peer-review

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

1.10x

Quality

67%

Does it follow best practices?

Impact

93%

1.10x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/peer-review/SKILL.md

Evaluation results

98%

25%

Peer Review: Antihypertensive Drug Trial Manuscript

Structured peer review report format

Criteria

Without context

With context

Summary statement present

90%

100%

Strengths listed

25%

100%

Weaknesses listed

25%

87%

Major comments numbered

25%

100%

Major comment explains why problematic

100%

Major comment suggests solutions

100%

Minor comments with locations

87%

Statistical completeness evaluated

100%

Reporting standard compliance checked

100%

Ethical considerations evaluated

100%

Initial synopsis present

100%

Constructive tone maintained

100%

95%

Peer Review: Meta-analysis of Mediterranean Diet and Cardiovascular Outcomes

Systematic review and meta-analysis evaluation

Criteria

Without context

With context

PRISMA compliance evaluated

100%

Search strategy assessed

100%

Inclusion/exclusion criteria assessed

25%

62%

Publication bias evaluated

100%

Heterogeneity addressed

100%

Pooling method evaluated

100%

Data/code availability checked

100%

Summary with recommendation

100%

Major comments numbered

100%

Minor comments with locations

50%

75%

Overstatement red flags checked

100%

Strengths and weaknesses

25%

100%

86%

-6%

Peer Review: Deep Learning Model for Drug Response Prediction

Computational methods and reproducibility evaluation

Criteria

Without context

With context

Software versions assessed

100%

50%

Code availability assessed

100%

Algorithm validation evaluated

100%

90%

Data availability assessed

50%

25%

Overstatement/causation red flags identified

100%

Statistical reporting evaluated

100%

Experimental design rigor checked

100%

Reproducibility overall assessed

100%

87%

Summary with recommendation

100%

Major comments with explanation

100%

Minor comments with locations

80%

Strengths and weaknesses in summary

40%

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: b58ad7e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Peer Review: Antihypertensive Drug Trial Manuscript Peer Review: Meta-analysis of Mediterranean Diet and Cardiovascular Outcomes Peer Review: Deep Learning Model for Drug Response Prediction

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.