smart-followupsGenerate contextual follow-up suggestions after AI responses. Shows 3 clickable buttons (Quick, Deep Dive, Related) when user types "/followups".
Install via ClawdBot CLI:
clawdbot install robbyczgw-cla/smart-followupsGenerate contextual follow-up suggestions for OpenClaw conversations.
Primary command:
/followupsAliases:
/fu
/suggestionsWhen you type /followups, I'll generate 3 contextual follow-up questions based on our conversation:
| Method | Example | Recommended |
|--------|---------|-------------|
| /followups | Just type it! | โ
Yes |
| /fu | Short alias | โ
Yes |
| Natural language | "give me suggestions" | Works too |
| After any answer | "what should I ask next?" | Works too |
Say "followups" in any conversation:
You: What is Docker?
Bot: Docker is a containerization platform...
You: /followups
Bot: ๐ก What would you like to explore next?
[โก How do I install Docker?]
[๐ง Explain container architecture]
[๐ Docker vs Kubernetes?]On button channels (Telegram/Discord/Slack): Tap a button to ask that question.
On text channels (Signal/WhatsApp/iMessage/SMS): Reply with 1, 2, or 3.
Each generation produces 3 suggestions:
| Category | Emoji | Purpose |
|----------|-------|---------|
| Quick | โก | Clarifications, definitions, immediate next steps |
| Deep Dive | ๐ง | Technical depth, advanced concepts, thorough exploration |
| Related | ๐ | Connected topics, broader context, alternatives |
Default: Uses OpenClaw's existing auth โ same login and model as your current chat.
Optional providers:
openrouter โ Requires OPENROUTER_API_KEYanthropic โ Requires ANTHROPIC_API_KEY{
"skills": {
"smart-followups": {
"enabled": true,
"provider": "openclaw",
"model": null
}
}
}| Option | Default | Description |
|--------|---------|-------------|
| provider | "openclaw" | Auth provider: openclaw, openrouter, anthropic |
| model | null | Model override (null = inherit from session) |
| apiKey | โ | API key for non-openclaw providers |
| Channel | Mode | Interaction |
|---------|------|-------------|
| Telegram | Buttons | Tap to ask |
| Discord | Buttons | Click to ask |
| Slack | Buttons | Click to ask |
| Signal | Text | Reply 1-3 |
| WhatsApp | Text | Reply 1-3 |
| iMessage | Text | Reply 1-3 |
| SMS | Text | Reply 1-3 |
| Matrix | Text | Reply 1-3 |
| Email | Text | Reply with number |
See CHANNELS.md for detailed channel documentation.
/followups| File | Purpose |
|------|---------|
| handler.js | Command handler and channel formatting |
| cli/followups-cli.js | Standalone CLI for testing/scripting |
| README.md | Full documentation |
| CHANNELS.md | Channel-specific guide |
| FAQ.md | Common questions |
Inspired by Chameleon AI Chat's smart follow-up feature.
Generated Mar 1, 2026
Integrate the skill into a customer support chatbot to automatically suggest follow-up questions after resolving an initial query, helping users explore related issues or get deeper explanations without restarting the conversation. This reduces support ticket volume and improves user satisfaction by guiding them to relevant next steps.
Use the skill in an AI-powered tutoring platform to generate follow-up questions after explaining a concept, encouraging students to ask for clarifications, dive deeper into topics, or explore related subjects. This fosters interactive learning and helps tailor lessons to individual student needs.
Deploy the skill in a documentation chatbot to suggest follow-up questions after users read about a tool or API, prompting them to ask about installation steps, advanced features, or comparisons with alternatives. This enhances user engagement and helps them find information more efficiently.
Incorporate the skill into a healthcare chatbot to suggest follow-up questions after users describe symptoms, guiding them to ask about treatment options, preventive measures, or related conditions. This provides a more comprehensive self-assessment tool while ensuring users stay informed.
Apply the skill in a sales chatbot to generate follow-up questions after a prospect inquires about a product, suggesting queries about pricing, technical specifications, or competitor comparisons. This helps qualify leads faster and moves them through the sales funnel with minimal manual intervention.
Offer the skill as part of a subscription-based AI chatbot platform, charging businesses a monthly fee per user or channel integration. Revenue comes from tiered plans based on usage limits, advanced features like custom branding, and priority support for enterprise clients.
Provide a free version with basic follow-up suggestions and limited channels, then upsell to premium plans that include more channels, advanced customization options, and integration with external APIs like OpenRouter or Anthropic. Revenue is generated from upgrades and one-time setup fees.
License the skill to other companies for embedding into their own products, such as customer service software or educational apps, with revenue from one-time licensing fees or royalties based on user engagement. This model leverages the skill's versatility across different industries without direct customer support overhead.
๐ฌ Integration Tip
Start by enabling the skill in a single channel like Telegram or Discord to test user interaction, then expand to other channels based on feedback and usage data.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...
Collaborative thinking partner for exploring complex problems through questioning
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
ๆ นๆฎ็จๆท็ๅ่ฝ้ๆฑ๏ผๅฎๆไธ VeADK ็ธๅ ณ็ๅ่ฝใ
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.