Skip to main content
prompt GP ChatGPT official · Anthropic

followup_triage — Claude Code prompt: purpose and install

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.

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 followup_triage does

followup_triage reviews questions raised after a research iteration and selects up to {{k}} for another round. It combines duplicates, removes items that existing evidence has settled or reachable sources cannot answer, then rewrites the rest as precise questions that stand on their own.

It checks knowledge/<section>.md, knowledge/open_questions.json, and prior answers in research/{{iteration_dir}}/ before making its selection. The result includes each question’s section, rationale, answer criteria, priority, and potential to change the recommendation. It also reports whether research should stop and lists sources that could not be obtained.

The project’s knowledge files and earlier answers are needed for the comparison; without them, the prompt cannot check which questions are already covered.

What it helps with

  • choose questions for another research round
  • combine duplicate follow-ups
  • remove questions already answered
  • flag questions that could change a recommendation

Example prompts for the agent

  • Review the researchers’ follow-up questions and select those that could change the recommendation.
  • Compare these questions with the project materials, merge duplicates, and prepare the next research list.
  • Sort the open questions by priority and identify any sources the project cannot access.

How to install followup_triage

1Plugin marketplace

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

2Manually: put the files in place

.claude/commands/followup_triage.md

Questions about followup_triage

How do I install followup_triage in Claude Code?

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

What does followup_triage do?

It filters and rewrites researchers’ follow-up questions for another research round, removing duplicates and questions already resolved by project evidence.

Which project files does followup_triage read?

It checks knowledge/<section>.md, knowledge/open_questions.json, and prior answers under research/{{iteration_dir}}/.

Similar prompts

All prompts for Science and research →

From the same set29

The whole set →
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 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 condense_trials The condense_trials prompt for Claude Code turns clinical-trial cards into a single digest. It groups programs by mechanism and phase, with findings tied to the report goal. GP ChatGPT ★ 654repo stars condense_part condense_part is a Claude Code prompt that trims a clinical forecast report section to a word limit. It keeps key figures, tables, and citations intact. GP ChatGPT ★ 654repo stars classify_trial The classify_trial Claude Code prompt classifies clinical trial records for a specified indication. It takes one registry entry and returns data in a JSON schema. GP ChatGPT ★ 654repo stars

Project sponsors

Companies that keep this analytics open