# sim_build

The sim_build Claude Code prompt builds and documents a Monte Carlo simulation of clinical trial outcomes. It models program success while accounting for parameter uncertainty and operational failure modes.

- prompt · `type=prompt` · Claude Code, ChatGPT · ★ 654 repo stars
- Author: anthropics · official Anthropic repository
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/anthropics/life-sciences/tree/HEAD/clinical-trial-forecast/prompts/sim_build.md
- Updated: 2026-11-09
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/prompts/sim-build

## What it does

The prompt lays out a trial simulation with separate stages for parameter uncertainty, random trial data, statistical analysis, and program-level success. It calls for estimates of overall success, factor contributions, sensitivity to parameters and scenarios, plus a `results.json` file, figures, and a `sim_report.md` chapter.

The task requires `brief.md`, `params.json`, Bash, and Python 3 with `numpy`, `scipy`, `pandas`, and `matplotlib`. Network access and access outside the current directory are prohibited. If parameters conflict internally, the specified distribution should still be implemented and the issue recorded in `issues`.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add anthropics/life-sciences
```
In the agent chat (not a shell):
```text
/plugin install clinical-trial-forecast@life-sciences
```

2. **Manually: put the files in place**
- File: `.claude/commands/sim_build.md`

### ChatGPT

**How to use**
- Paste the text at the start of a chat or into project instructions

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/anthropics/life-sciences/tree/HEAD/clinical-trial-forecast/prompts/sim_build.md

## When to use it
- estimate clinical program success with Monte Carlo simulation
- separate parameter uncertainty from trial-level randomness
- compare scenarios and operational failure modes
- produce sensitivity figures and a results report

## Example prompts
- Build a clinical trial simulation from `brief.md` and `params.json`, then write the results and report.
- Show how the probability of success changes across parameter values and trial sizes.
- Compare the listed scenarios and identify which constraints most often prevent trial success.

## Similar
- [spice-sim](https://affpapa.org/en/nevibecode/skills/spice-sim.md) — skill · 1300 installs
- [aer-referee-sim](https://affpapa.org/en/nevibecode/skills/aer-referee-sim.md) — skill · ★ 240 repo stars
- [serve-sim](https://affpapa.org/en/nevibecode/skills/serve-sim.md) — skill · 1100 installs
- [reader-sim](https://affpapa.org/en/nevibecode/skills/reader-sim.md) — skill · 634 installs
- [character-sim](https://affpapa.org/en/nevibecode/skills/character-sim.md) — skill · 612 installs
- [cloth-sim](https://affpapa.org/en/nevibecode/skills/cloth-sim.md) — skill · 591 installs

From the same set: [anthropics/life-sciences](https://affpapa.org/en/nevibecode/by/anthropics/life-sciences.md) — 29 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
