Works with the AI Agents you already use
discrete event simulation model designer
Guessing at system capacity leads to bottlenecks or wasted overhead.
$2.99
discrete event simulation model designer
Example session with this skill installed
Design a DES model for a clinic with 3 doctors. Patients arrive at 12/hour. Mean service time is 12 minutes. Calculate wait times and utilization for a 10-hour horizon.
- Read your context and instructions
- Compiled the discrete event simulation
I have modeled the clinic scenario as an M/M/3 queueing system. The arrival rate is 12 patients per hour, with each of the 3 doctors providing service at a mean rate of 5 patients per hour.
Simulation Performance Metrics
| Metric | Value | Unit |
|---|---|---|
| Throughput | 12 | patients/hour |
| Server Utilization | 80.00 | % |
| Avg. Queue Length | 2.2222 | patients |
| Avg. Wait Time in Queue | 11.1111 | minutes |
| Avg. Time in System | 23.1111 | minutes |
| Probability of Waiting | 64.89 | % |
Model Assumptions
- Arrivals follow a Poisson distribution (12/hr).
- Service times follow an exponential distribution (mean 12 min).
- System is stable (utilization < 100%).
- Analytical estimate — validation required if service times are non-exponential.
Next steps
- Validate if patient arrival patterns are consistent throughout the 10-hour horizon.
- If wait times exceed targets, run a scenario with 4 doctors to compare utilization.
- Review the
calculation_tracein the raw output for formula verification.
Connects securely to your tools. The creator never sees your data.
About this skill
Guessing at system capacity leads to bottlenecks or wasted overhead. Manual queueing calculations are error-prone and difficult to scale across complex processes.
This skill builds deterministic discrete-event simulation (DES) models from event tables and resource schedules to compute precise steady-state performance metrics. It eliminates the guesswork in capacity planning by applying M/M/c queueing theory to your process data.
What it does
- Model specification defines DES models from arrival rates, service process definitions, and resource pools.
- Performance computation calculates expected throughput, average queue lengths, and wait times.
- Utilization analysis determines server utilization percentages and the probability of arrivals needing to wait.
- Steady-state estimation provides total time-in-system metrics (queue plus service) using mathematical formulas.
- Validation markers flags results requiring organizational validation or management decisions.
How it works
- Register source documents to establish a clear citation trail for all arrival and service facts.
- Define process parameters including arrival rates, service time means, and resource pool counts.
- Generate a structured request to trigger the computation engine.
- Review the performance metrics table and address any instability or field warnings.
Frameworks & tools
The skill uses a Python-based computation engine and JSON schema validation. It relies on M/M/c queueing theory formulas for steady-state analysis.
Why this beats prompting it yourself
Generic prompts often struggle with the mathematical precision required for M/M/c formulas and multi-server utilization logic. This skill follows a rigorous computation trace, ensuring results are calculated via a verified engine rather than probabilistic LLM guessing.
Use cases
- Estimate throughput and bottlenecks for a new customer service workflow.
- Plan server or staff capacity based on projected arrival rates and service times.
- Analyze the impact of adding resources on average wait times and queue lengths.
- Verify system stability by checking if service capacity exceeds arrival rates.
Known limitations
Assumes M/M/c conditions (Poisson arrivals, exponential service). Not for interval-based staff rostering or scheduling. Requires Python 3 for the computation script.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Assumes M/M/c conditions (Poisson arrivals, exponential service). Not for interval-based staff rostering or scheduling. Requires Python 3 for the computation script.
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 buying a skill.
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 2 days ago