Skip to main content
prompt GP ChatGPT official · Anthropic

narrative_editor — Claude Code prompt: clinical forecast summary

The narrative_editor Claude Code prompt drafts Summary and Methods sections for a clinical-trial forecast. It ties the probability estimate to model evidence and trial details.

no license ★ 654 updated 2026-11-09

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add anthropics/life-sciences
/plugin install clinical-trial-forecast@life-sciences
Open on GitHub

What narrative_editor does

The prompt drafts Summary and Methods sections for a clinical-trial forecast report. It checks the Summary against the staged narrative and files containing statistics, results, and figure captions. It also reads text and notes under intake, plus report/claim_ledger.md when that file exists.

The Summary covers the headline forecast and its intervals, the factors driving uncertainty, recommendations, and a table of trial facts. For each key factor, the prompt asks for a plain-language explanation, supporting trial names and figures, and probabilities at the factor’s low and high values. Methods gives a short account of evidence gathering and checks, modelling, and claim verification; the code and parameter sheet are in sim/.

Web access is disallowed, and sponsor disclosures must be distinguished from observed facts. Installation in Claude Code uses both marketplace commands and the prompt file at .claude/commands/narrative_editor.md.

What it helps with

  • draft a clinical-trial forecast summary from report materials
  • show which uncertainties move the forecast probability most
  • assemble trial design, population, and timing details in a table
  • describe the evidence checks and modelling process

Example prompts for the agent

  • Draft the forecast Summary from the report files and the data in sim.
  • Explain which factors drive the probability and show the estimate at each factor’s low and high values.
  • Prepare the Methods section and trial table for the report.

How to install narrative_editor

1Plugin marketplace

/plugin marketplace add anthropics/life-sciences
/plugin install clinical-trial-forecast@life-sciences

2Manually: put the files in place

.claude/commands/narrative_editor.md

Questions about narrative_editor

How do I install narrative_editor in Claude Code?

Run these commands in order: /plugin marketplace add anthropics/life-sciences, then /plugin install clinical-trial-forecast@life-sciences. The prompt file is .claude/commands/narrative_editor.md.

What does narrative_editor do?

It drafts a forecast Summary with uncertainty drivers and a trial-facts table, then writes a short Methods section. It draws on report materials and simulation data.

Which files does narrative_editor read for the Summary?

It reads report/parts/narrative.md, sim/summary_stats.json, sim/results.json, sim/figures/captions.json, intake/text/*.txt, and intake/notes/*.md. It also uses report/claim_ledger.md if present.

Similar prompts

All prompts for Science and research →

From the same set29

The whole set →
sim_brief The sim_brief Claude Code prompt guides a clinical-trial simulation and its report. It runs when an agent is asked to implement a model from params.json. GP ChatGPT ★ 654repo stars researcher researcher is a Claude Code prompt for answering one research question about an indication. It draws on project files and external sources, checks figures, and returns cited findings. GP ChatGPT ★ 654repo stars research_planner The research_planner Claude Code prompt plans the next research round for a report on a medical indication. It prioritizes questions that could shift a recommendation or narrow decision-critical estimates. GP ChatGPT ★ 654repo stars narrative_writer The narrative_writer prompt for Claude Code and ChatGPT builds a narrative section for a clinical-trial forecast report. It traces the model from phase 2 evidence to the estimated probability of a phase 3 outcome. GP ChatGPT ★ 654repo stars integrator integrator is a Claude Code and ChatGPT prompt that synthesizes evidence and new research answers into a cited report section, tracking source disagreements and open questions. GP ChatGPT ★ 654repo stars 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. GP ChatGPT ★ 654repo stars followup_triage The followup_triage prompt for Claude Code and ChatGPT sorts researchers’ follow-up questions for another research round. It removes duplicates and questions already answered. GP ChatGPT ★ 654repo stars copyedit_section copyedit_section — a Claude Code prompt revises clinical-trial forecast sections. It reshapes dense prose while retaining figures, citations, and document structure. GP ChatGPT ★ 654repo stars

Project sponsors

Companies that keep this analytics open