paper-to-claim-verifier

paper-to-claim-verifier is a skill for Claude Code, Codex from aipoch/medical-research-skills. It costs 132 tokens per session (3,040 once invoked), scanned A, original, MIT.

A checker that compares a scientific claim with the original paper or papers cited to support it.

In plain words
What is it for?
Use it to test manuscript sentences, slides, or widely repeated statements for overstatement and citation errors.
Why use it?
Repeated claims can drift away from what the cited research actually showed, including by confusing correlation with cause.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to test manuscript sentences, slides, or widely repeated statements for overstatement and citation errors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aipoch/medical-research-skills/paper-to-claim-verifier
About the project

Medical Research Agent Skills is a library of agent instructions for medical and biomedical research, covering evidence analysis, study protocol design, data analysis, and academic writing. Researchers use it to guide compatible coding agents through common scientific workflows. The catalogue contains many of the library's skills and commands.

aipoch/medical-research-skills · 1,860 stars · on GitHub · aipoch.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add aipoch/medical-research-skills --skill paper-to-claim-verifier
Clone the repo
git clone --depth 1 https://github.com/aipoch/medical-research-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for paper-to-claim-verifier

README.md
[![agentmods](https://agentmods.dev/badge/skills/aipoch/medical-research-skills/paper-to-claim-verifier/github.svg)](https://agentmods.dev/skills/aipoch/medical-research-skills/paper-to-claim-verifier)
Your own site
<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/paper-to-claim-verifier"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/paper-to-claim-verifier/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for paper-to-claim-verifier

Your own site · 80×15
<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/paper-to-claim-verifier"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/paper-to-claim-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00132 $0.03040
Opus 5 $0.00066 $0.01520
Sonnet 5 $0.00026 $0.00608
Haiku 4.5 $0.00013 $0.00304

Measured 9d ago against content hash 85393ab27d38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

paper-to-claim-verifier scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

awesome-med-research-skills/Evidence Insight/paper-to-claim-verifier/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source: https://github.com/aipoch/medical-research-skills

Paper-to-Claim Verifier

You are an expert scientific claim-verification analyst.

Task: Determine whether a scientific or biomedical claim is actually supported by the cited original paper(s), and if not, explain whether the problem is citation drift, overstatement, selective citation, context mismatch, evidence inflation, or a correlation-to-causation error.

This skill is for users who want to check statements such as:

  • “This biomarker predicts response to immunotherapy.”
  • “Studies have shown that gut microbiota causes stroke progression.”
  • “PD-L1 is a validated prognostic marker in this cancer.”
  • “This pathway is a therapeutic target in sepsis.”
  • “Everyone cites this paper for that conclusion — is that actually what it said?”

This skill must always distinguish between:

  • the exact claim being tested
  • the citation(s) attached to the claim
  • what the cited paper explicitly reported
  • what can be reasonably inferred but was not directly proven
  • what the claim adds beyond the paper
  • whether the mismatch is minor wording drift or a major evidence error

This skill is not a generic summarizer. It is a claim-to-source verification system.


Reference Module Integration

The references/ directory is not optional background material. It defines the operational rules that must be actively used while running this skill.

Use the reference modules as follows:

  • references/claim-decomposition-rules.md → use when rewriting the target claim into verifiable components in Section A.
  • references/source-tracing-rules.md → use when tracing cited papers, anchor studies, and secondary retellings in Section B.
  • references/evidence-support-judgment-rules.md → use when deciding whether the paper strongly supports, partially supports, weakly supports, or does not support the claim in Sections D–F.
  • references/citation-drift-taxonomy.md → use when classifying mismatch types in Section G.
  • references/causality-boundary-rules.md → use whenever a claim may overstep from association to mechanism, prediction, intervention relevance, or causation in Sections E–G.
  • references/context-transfer-rules.md → use when checking whether the paper and the claim refer to the same population, endpoint, model, platform, disease stage, or use case in Sections C–F.
  • references/literature-integrity-rules.md → use throughout all sections to prevent fabricated references, invented findings, or unsupported citation-chain assumptions.
  • references/workflow-step-template.md → use to keep the reasoning sequence aligned with the required step order.
  • references/output-section-guidance.md → use as the section-level formatting and content control standard for Sections A–J.

Read the full file on GitHub · 327 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 327 lines · 132 tokens per session scan A 85393ab27d38

Subscribe to this mod's changes

paper-to-claim-verifier is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 3,040 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories