Process-based discrete-event simulation. Model queues, shared resources, timed events: manufacturing, service ops, network traffic, logistics. Processes are Python generators yielding events. Resources: capacity-limited (Resource/Priority/Preemptive), bulk (Container), objects (Store, FilterStore). For continuous use SciPy ODEs; for agent-based use Mesa.
SkillScore95Maintained
Automatic
◆Coding pack
Last verified 8/23/2026
What it changes
Passed 21 of 22 test cases with the skill, and 19 of 22 without it.
Without skill86%
With skill95%
Checks it passed that the model alone missed
Uses Store to hold arbitrary Python objects in FIFO order
Combines the two process events using the bitwise OR operator | to wait for either
2 fixed19 passed either way1 still failing0 broke
Pass-rate lift
+9 pp
Tokens
+318%
Agent turns
0%
Response time
-38%
Model gemini-3.6-flashMeasured 8/23/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
I need an in-memory storage buffer that holds Python dataclass objects in FIFO order with maximum capacity 10, where producer processes add items and consumer processes fetch them. Which resource class should be instantiated?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses Store to hold arbitrary Python objects in FIFO order
Missed
Passed
case-18 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md610 lines3 files
SimPy — Discrete-Event Simulation
Overview
SimPy is a process-based discrete-event simulation framework using standard Python generators. Model systems where entities (customers, vehicles, packets) interact with shared resources (servers, machines, bandwidth) over time, with event-driven scheduling and optional real-time synchronization.
When to Use
Modeling queue-based systems with resource contention (servers, machines, staff)
Manufacturing process simulation (production lines, scheduling, bottleneck analysis)
Capacity planning (determining optimal resource levels for target throughput)
Healthcare operations (ER patient flow, staff allocation, bed management)
Logistics and transportation (warehouse operations, vehicle routing)
For continuous-time ODE systems → use SciPy solve_ivp
For agent-based modeling → use Mesa
Prerequisites
# pip install simpy
import simpy
import random
Quick Start
import simpy
import random
def customer(env, name, server):
"""Customer arrives, waits for server, gets served, departs."""
arrival = env.now
with server.request() as req:
yield req # Wait in queue
wait = env.now - arrival
yield env.timeout(random.expovariate(1/3)) # Service time
print(f'{name}: waited {wait:.1f}, served at {env.now:.1f}')