heartbeatAuto-learns when to wake. Balances responsiveness with efficiency, grows autonomy over time.
Install via ClawdBot CLI:
clawdbot install ivangdavila/heartbeatThis skill auto-evolves. Start conservative, learn patterns, confirm before assuming.
Core Loop:
Check intervals.md for timing strategies. Check triggers.md for event-based waking.
| Level | Interval | When |
|-------|----------|------|
| active | 5-15 min | Ongoing conversation, urgent monitor |
| watching | 30-60 min | Waiting for specific event |
| idle | 2-4 hours | Nothing pending, background checks |
| dormant | 4-8 hours | Night, inactive periods |
Default to idle. Promote/demote based on context and learned patterns.
dormant unless emergencywatching until completeOne line: trigger: interval (level) [hit rate]
Examples:
email/urgent: 30min (watching) [80% useful]calendar/upcoming: 2h (idle) [confirmed]deploy/monitor: 10min (active) [until complete]social/mentions: 4h (idle) [low value, user said skip]Phrases that adjust autonomy:
After pattern emerges: Confirm before internalizing. "I notice X rarely needs checking—reduce to every 4h?"
Empty sections = still learning. Observe utility of each wake, propose adjustments.
Generated Mar 1, 2026
The Heartbeat skill can monitor support ticket queues, automatically waking to check for high-priority or urgent tickets based on learned patterns. It adapts intervals during peak hours (active level) and reduces checks during off-hours (dormant level), improving response times while conserving resources.
In IT operations, Heartbeat manages wake intervals for system health checks, such as server uptime or deployment status. It starts conservatively, learns optimal monitoring frequencies for different components, and adjusts based on triggers like alerts or sub-agent tasks, ensuring efficient oversight without unnecessary interruptions.
For social media teams, Heartbeat auto-adapts to check mentions, comments, or trends. It learns when high-engagement periods occur, shifting between active and idle levels, and respects user input to ignore low-value notifications, balancing timely responses with focused work periods.
Heartbeat helps individuals manage tasks by waking to check email, calendar events, or reminders. It observes user habits, confirms before changing intervals, and respects quiet times like sleep hours, promoting autonomy while minimizing disruptions in daily workflows.
In e-commerce, Heartbeat monitors order statuses, inventory updates, and customer inquiries. It adapts wake levels based on sales volume, using watching mode for pending orders and idle for background checks, optimizing operational efficiency during high-demand periods.
Offer Heartbeat as a cloud-based service with tiered pricing based on features like number of monitors or integration depth. Revenue comes from monthly or annual subscriptions, targeting businesses needing adaptive automation without heavy upfront costs.
Sell Heartbeat through enterprise licenses for large organizations, including customization, dedicated support, and on-premise deployment options. Revenue is generated via one-time fees or annual contracts, focusing on scalability and security for critical operations.
Provide a free basic version of Heartbeat with limited monitors and intervals, then upsell to premium features like advanced pattern learning or API integrations. Revenue streams from in-app purchases or upgrade subscriptions, appealing to small teams and individual users.
💬 Integration Tip
Start by integrating Heartbeat with one data source, such as email or a calendar API, to observe initial patterns and confirm adjustments before scaling to multiple monitors.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.
OpenClaw CLI wrapper — gateway, channels, models, agents, nodes, browser, memory, security, automation.
MoltGuard — runtime security plugin for OpenClaw agents by OpenGuardrails. Helps users install, register, activate, and check the status of MoltGuard. Use wh...