Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →xintaofei/peer-review
Structured manuscript/grant review with checklist-based evaluation.
Passed 22 of 23 test cases with the skill, and 21 of 23 without it.
2 fixed20 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
Evaluate the methods section of a neuroscience paper testing a new cognitive drug on 5 rats per group without mentioning statistical power calculations or primary effect size estimates. The authors report p = 0.08 and conclude 'the drug showed a promising trend.'
| Checked | Without skill | With skill |
|---|---|---|
| Identifies the absence of pre-study statistical power calculations as a major limitation. | Missed | Passed |
| Critiques claiming a promising trend from a non-significant p-value. | Passed | Passed |
The instructions your model reads when the skill loads.
Peer review is a systematic process for evaluating scientific manuscripts. Assess methodology, statistics, design, reproducibility, ethics, and reporting standards. Apply this skill for manuscript and grant review across disciplines with constructive, rigorous evaluation.
This skill should be used when:
Related Resource: The venue-templates skill provides reviewer_expectations.md with detailed guidance on what reviewers look for at different venues (Nature/Science, Cell Press, medical journals, ML conferences). Use this to calibrate your review standards to the target venue.
When creating documents with this skill, always consider adding scientific diagrams and schematics to enhance visual communication.
If your document does not already contain schematics or diagrams:
For new documents: Scientific schematics should be generated by default to visually represent key concepts, workflows, architectures, or relationships described in the text.
How to generate schematics:
python scripts/generate_schematic.py "your diagram description" -o figures/output.png
The AI will automatically:
test cases passed, vs 21 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.