paper-to-claim-verifier

Verifies whether a scientific or biomedical claim is actually supported by the cited original papers rather than by citation drift, overstatement, selective citation, or correlation-to-causation inflation. Use this skill whenever a user wants to check whether a repeated statement, slide claim, manuscript sentence, review assertion, or “people often say” scientific conclusion is truly supported by the underlying primary literature. Always separate the claim itself, the cited paper(s), what the paper actually showed, what it did not show, and whether later retellings drifted beyond the original evidence. Never fabricate references, findings, study features, or citation chains.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable instruction skill with a clear ordered workflow, explicit checkpoints, and excellent progressive disclosure via 9 well-integrated reference modules. The main weakness is redundancy across the Core Function, Hard Rules, Should-Not, and Quality Standard sections that restate the same constraints.

Suggestions

Collapse the 'Core Function' 10-item list into the 8-step Execution section rather than restating both, since they cover the same sequence.

Merge 'What This Skill Should Not Do' and the 'Quality Standard' into the existing Hard Rules and Step 8 outputs to remove repeated constraints (e.g., never fabricate, association vs causation).

Trim near-duplicate example sets: the Input Validation examples, Sample Triggers, and opening example claims overlap heavily and could be consolidated to one representative list.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and substantive, but the Core Function list, Hard Rules, 'What This Skill Should Not Do', and Quality Standard sections repeat the same distinctions (association vs causation, never fabricate, review-vs-primary) that the 8 steps and reference modules already establish.	3 / 5
Actionability	Provides a concrete, executable instruction set: a fixed 8-step ordered procedure, exact support-level labels, an exact mismatch taxonomy, and a mandatory A-J output structure with per-section sub-bullets.	5 / 5
Workflow Clarity	Sequences an 8-step process to run in order, with explicit validation/stop conditions (out-of-scope redirect, trace backward if not the true origin, per-subclaim support judgment) and a 15-rule checkpoint list.	5 / 5
Progressive Disclosure	Body is an overview that maps each of the 9 real reference files to a specific output section with one-level-deep, clearly signaled navigation and no nested references.	5 / 5
	Total	18 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states what the skill does and when to use it with natural trigger phrasing. Minor gains possible by adding a few concrete source identifiers (PMID/DOI/citation string) as triggers and a tighter enumeration of concrete operations.

Dimension	Reasoning	Score
Specificity	Names concrete actions such as 'Verifies whether... supported by the cited original papers' and distinguishes 'citation drift, overstatement, selective citation, or correlation-to-causation inflation', plus a claim/paper/separation step, but the actions stay conceptual rather than a fully enumerated operation set.	4 / 5
Completeness	Explicitly answers both what ('Verifies whether a scientific or biomedical claim is actually supported...') and when ('Use this skill whenever a user wants to check whether...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrasing such as 'repeated statement, slide claim, manuscript sentence, review assertion, or "people often say" scientific conclusion'; coverage is good but lacks some synonyms like PMID/DOI/citation-string.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (claim-to-source verification against citation drift) with distinctive triggers and minimal overlap risk against general summarizer or literature-search skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Evidence Insight/paper-to-claim-verifier/SKILL.md
Commit: f5ef65b

Reviewed: ~12 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.