Skip to main content
prompt GP ChatGPT official · Anthropic

verify_claim — Claude Code prompt for claim checks

The verify_claim Claude Code prompt checks a claim from a clinical research report against primary sources. It tests figures and conditions, finds trial examples, then returns a verdict.

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 verify_claim does

The prompt examines one claim about a drug or indication. It identifies testable statements, searches primary sources, and compares the claim with real trial examples. It can draw on project files such as registry records, trial analyses, article texts, and simulation inputs and outputs. If evidence comes only from secondary sources, the result should say so.

It also flags omitted study conditions and possible reading errors, such as using the wrong arm, timepoint, or denominator. A separate check distinguishes observed results from sponsor plans and estimates. The response ends with a verdict, confidence level, and corrected wording where needed. It requires access to project data, the clinical_trials and pubmed MCP connectors, WebSearch, and the tools in {{fetch_tools}}.

What it helps with

  • check a report figure against a primary source
  • find study conditions that affect a reported result
  • compare a claim with named trials and their identifiers
  • separate sponsor plans from observed outcomes
  • correct a claim based on the wrong arm or timepoint

Example prompts for the agent

  • Check the claim “{{claim}}” from a report on {{indication}} for {{asset}} against primary sources.
  • Compare this report figure with trial registry records and papers; list the conditions and confidence level.
  • Check whether the report presents a sponsor plan as an observed result, then rewrite the claim accurately.

How to install verify_claim

1Plugin marketplace

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

2Manually: put the files in place

.claude/commands/verify_claim.md

Questions about verify_claim

How do I install verify_claim in Claude Code?

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

What does verify_claim do?

It checks a single claim from a clinical research report against primary sources. It flags omitted conditions and likely interpretation errors, then returns a verdict with a confidence level.

What does verify_claim need to run?

It needs access to project data, the clinical_trials and pubmed MCP connectors, WebSearch, and the tools in {{fetch_tools}}.

Similar prompts

All prompts for Science and research →

From the same set29

The whole set →
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. GP ChatGPT ★ 654repo stars 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. GP ChatGPT ★ 654repo stars sim_spec The sim_spec Claude Code prompt turns assembled trial evidence into a parameter sheet for a Monte Carlo model. A separate builder implements that sheet. GP ChatGPT ★ 654repo stars sim_finalize The sim_finalize prompt for Claude Code prepares a report on an accepted clinical-trial simulation. Run it to assemble the model description, summary measures, and figures. GP ChatGPT ★ 654repo stars 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

More in the catalog

Project sponsors

Companies that keep this analytics open