Skip to main content
prompt GP ChatGPT official · Anthropic

research_planner — Claude Code prompt: purpose and setup

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.

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 research_planner does

The prompt selects follow-up research questions using the report’s goal, the decision it informs, and the evidence gaps that matter most. Questions must be specific and answerable through public sources such as trial registries, papers, and regulatory materials.

It reads intake files alongside existing evidence summaries, trial cards, and simulation notes before planning. Earlier unanswered questions remain in scope when they are still relevant. A source blocked by access or format problems is excluded from future questions unless a new route to it is available.

When an independent number check marks a value as corrected, the prompt uses that value instead of the earlier one; unverifiable figures retain the “(unverified)” label. It also decides whether another research round is warranted and which report sections to pause.

What it helps with

  • prioritize questions that could change a recommendation
  • find evidence gaps in weaker report sections
  • tighten estimates used by a decision or simulation
  • avoid repeating searches for inaccessible sources

Example prompts for the agent

  • Plan the next research questions using the report goal and unresolved evidence gaps.
  • Identify trial evidence that could change the recommendation.
  • Revise the question plan around blocked sources and independently checked figures.

How to install research_planner

1Plugin marketplace

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

2Manually: put the files in place

.claude/commands/research_planner.md

Questions about research_planner

How do I install research_planner in Claude Code?

Run /plugin marketplace add anthropics/life-sciences, then /plugin install clinical-trial-forecast@life-sciences. The command file path is .claude/commands/research_planner.md.

What does research_planner do?

It plans follow-up research questions, prioritizing evidence that could affect a recommendation or sharpen estimates used for a decision.

How does the prompt handle sources that cannot be accessed?

It records the blocked source and the reason, then avoids questions that depend on it. A question can return if a new way to reach the information emerges.

Similar prompts

All prompts for Science and research →

From the same set29

The whole set →
sim_critic The sim_critic Claude Code prompt audits a Monte Carlo clinical-trial model against its evidence, code, results, and report. It flags calibration issues and returns a verdict with ranked change requests. GP ChatGPT ★ 654repo stars 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. GP ChatGPT ★ 654repo stars 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 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 narrative_editor 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. 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

Project sponsors

Companies that keep this analytics open