/simulate

> Run scenario simulations to explore outcomes before committing to a decision.

170 stars

byMiosa-osa

View on GitHub Installation ↓

Best use case

/simulate is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

> Run scenario simulations to explore outcomes before committing to a decision.

Teams using /simulate should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/simulate/SKILL.md --create-dirs "https://raw.githubusercontent.com/Miosa-osa/canopy/main/library/skills/strategy/simulate/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/simulate/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How /simulate Compares

Feature / Agent	/simulate	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

> Run scenario simulations to explore outcomes before committing to a decision.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# /simulate

> Run scenario simulations to explore outcomes before committing to a decision.

## Usage
```
/simulate "<scenario>" [--branches <n>] [--depth <n>]
```

## What It Does
Takes a scenario or decision and simulates multiple outcome branches. Uses Monte Carlo tree search to explore the decision space, evaluating each branch on probability and impact. Returns a ranked set of outcomes with recommended actions.

## Implementation
Runs: `cd engine && mix optimal.simulate`

Process:
1. **Parse scenario** -- extract the decision point, actors, constraints, and unknowns.
2. **Generate branches** -- produce N possible outcomes (default: 3).
3. **Evaluate** -- score each branch on probability (0-1) and impact (positive/negative).
4. **Simulate forward** -- for each branch, simulate 2nd-order effects.
5. **Rank** -- order by expected value (probability x impact).
6. **Report** -- structured outcome tree with recommended action.

## Examples
```bash
# Simulate a pricing decision
/simulate "What happens if we raise AI Masters to $2K/seat?"

# Simulate with more branches
/simulate "Bennett leaves the team" --branches 5

# Deeper simulation
/simulate "We launch the platform in Q2 vs Q3" --depth 3
```

## Command