# trial_checklist_condense

The trial_checklist_condense Claude Code prompt condenses one clinical trial’s item-level analysis into a report and a searchable card. It draws from analysis files and a trial registry summary.

- 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/trial_checklist_condense.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/trial-checklist-condense

## What it does

The prompt creates `analysis_markdown` and `card_markdown` for a single trial, then returns lists of key facts and gaps. It reads JSON files for answered items in `analyses/{{nct}}/items/` and the registry summary at `trials/{{nct}}.json`; claims and citations come from those files.

The analysis contains sections grouped by worker, cited facts, gaps, and adjacent findings. The card captures trial details and results by arm when the source files contain them. The analysis limit is 2,500 words; the card limit is 250 words.

The prompt needs both the item files and registry summary to produce its output. Citations must retain their original wording.

## 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/trial_checklist_condense.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/trial_checklist_condense.md

## When to use it
- combine item-level findings into one trial analysis
- create a compact card for later agent searches
- extract cited facts and confidence levels
- record evidence gaps and paper requests

## Example prompts
- Condense trial `{{nct}}` for a `{{report_kind}}` on `{{indication}}`, with the goal `{{goal}}`.
- Turn the findings for trial `{{nct}}` into an analysis document and a searchable card.

## Similar
- [tooluniverse-clinical-trial-design](https://affpapa.org/en/nevibecode/skills/tooluniverse-clinical-trial-design.md) — skill · 463 installs
- [clinical-trial-protocol-skill](https://affpapa.org/en/nevibecode/skills/clinical-trial-protocol-skill.md) — skill · 469 installs
- [tooluniverse-clinical-trial-matching](https://affpapa.org/en/nevibecode/skills/tooluniverse-clinical-trial-matching.md) — skill · 411 installs
- [TARGET Checklist MCP](https://affpapa.org/en/nevibecode/mcp/target-checklist-mcp.md) — MCP server
- [clinical-reports](https://affpapa.org/en/nevibecode/skills/clinical-reports.md) — skill · 77 installs
- [academic-revision-checklist](https://affpapa.org/en/nevibecode/skills/academic-revision-checklist.md) — skill · ★ 88 repo stars

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
