Works with the AI Agents you already use
condition based maintenance triggers
Evaluates sensor readings against thresholds to generate maintenance alerts, identify trends, and prioritize actions by severity.
$1.99
condition based maintenance triggers
Example session with this skill installed
Analyze these readings for Pump-01. Vibration: 8.5 mm/s (Warning: 7.0, Critical: 10.0). Temp: 92C (Warning: 85, Critical: 95). Previous vibration was 6.2 mm/s. All data from SCADA Export E1.
- Read your context and instructions
- Compiled the condition based maintenance
I have processed the sensor readings for Pump-01 against the defined thresholds using the analysis engine.
Condition-based Maintenance Triggers — Industrial Plant, 2024-05-20
1. Scope, sources and assumptions
- Sources: E1 (SCADA Export)
- Date: 2024-05-20
- Sensors: 2
- Readings: 2
- Assumptions: Trend threshold defaults to 10% (E1).
2. Summary
| Category | Count |
|---|---|
| Total Alerts | 2 |
| Critical | 0 |
| Warning | 2 |
| Healthy Sensors | 0 |
3. Critical alerts (immediate action required)
No critical alerts.
4. Warning alerts (schedule inspection)
| Sensor | Asset | Parameter | Value | Condition | Message |
|---|---|---|---|---|---|
| S-VIB-01 | Pump-01 | Vibration | 8.5 mm/s | Warning High | Value exceeds 7.0 threshold |
| S-TMP-01 | Pump-01 | Temp | 92 C | Warning High | Value exceeds 85 threshold |
5. Sensor status overview
| Sensor | Asset | Parameter | Status | Latest Value | Reading Count |
|---|---|---|---|---|---|
| S-VIB-01 | Pump-01 | Vibration | WARNING | 8.5 | 1 |
| S-TMP-01 | Pump-01 | Temp | WARNING | 92.0 | 1 |
6. Trend analysis
| Sensor | Parameter | Direction | Change % | Status |
|---|---|---|---|---|
| S-VIB-01 | Vibration | UP | 37.1% | ALERT |
| S-TMP-01 | Temp | N/A | 0.0% | INSUFFICIENT DATA |
7. Data quality and warnings
- Code W-01: Insufficient historical data for S-TMP-01 trend calculation.
8. Recommendations and items for human review
- Schedule vibration analysis for Pump-01 to investigate 37% increase (Computed result).
- Inspect cooling system for Pump-01 due to 92C temperature reading (Supplied threshold).
- Analytical estimate — validation required: Trend suggests accelerating wear on bearings.
This analysis supports, and does not replace, professional judgment and on-site inspection.
Management decision required for any equipment shutdown.
Next steps
- Verify the accuracy of the SCADA Export E1 sensor calibration.
- Dispatch a technician to perform a manual heat scan on Pump-01.
- Provide more historical data for S-TMP-01 to enable trend monitoring.
Connects securely to your tools. The creator never sees your data.
About this skill
Industrial asset management requires precision that manual data entry and generic prompts cannot provide. This skill evaluates raw sensor readings against specific operating thresholds to identify maintenance triggers and anomalies before they lead to failure. It uses a deterministic script to process snapshots of temperature, vibration, pressure, and other critical metrics with exact decimal accuracy.
What it does
- Threshold Monitoring compares real-time and historical sensor values against warning and critical limits.
- Alert Generation produces categorized maintenance triggers based on breach severity.
- Trend Analysis calculates percentage changes over time to identify developing equipment issues.
- Data Quality Assessment flags suspect readings, unknown sensors, and insufficient data points.
- Prioritized Recommendations ranks necessary maintenance actions to ensure urgent conditions are addressed first.
How it works
- The developer provides sensor configurations (thresholds, units, trend percentages) and reading snapshots.
- The skill constructs a structured
request.jsonfor deterministic processing. - A backend script executes the analysis, ensuring no rounding errors or manual estimation.
- The skill generates a formal maintenance report with prioritized alerts, trend tables, and data quality warnings.
Frameworks & tools
The skill utilizes a self-contained Python analysis engine for threshold evaluation and trend calculation. It follows a strict JSON-schema-based input/output workflow.
Why this beats prompting it yourself
Generic LLM prompting often leads to hallucinated thresholds or mathematical errors in trend calculations. This skill offloads the logic to a deterministic script, ensuring every alert is based on exact data breaches rather than probabilistic guesses.
Use cases
- Monitoring vibration and temperature in industrial pumps to trigger warning alerts.
- Analyzing pressure drops across filter systems to schedule preventive cleaning.
- Identifying developing trends in motor current that suggest impending bearing failure.
- Auditing sensor data quality across large asset fleets to find faulty instrumentation.
Known limitations
Does not support predictive machine learning models or complex failure forecasting. Limited to processing supplied snapshots rather than real-time SCADA streams.
Requires manual sensor configuration and readings as snapshots. Does not perform root cause analysis or real-time SCADA integration. Not for predictive ML forecasting.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 day ago