Skip to main content
prompt GP ChatGPT official · Anthropic

condense_trials — Claude Code prompt for trial digests

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.

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 condense_trials does

The prompt reads trial cards from analyses/<NCT>/card.md and the trials_index.csv index, then creates one Markdown digest. For each mechanism class, it lists programs and developers alongside trial size, duration, primary endpoint, status, and numerical findings. It adds brief observations connected to the report goal.

The result also contains a table of phase 3 and pivotal trials with primary findings, a planned-enrollment ranking of recruiting and upcoming trials, cross-trial observations, and open questions. NCT identifiers appear throughout. When a number check provides a corrected value, that value replaces the original; unverifiable figures retain the label “unverified.” The output goes in the digest_markdown field.

What it helps with

  • combine clinical-trial cards into one digest
  • compare trial findings by mechanism class and phase
  • summarize primary results from phase 3 and pivotal trials
  • rank recruiting and upcoming trials by planned enrollment
  • surface shared patterns and unanswered questions

Example prompts for the agent

  • Create a clinical-trial digest from the cards in analyses/ and trials_index.csv for a report on phase 2 to phase 3 translation.
  • Group programs by mechanism and phase, then rank recruiting and upcoming trials by planned enrollment.
  • Summarize trial findings for the report and return the result in digest_markdown.

How to install condense_trials

1Plugin marketplace

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

2Manually: put the files in place

.claude/commands/condense_trials.md

Questions about condense_trials

How do I install condense_trials in Claude Code?

Run these commands in order: /plugin marketplace add anthropics/life-sciences, then /plugin install clinical-trial-forecast@life-sciences. Use .claude/commands/condense_trials.md afterward.

What does condense_trials do?

It turns trial cards and an index into a Markdown digest organized by mechanism class and phase. The digest includes trial findings, summary tables, cross-trial observations, and open questions, with NCT identifiers throughout.

How does it handle corrected or unverified numbers?

A corrected value replaces the original. Unverifiable figures keep an “unverified” label.

Similar prompts

All prompts for Science and research →

From the same set29

The whole set →
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 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 card_checker The card_checker Claude Code prompt checks key figures against the sources cited in an answer. It flags mismatches in doses, study arms, timepoints, units, and populations. GP ChatGPT ★ 654repo stars apply_ledger The apply_ledger Claude Code prompt applies independent fact-check findings to a report section. It revises claims flagged in the ledger while preserving untouched content. GP ChatGPT ★ 654repo stars

Project sponsors

Companies that keep this analytics open