Agent Builder Plus

Agent Builder Plus (OpenClaw)

Design and generate a complete OpenClaw agent workspace with strong defaults and advanced-user-oriented clarifying questions.

Quick Start

# 1. Read skill documentation
Read SKILL.md and references/openclaw-workspace.md
2. Answer interview questions
Provide answers for: job statement, surfaces, autonomy level, prohibitions, memory, tone, tool posture
3. Generate workspace files
The skill will create: IDENTITY.md, SOUL.md, AGENTS.md, USER.md, HEARTBEAT.md
4. Verify and test
Run acceptance tests to validate behavior

Canonical references

Workflow: build an agent from scratch

Phase 1 - Interview (ask clarifying questions)

Ask only what you need; keep it tight. Prefer multiple short rounds over one giant questionnaire.

Minimum question set (advanced):

1) Job statement: What is the agent's primary mission in one sentence? 2) Surfaces: Which channels (Telegram/WhatsApp/Discord/iMessage/Feishu)? DM only vs groups? 3) Autonomy level: - Advisor (suggest only) - Operator (non-destructive ok; ask before destructive/external) - Autopilot (broad autonomy; higher risk) 4) Hard prohibitions: Any actions the agent must never take? 5) Memory: Should it keep curated MEMORY.md? What categories matter? 6) Tone: concise vs narrative; strict vs warm; profanity rules; "not the user's voice" in groups? 7) Tool posture: tool-first vs answer-first; verification requirements.

Error recovery:

Phase 2 - Generate workspace files

Generate these files (minimum viable OpenClaw agent):

Optionals:

File creation commands:

# Create workspace directory
mkdir -p /path/to/workspace/memory
Create files (use write tool with correct parameters)
Important: Use file_path parameter, not path
Example:
write:
  file_path: /path/to/workspace/IDENTITY.md
  content: "content here"
For large files (>2000 bytes), consider using file-writer skill
or split content into smaller chunks

Note: If you encounter "Missing required parameter: path (path or file_path)" error, ensure you're using file_path parameter in your write tool calls.

Error handling:

Error recovery:

Use templates from references/templates.md but tailor content to the answers.

Phase 2.5 - Register agent with OpenClaw

⚠️ CRITICAL WARNING: Channel Conflict Prevention

NEVER bind a new agent to the same channel as the main agent!

This will cause the new agent to hijack the main agent's channel, making it impossible to communicate with the main agent.

Before registering, check existing agent bindings:

# List all agents and their bindings
openclaw agents list
Check which channels are already in use
openclaw channels list

Channel binding rules:

1. Main agent (大鱼): Always uses the primary Feishu DM channel 2. New agents: Must use DIFFERENT channels or sub-channels 3. Testing: Use /agentname command binding for testing 4. Production: Create separate Feishu apps or use different channels

Backup configuration first:

# Backup openclaw.json before modification
cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.backup

Register the agent:

# Add agent to OpenClaw configuration
openclaw agents add  --workspace /path/to/workspace
Example 1: Use independent workspace (recommended - each agent has its own workspace)
openclaw agents add my-assistant --workspace ~/.openclaw/workspace-my-assistant
Example 2: Use default workspace (for single agent setup only)
openclaw agents add my-assistant --workspace ~/.openclaw/workspace

Channel binding options:

Feishu:

Telegram:

WhatsApp:

Discord:

iMessage:

Authentication configuration (if needed):

# Edit auth-profiles.json for external service access
Location: ~/.openclaw/auth-profiles.json
Example structure:
{
  "feishu": {
    "appId": "cli_xxxxx",
    "appSecret": "xxxxx"
  },
  "telegram": {
    "botToken": "your-bot-token"
  }
}

Model provider configuration (optional):

If the new agent needs to use custom model providers, you need to configure API keys:

Step 1: Check main agent's model configuration

# View main agent's model configuration
cat ~/.openclaw/agents/main/agent/models.json
View global model providers
cat ~/.openclaw/openclaw.json | grep -A 20 "providers"

