Skip to main content
prompt GP ChatGPT official · Anthropic

card_checker — Claude Code prompt: number checks and install

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.

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 card_checker does

The prompt checks each key figure against its cited source, comparing the value and its study arm, timepoint, unit, and population. It labels findings as confirmed, corrected, or unverifiable. When a source shows a different value, it gives the corrected figure and identifies the mismatch.

Its tools include Read, Grep, and Glob for project files, the clinical_trials and pubmed connectors, WebSearch, and {{fetch_tools}}. Sources can include full article texts, registry records, and per-trial analyses. For PDFs, the prompt calls for direct reading so tables and figures can be checked. Access to the sources and the listed tools is required.

What it helps with

  • check a reported figure against its cited paper or registry entry
  • catch a mismatch in dose, study arm, or timepoint
  • verify the unit and denominator used for a result
  • flag a number that cannot be confirmed in its source

Example prompts for the agent

  • Check the key figures in this answer against the cited sources and report mismatches.
  • Compare the doses and timepoints for each study arm in these results.
  • Verify the reported values against the PDF tables and figures.

How to install card_checker

1Plugin marketplace

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

2Manually: put the files in place

.claude/commands/card_checker.md

Questions about card_checker

How do I install card_checker in Claude Code?

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

What does card_checker do?

It checks key figures from an answer against cited sources. Each figure is marked confirmed, corrected, or unverifiable, with a correction when the source shows a different value.

What does card_checker need to work?

It needs access to the sources, plus Read, Grep, Glob, the clinical_trials and pubmed connectors, WebSearch, and {{fetch_tools}}.

Similar prompts

All prompts for Science and research →

From the same set29

The whole set →
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 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 appendix_writer appendix_writer — a prompt for Claude Code and ChatGPT that compiles technical simulation appendices for clinical trials. It converts model files into structured audit documentation without external web calls. GP ChatGPT ★ 654repo stars style_guide The style_guide Claude Code prompt sets the style and structure for clinical trial reports. It applies to report drafting, shortening, and editing tasks. GP ChatGPT ★ 654repo stars clinical-trial-forecast clinical-trial-forecast is a Claude Code skill that estimates the chance of success for one registered clinical trial. It starts when asked to assess a named study or its primary endpoint. CX Codex +1 ★ 654repo stars

Project sponsors

Companies that keep this analytics open