Smart Follow-ups Skill

Generate contextual follow-up suggestions for OpenClaw conversations.

Slash Command

The command name is derived from the skill's name field:

/smart-followups

OpenClaw 2.0 registers no aliases (/fu, /suggestions, and /next do not work), and separate commands:, triggers:, or channels: frontmatter fields are ignored.

When you run /smart-followups, the skill generates 3 contextual follow-up questions based on the conversation:

1. ⚡ Quick — Clarification or immediate next step
2. 🧠 Deep Dive — Technical depth or detailed exploration
3. 🔗 Related — Connected topic or broader context

How to Trigger

Usage

Say "followups" in any conversation:

You: What is Docker?
Bot: Docker is a containerization platform...

You: /smart-followups

Bot: 💡 What would you like to explore next?
[⚡ How do I install Docker?]
[🧠 Explain container architecture]
[🔗 Docker vs Kubernetes?]

The skill produces the 3 suggestions. How they are rendered depends on the channel: the agent can show buttons only on channels that support interactive buttons, and only if it builds them there. Otherwise it posts a numbered text list — reply with 1, 2, or 3.

Categories

Each generation produces 3 suggestions:

Authentication

Default: Uses OpenClaw's existing auth — same login and model as your current chat.

Optional providers:

• openrouter — Requires OPENROUTER_API_KEY
• anthropic — Requires ANTHROPIC_API_KEY

Configuration

{
  "skills": {
    "entries": {
      "smart-followups": {
        "enabled": true,
        "provider": "openclaw",
        "model": null
      }
    }
  }
}

Channel Support

The skill generates the suggestions; the agent decides how to render them within each channel's capabilities.

See CHANNELS.md for detailed channel documentation.

How It Works

1. User runs /smart-followups
2. The agent gathers recent conversation context (OpenClaw does not load handler.js; skills are instruction packs)
3. The agent generates 3 contextual questions (using the current model/auth)
4. The agent renders them as buttons or as a numbered text list, depending on what the channel supports
5. User taps a button or replies with a number
6. OpenClaw answers that question

Files

Credits

Inspired by Chameleon AI Chat's smart follow-up feature.