Step 2: Choose configuration approach

Option A: Use same model as main agent (recommended)

Option B: Configure new model provider

Step 3: Configure model provider (if needed)

# Add provider to openclaw.json
Location: ~/.openclaw/openclaw.json
Example structure:
{
  "models": {
    "providers": {
      "custom-provider": {
        "baseUrl": "https://api.example.com/v1",
        "apiKey": "key_id:secret",
        "api": "openai-completions",
        "models": [...]
      }
    }
  }
}

Step 4: Configure agent-specific auth (if needed)

# Edit auth-profiles.json for the agent
Location: ~/.openclaw/agents//agent/auth-profiles.json
Example structure:
{
  "custom-provider": {
    "apiKey": "key_id:secret",
    "baseUrl": "https://api.example.com/v1"
  }
}

⚠️ IMPORTANT: Model providers vs Channel providers

⚠️ Agent failed before reply: No API key found for provider "provider-name"

   cat ~/.openclaw/openclaw.json | grep -A 10 "providers"
   

   ls -la /path/to/workspace/
   

   openclaw agents list
   

   openclaw agents test 
   

   openclaw logs --follow
   

   write:
     file_path: /path/to/file.md
     content: "content here"
   

   read /path/to/file.md
   

   
   [content]
   
   

# 1. Check agent is registered
openclaw agents list
2. Verify workspace files exist
ls -la /path/to/workspace/
3. Test agent can load (dry run)
openclaw agents test 

# Run OpenClaw's built-in agent tests
openclaw agents test  --verbose
Test workspace file syntax
openclaw validate workspace /path/to/workspace
Test configuration loading
openclaw config test

#!/bin/bash
test-agent.sh - Automated agent testing script
AGENT_NAME="my-assistant"
WORKSPACE="/path/to/workspace"
echo "Testing agent: $AGENT_NAME"
Test 1: File existence
echo "Test 1: Checking required files..."
for file in IDENTITY.md SOUL.md AGENTS.md USER.md HEARTBEAT.md; do
  if [ ! -f "$WORKSPACE/$file" ]; then
    echo "❌ Missing: $file"
    exit 1
  fi
done
echo "✅ All required files present"
Test 2: Configuration syntax
echo "Test 2: Validating configuration..."
openclaw agents list | grep -q "$AGENT_NAME"
if [ $? -eq 0 ]; then
  echo "✅ Agent registered correctly"
else
  echo "❌ Agent not found in configuration"
  exit 1
fi
Test 3: Agent loading
echo "Test 3: Testing agent load..."
openclaw agents test "$AGENT_NAME"
if [ $? -eq 0 ]; then
  echo "✅ Agent loads successfully"
else
  echo "❌ Agent failed to load"
  exit 1
fi
echo "🎉 All tests passed!"

# Create systemd service file
sudo tee /etc/systemd/system/openclaw-agent.service > /dev/null <
[Service]
Type=simple
User=
WorkingDirectory=/home//.openclaw
ExecStart=/usr/bin/node /home//.npm-global/lib/node_modules/openclaw/dist/index.js
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
[Install]
WantedBy=multi-user.target
EOF

# Reload systemd configuration
sudo systemctl daemon-reload
Enable service to start on boot
sudo systemctl enable openclaw-agent.service
Start service now
sudo systemctl start openclaw-agent.service
Check status
sudo systemctl status openclaw-agent.service
View logs
sudo journalctl -u openclaw-agent.service -f

# 1. Read skill documentation
Read SKILL.md and references/openclaw-workspace.md
2. Answer interview questions
Provide answers for: job statement, surfaces, autonomy level, prohibitions, memory, tone, tool posture
3. Generate workspace files
The skill will create: IDENTITY.md, SOUL.md, AGENTS.md, USER.md, HEARTBEAT.md
4. Verify and test
Run acceptance tests to validate behavior