← Back to Skills Marketplace
5110
Downloads
8
Stars
11
Active Installs
19
Versions
Install in OpenClaw
/install smart-followups
Description
Generate contextual follow-up suggestions after AI responses. Shows 3 clickable buttons (Quick, Deep Dive, Related) when user types "/followups".
Usage Guidance
Install is reasonable if you want contextual follow-up suggestions. Prefer the default OpenClaw-native mode, use /followups rather than broad trigger phrases where possible, keep autoTrigger disabled unless you explicitly want suggestions after every response, and treat optional OpenRouter/Anthropic API keys and conversation context as sensitive.
Capability Analysis
Type: OpenClaw Skill
Name: smart-followups
Version: 2.1.8
The smart-followups skill bundle is a well-documented tool designed to generate contextual follow-up questions for AI conversations across multiple messaging platforms. The core logic in handler.js and cli/followups-cli.js uses standard LLM integration patterns (Anthropic/OpenRouter) and includes defensive prompt engineering to treat conversation history as opaque data, mitigating potential prompt injection from users. No evidence of data exfiltration, malicious execution, or unauthorized persistence was found; the behavior is entirely consistent with the stated purpose.
Capability Assessment
Purpose & Capability
The core behavior is coherent with the stated purpose: it uses recent conversation context to generate three follow-up suggestions and formats them for supported chat channels. Users should understand that recent chat content is used for generation.
Instruction Scope
The preferred command is /followups, but the manifest and docs also list broad natural-language triggers such as followups and suggestions, and documentation describes optional autoTrigger mode. These are disclosed and purpose-related, but could cause accidental invocation if the host platform matches triggers loosely.
Install Mechanism
Installation is conventional for an OpenClaw skill: ClawHub/manual install, Node requirement, and no install-time script or hidden downloader. The package has test/demo scripts but no automatic postinstall behavior.
Credentials
The main handler uses OpenClaw-native auth, while the standalone CLI can read OPENROUTER_API_KEY or ANTHROPIC_API_KEY and send recent exchanges to those providers. This is disclosed and proportionate to the optional CLI/provider feature.
Persistence & Privilege
No evidence of elevated privileges, destructive actions, broad local file access, or background persistence. The handler stores only temporary session mappings for numbered follow-up replies.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install smart-followups - After installation, invoke the skill by name or use
/smart-followups - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.1.8
Docs portability cleanup: replaced hardcoded log path examples with portable placeholders.
v2.1.6
Added prompt-injection boundary and aligned metadata/docs.
v2.1.5
Security: prompt injection boundary for conversation context in CLI.
v2.1.4
Fix: removed stale env var declarations from SKILL.md metadata. No API keys needed.
v2.1.3
Security: removed external API provider config from metadata. Handler uses OpenClaw-native auth only. CLI reference removed from skill config.
v2.1.2
Remove hardcoded DEFAULT_MODEL from CLI - now requires explicit --model flag, aligns with OpenClaw-native pattern
v2.1.1
smart-followups v2.1.1
- Documentation updates and cleanup across multiple files.
- No functional or API changes in this release.
v2.1.0
smart-followups 2.1.0
- Added official slash command support: `/followups` (plus aliases `/fu`, `/suggestions`, and `/next`)
- Improved SKILL docs to highlight slash command and its usage
- Updated triggers to include slash commands and new command aliases
- No API or authentication changes; usage remains the same across all supported channels
v2.0.1
Add ClawHub runtime requirements metadata (SKILL.md frontmatter)
v2.0.0
Clean v2.0.0 release - version consistency and cleanup
v1.0.7
Add runtime requirements metadata for ClawHub discovery
v1.0.9
- Renamed all references from "Clawdbot" to "OpenClaw" for platform consistency.
- Updated provider configuration and documentation defaults from "clawdbot" to "openclaw".
- Revised skill documentation and instructions across all major docs (README.md, SKILL.md, etc.).
- No changes to triggers, channel support, or core functionality.
v1.0.6
chore: ensure node_modules in .gitignore
v1.0.5
chore: ensure node_modules in .gitignore
v1.0.4
Update author email to [email protected]
v1.0.3
Honest ClawdHub listing - keyword triggers, not /slash commands
v1.0.2
Honest docs: keyword trigger not /slash command
v1.0.1
README branding update - clearer Clawdbot skill identity
v1.0.0
Initial release: 3 contextual suggestions, multi-channel support, Clawdbot native auth
Metadata
Frequently Asked Questions
What is Smart Follow-ups?
Generate contextual follow-up suggestions after AI responses. Shows 3 clickable buttons (Quick, Deep Dive, Related) when user types "/followups". It is an AI Agent Skill for Claude Code / OpenClaw, with 5110 downloads so far.
How do I install Smart Follow-ups?
Run "/install smart-followups" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Smart Follow-ups free?
Yes, Smart Follow-ups is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Smart Follow-ups support?
Smart Follow-ups is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Smart Follow-ups?
It is built and maintained by Robby (@robbyczgw-cla); the current version is v2.1.8.
More Skills