heartbeat
Heartbeat Skill
A self-monitoring system inspired by ZeroClaw's heartbeat architecture. This skill enables agents to perform periodic health checks, system diagnostics, and proactive maintenance without external triggers.
Purpose
The heartbeat system allows an agent to:
- Monitor its own health and resources
- Report status periodically
- Perform routine maintenance tasks
- Alert on anomalies or issues
- Stay "alive" and responsive
Key Concepts
Heartbeat Types
- health: System health check (disk, memory, process status)
- report: Generate and send status reports
- maintenance: Perform cleanup, optimization, or updates
- custom: User-defined heartbeat tasks
Configuration
The heartbeat is configured via HEARTBEAT.md in the workspace root:
# Heartbeat Configuration
- health: Check system health every 30 minutes
- report: Send status report every day at 9 AM
- maintenance: Run cleanup every Sunday at 2 AM
Tools Added
When this skill is active, the agent gains access to:
heartbeat_schedule
Schedule a new heartbeat task.
// Schedule a health check every 30 minutes
heartbeat_schedule({
name: "health-check",
type: "health",
interval: "30m",
enabled: true
})
heartbeat_run
Manually trigger a heartbeat task.
// Run a specific heartbeat
heartbeat_run({ name: "health-check" })
// Run all enabled heartbeats
heartbeat_run({ all: true })
heartbeat_list
List configured heartbeat tasks.
heartbeat_list({})
heartbeat_status
Check the status and results of heartbeat tasks.
// Get status of all heartbeats
heartbeat_status({})
// Get status of specific heartbeat
heartbeat_status({ name: "health-check" })
Usage in Agent Prompt
When this skill is active, include this context in your system prompt:
## Heartbeat System
You have access to a periodic self-monitoring system (heartbeat). Use it to:
- Monitor system health and resources
- Generate periodic status reports
- Perform routine maintenance
Available commands:
- `heartbeat_schedule` - Schedule a new recurring check
- `heartbeat_run` - Manually run a heartbeat task
- `heartbeat_list` - Show all configured heartbeats
- `heartbeat_status` - Check heartbeat status and results
Create HEARTBEAT.md in the workspace root to define your heartbeat tasks.
Integration with PopeBot
This skill integrates with PopeBot's cron system by:
- Reading heartbeat definitions from HEARTBEAT.md
- Converting them to cron-compatible schedules
- Storing heartbeat status in the logs directory
File Structure
.pi/skills/heartbeat/
├── SKILL.md # This file
├── lib/
│ ├── scheduler.js # Heartbeat scheduling logic
│ ├── runners.js # Built-in heartbeat runners
│ └── status.js # Status tracking
└── templates/
└── HEARTBEAT.md # Example configuration
More from winsorllc/upgraded-carnival
vector-memory
Vector-based semantic memory using embeddings for intelligent recall. Store and search memories by meaning rather than keywords. Use when you need semantic search, similar document retrieval, or context-aware memory.
131model-router
Route requests between different LLM providers and models. Configure routing rules, fallback providers, and model-specific parameters inspired by ZeroClaw and OpenClaw model routing systems.
63rss-monitor
Monitor RSS/Atom feeds and blogs for new content using feedparser.
59rss-reader
Read and parse RSS/Atom feeds. Use when: user wants to subscribe to feeds, get latest articles, or monitor news sources.
54video-frames
Production-grade video frame extraction with thumbnail grids, GIF creation, and batch frame processing. Includes intelligent quality presets, progress tracking, and comprehensive error handling.
39elevenlabs-tts
Convert text to speech using ElevenLabs API. Use when you need to generate voice audio for messages, narrations, or accessibility.
25