scientific-critical-thinking

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.

1.02x

Quality

67%

Does it follow best practices?

Impact

96%

1.02x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

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

Evaluation results

100%

13%

Internal Study Evaluation: MindBoost Cognitive Supplement Trial

Structured critique with GRADE and precise terminology

Criteria

Without context

With context

Summary section present

100%

Strengths section present

100%

Severity-classified concerns

25%

100%

Recommendations section present

100%

Overall assessment present

100%

Named biases

70%

100%

Blinding issue identified

100%

Multiple comparisons identified

100%

P-value clustering flagged

100%

GRADE or evidence quality downgrading

60%

100%

Overgeneralization identified

100%

Missing effect sizes/CIs noted

100%

Funding conflict flagged

100%

89%

-6%

Science Communication Fact-Check: University Press Release

Claim evaluation and fallacy identification

Criteria

Without context

With context

Claim type identified

100%

Causation fallacy named

100%

Anecdotal fallacy identified

100%

Authority/historical fallacy named

100%

Absolute language flagged

100%

Confounding dismissed

100%

Evidence needed for causal claim

100%

Fallacy doesn't disprove conclusion

37%

62%

Pre-publication flagged

100%

At least two named fallacies

100%

Hedging language suggested

100%

37%

Overgeneralization identified

100%

62%

100%

Study Design Consultation: Nurse Burnout Mindfulness Trial

Rigorous research design guidance

Criteria

Without context

With context

A priori power analysis

100%

Randomization recommended

100%

Blinding addressed

100%

Preregistration recommended

100%

CONSORT guideline referenced

100%

Primary vs secondary outcomes

100%

Effect sizes and CIs planned

100%

Attrition in sample size

100%

Validated burnout measure

100%

Control condition addressed

100%

Confirmatory vs exploratory distinction

100%

Missing data plan

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: 25e1c0f

Evaluated: about 2 months ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Internal Study Evaluation: MindBoost Cognitive Supplement Trial Science Communication Fact-Check: University Press Release Study Design Consultation: Nurse Burnout Mindfulness Trial

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.