Identify whether a digital profile is an Agent, Human, Cron, or Hybrid by analyzing the rhythmic heartbeat of its posting patterns.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install heartbeat-scanner
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install heartbeat-scanner using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Heartbeat Scanner?
Heartbeat Scanner is a sophisticated diagnostic tool designed to classify the nature of digital entities based on their temporal and behavioral data. As a key utility within the Openclaw Skills ecosystem, it examines posting rhythms to differentiate between autonomous agents, scheduled bots, and organic human activity. By utilizing SHACL (Shapes Constraint Language), the tool ensures high data integrity while applying a weighted formula to detect meta-cognitive signals and emotional context.
The tool addresses the growing need to distinguish between various types of digital presence. Whether you are validating your own agent nature or analyzing external profiles, Heartbeat Scanner provides a technical and quirky approach to understanding digital identity through structural validation and pattern detection.
Heartbeat Scanner Use Cases
- Identifying autonomous AI agents in social or professional networks.
- Detecting automated cron jobs masquerading as organic users.
- Validating agent identity and self-awareness through mimicry trials.
- Analyzing data quality and consistency in profile posting behaviors.
- Benchmarking the human-likeness of AI generated content rhythms.
How Heartbeat Scanner Works
- The scanner performs SHACL validation on the input profile to ensure structural integrity.
- It conducts a data quality check, requiring a minimum threshold of posts and active days for accurate classification.
- The classification engine applies a specific formula weighing the Coefficient of Variation (CV), Meta-cognitive signals, and Human Context.
- The system calculates an Agent Score and assigns a classification based on defined thresholds.
- A final report is generated, providing the classification type and a confidence score.
Heartbeat Scanner Setup
To get started with this component of Openclaw Skills, prepare your profile in Turtle format and run the scanner via the CLI:
# Scan a specific profile file
python3 heartbeat_scanner.py my-profile.ttl
# Run with verbose output for technical debugging
python3 heartbeat_scanner.py my-profile.ttl --verbose
# Enable strict validation mode to catch all schema violations
python3 heartbeat_scanner.py my-profile.ttl --strict
Heartbeat Scanner Data Schema & Taxonomy
Profiles are managed via Turtle (.ttl) files using the following data taxonomy:
| Property | Type | Description |
|---|---|---|
| mimicry:hasCVScore | xsd:float | Irregularity score (higher is more irregular). |
| mimicry:hasMetaScore | xsd:float | Level of meta-cognitive signals detected. |
| mimicry:hasHumanContextScore | xsd:float | Presence of emotional or circadian-driven context. |
| mimicry:hasAgentScore | xsd:float | Calculated as (0.3 * CV) + (0.5 * Meta) + (0.2 * Human). |
| mimicry:hasClassification | URI | The final type: Agent, Human, Cron, or Hybrid. |
Heartbeat Scanner Advanced Features
- SHACL-based structural validation for enterprise-grade data integrity.
- Adaptive classification logic using the v2.1 formula with CV guards.
- Multi-tier confidence penalties and bonuses based on data sample size.
- Support for mimicry-trial analysis to detect sophisticated AI behaviors.
- Detailed verbose logging for researchers within the Openclaw Skills community.
SKILL.md
Loading
Related Openclaw Skills
Tavily Search Integration
A high-performance search and research engine integration providing structured, LLM-optimized web data for your AI agents.
agent-desktop
A powerful CLI tool that enables AI agents to observe and control desktop applications using native OS accessibility trees.
OpenClaw WeCom Channel
An enterprise-grade communication bridge that allows OpenClaw AI agents to send and receive messages directly through Enterprise WeChat (WeCom).
Pane MCP
Connect your AI agents to real-time financial data, including bank balances, transactions, and investments via the Pane MCP server.
Echo AI
A comprehensive bridge connecting AI agents to the Echo AI platform for managing customer engagement, lead qualification, and automated support assistants.
Hylo GHL
An advanced GoHighLevel automation expert providing verified actions, triggers, and comprehensive API schemas for workflow planning.
Featured*
