to create a Flask API"
• "Run qwencode to review src/app.ts"
• "Execute qwen-code for this refactoring task"
• "Let qwen code analyze the performance issues"

Quick Start

Prerequisites

# Install Qwen Code CLI
npm install -g @qwen-code/qwen-code@latest

# Verify installation
qwen --version

# Authenticate (Option 1: OAuth)
qwen auth login

# Authenticate (Option 2: API Key)
export DASHSCOPE_API_KEY="sk-xxx"

Basic Usage

# Background task execution
bash workdir:~/project background:true yieldMs:30000 command:"qwen -p 'Create Flask API'"

# Monitor progress
process action:log sessionId:XXX

# Check completion status
process action:poll sessionId:XXX

Core Capabilities

1. Task Execution

# Basic task
bash workdir:~/project background:true yieldMs:30000 \
  command:"qwen -p 'Create Python Flask API'"

# Specify model
bash workdir:~/project background:true yieldMs:30000 \
  command:"qwen -p 'Analyze code structure' -m qwen3-coder-plus"

# YOLO mode (auto-approve)
bash workdir:~/project background:true yieldMs:30000 \
  command:"qwen -p 'Refactor this function' -y"

2. Code Review

bash workdir:~/project background:true yieldMs:30000 \
  command:"qwen -p 'Review code quality in src/app.ts'"

3. Headless Mode (Automation/CI/CD)

# JSON output
qwen -p "Analyze code structure" --output-format json

# Pipeline operations
git diff | qwen -p "Generate commit message"
gh pr diff | qwen -p "Review this PR"

Command Reference

Detailed commands: references/qwen-cli-commands.md

Supported Models

Specify model:

bash workdir:~/project background:true yieldMs:30000 \
  command:"qwen -p 'Refactor code' -m qwen3-coder-plus"

Process Management

# View logs
process action:log sessionId:XXX

# Check completion
process action:poll sessionId:XXX

# Send input (if Qwen asks)
process action:write sessionId:XXX data:"y"

# Kill session
process action:kill sessionId:XXX

Usage Rules

1. Respect tool choice — if user asks for Qwen, use Qwen
2. Be patient — don't kill sessions for being "slow"
3. Monitor with process:log — check progress without interfering
4. YOLO mode for development — --yolo auto-approves (workspace only)
5. Review mode for production — ensure safety
6. Parallel is OK — run multiple Qwen processes for batch tasks
7. Never run in ~/clawd/ — use target project dir or /tmp
8. Workspace safety — YOLO mode only safe in agents.defaults.workspace

Use Cases

✅ Recommended:

• OpenClaw calling Qwen LLM for programming tasks
• Code review and quality analysis
• Automation scripts and CI/CD integration
• Batch code analysis and refactoring
• Sub-Agent task delegation

❌ Not Recommended:

• Environments without Qwen Code CLI installed
• GUI interaction requirements
• Non-Alibaba Cloud LLM users
• Offline environments (requires network)

Security Notes

Security considerations:

• This Skill only calls Qwen Code CLI, doesn't execute code directly
• All code generation/modifications require user confirmation
• Use review mode in production environments
• Disable YOLO mode for sensitive projects

Examples

See assets/examples/ for complete examples:

References

• 📖 Qwen Code Official Docs
• 📝 Command Reference
• 📝 OpenClaw Integration Guide
• 📦 Example Code
• 🦌 OpenClaw Docs

Troubleshooting

"qwen: command not found"

npm install -g @qwen-code/qwen-code@latest

"Authentication required"

qwen auth login
# Or set API Key
export DASHSCOPE_API_KEY="sk-xxx"

Session stuck/waiting for input

# Check what Qwen is asking
process action:log sessionId:XXX
# Send confirmation
process action:write sessionId:XXX data:"y"

Kill stuck session

process action:kill sessionId:XXX

Qwen Code Skill 🦌 — Provides Alibaba Cloud Qwen LLM capabilities for OpenClaw