scientific-critical-thinking
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill scientific-critical-thinking --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Evaluates research rigor across methodology, experimental design, statistical validity, biases, confounding, and evidence quality using GRADE and Cochrane ROB frameworks to enable critical analysis of scientific claims.
How it works
The skill provides a structured critique framework:
- Methodology Critique: assesses study design, validity (internal, external, construct, statistical conclusion), control/blinding, and measurement quality with specific checklist items.
- Bias Detection: systematically reviews cognitive, selection, measurement, analysis biases, and confounding, with prompts to examine study flow, blinding, validation, and reporting.
- Statistical Analysis Evaluation: analyzes sample size/power, appropriateness of tests, multiple comparisons, p-values interpretation, effect sizes/CI, missing data handling, and modeling concerns.
- Evidence Quality Assessment: ranks study designs, evaluates risk of bias, applies GRADE considerations, and examines convergence of evidence and contextual factors.
- Logical Fallacy Identification: detects causation, generalization, authority, statistical, structural, and science-specific fallacies, naming the fallacy and outlining needed evidence.
- Research Design Guidance: guides design decisions, including question refinement, design selection, bias minimization, sample planning, and measurement strategy. The core goal is to provide concrete, discipline-appropriate evaluation steps; it references external principled checklists and frameworks (e.g., GRADE, Cochrane ROB) within its guidance.
When to use it
Use when evaluating research methodology, experimental design, statistical validity, biases, confounding, evidence quality, or when conducting systematic reviews or meta-analyses; particularly for applying GRADE or Cochrane risk of bias assessments and for critical analysis of research papers.
What it can touch
The skill outlines touchpoints for evaluating study design, validity domains, bias categories, statistical methods, and evidence frameworks. It directs the user to use the provided evaluation steps and checklists, and to reference relevant methodological guidance as needed.
Caveats
The skill relies on standard research methods frameworks (GRADE, Cochrane ROB). It does not guarantee outcomes of individual studies; it provides a structured critique framework and prompts for assessment.
<!-- ╔══════════════════════════════════════════════════════════════╗ ║ 本文件为开源 Skill 原始文档，收录仅供学习与研究参考 ║ ║ CoPaper.AI 收集整理 | https://copaper.ai ║ ╚══════════════════════════════════════════════════════════════╝ 来源仓库: https://github.com/K-Dense-AI/claude-scientific-writer 项目名称: claude-scientific-writer 开源协议: MIT License 收录日期: 2026-04-02 声明: 本文件版权归原作者所有。此处收录旨在为社会科学实证研究者 提供 AI Agent Skills 的集中参考。如有侵权，
What does the scientific-critical-thinking skill do?
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill scientific-critical-thinking --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.