# forecast_scope

The forecast_scope Claude Code prompt sets up a probability-of-technical-success forecast for a registered clinical trial. It turns the request and registry record into a project.json configuration.

- 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/forecast_scope.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/forecast-scope

## What it does

The prompt builds `project.json` for a forecast about one registered clinical trial. It reads `question.md` and the trial record at `raw/ctgov/{{focal_nct}}.json`; it also uses `intake/notes/background.md` when that file exists. The output captures the asset, indication, enrolled population, endpoint, success criteria and trial design.

The configuration also defines analysis sections, simulation parameters and registry searches for precedent trials. This step has no web access, so it relies on the supplied files and specialist knowledge. Background details marked confidential stay out of fields passed to web researchers.

## 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/forecast_scope.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/forecast_scope.md

## When to use it
- set forecast parameters for a registered clinical trial
- define the endpoint and technical-success criteria
- prepare research questions about precedent trials
- create a project configuration for later research steps

## Example prompts
- Run `/clinical-trial-forecast:forecast_scope` to set up a forecast using the trial in `question.md`.
- Create `project.json` from the request and the record in `raw/ctgov/{{focal_nct}}.json`.
- Use `intake/notes/background.md` when available, but leave confidential details out of the public thesis.

## Similar
- [GribStream.com Historical Weather Forecast API](https://affpapa.org/en/nevibecode/mcp/gribstreamcom-historical-weather-forecast-api.md) — MCP server · 2733 installs
- [earth2studio-deterministic-forecast](https://affpapa.org/en/nevibecode/skills/earth2studio-deterministic-forecast.md) — skill · 1900 installs
- [exam-forecast](https://affpapa.org/en/nevibecode/skills/exam-forecast.md) — skill · 667 installs
- [scope-framing](https://affpapa.org/en/nevibecode/skills/scope-framing.md) — skill · ★ 348 repo stars
- [sales-forecast-diagnostic](https://affpapa.org/en/nevibecode/skills/sales-forecast-diagnostic.md) — skill · 27600 installs
- [Weather API — Current & 7-Day Forecast Worldwide](https://affpapa.org/en/nevibecode/mcp/weather-api-current-7-day-forecast-worldwide.md) — MCP server · 4044 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
