# trial_checklist_worker

The trial_checklist_worker Claude Code prompt analyzes one clinical trial against a fixed question group. It draws on registry records, project files, and research sources.

- 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_worker.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-worker

## What it does

The prompt produces structured answers about one clinical trial, using a supplied report goal and set of questions. Each item gets a result in the requested JSON format, a short explanation, a confidence level, sources, and gaps. It also lists paywalled papers that could materially improve the answers and findings that fall outside the assigned questions.

Sources follow a set order: the registry record, project files, clinical-trial and PubMed MCP tools, then web search. Non-registry facts need inline citations, and numerical results retain their units and timepoints. Inferences are labelled. Read PDFs directly; tables and figures in the document take precedence over extracted text. The analysis needs populated template values, including the indication, audience, report goal, and question list.

## 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_worker.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_worker.md

## When to use it
- answer a fixed set of questions about one clinical trial
- compare registry details with project files and research papers
- record responder numerators and denominators by trial arm
- separate sourced facts from inferences and data gaps

## Example prompts
- Analyze one trial for the melanoma indication and answer the efficacy question group.
- Compare registry and paper results for this trial, with citations, confidence levels, and gaps.
- Prepare structured answers for a trial report focused on the key endpoint.

## Similar
- [clinical-trial-protocol-skill](https://affpapa.org/en/nevibecode/skills/clinical-trial-protocol-skill.md) — skill · 469 installs
- [tooluniverse-clinical-trial-design](https://affpapa.org/en/nevibecode/skills/tooluniverse-clinical-trial-design.md) — skill · 463 installs
- [tooluniverse-clinical-trial-matching](https://affpapa.org/en/nevibecode/skills/tooluniverse-clinical-trial-matching.md) — skill · 411 installs
- [math-proof-worker-deep](https://affpapa.org/en/nevibecode/agents/math-proof-worker-deep.md) — subagent · ★ 47914 repo stars
- [academic-revision-checklist](https://affpapa.org/en/nevibecode/skills/academic-revision-checklist.md) — skill · ★ 88 repo stars
- [TARGET Checklist MCP](https://affpapa.org/en/nevibecode/mcp/target-checklist-mcp.md) — MCP server

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
