Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Scientific Critical Thinking

Systematically evaluates research claims for design flaws, bias, statistical errors and evidence quality using GRADE and Cochrane Risk of Bias.

EducationIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Gives Claude a disciplined framework for appraising scientific claims instead of vague impressions:

  • Critiques study design, controls and confounding
  • Detects selection, measurement, publication and cognitive biases
  • Flags statistical problems: underpowering, multiplicity, p-value misuse, effect-size misreads
  • Applies GRADE evidence grading and Cochrane Risk of Bias domains
  • Identifies logical fallacies common in scientific argument
  • Delivers critique in a fixed structure: summary → strengths → concerns by severity → actionable recommendations → overall assessment

A references/ directory holds deeper material (scientific method, bias taxonomy, statistical pitfalls, evidence hierarchy, logical fallacies, experimental design checklist) that is loaded only when needed.

Who it's for

  • Graduate students and researchers prepping journal club or lab meetings
  • Anyone running a systematic review or meta-analysis
  • Researchers stress-testing a protocol before data collection
  • Curious readers fact-checking health, nutrition or policy headlines
  • Instructors teaching research methods and critical reading

(For writing a formal peer-review report, the repo's peer-review skill is the better fit.)

Examples

  1. Appraise a trial: "Assess this RCT domain by domain with Cochrane Risk of Bias, and separate fatal flaws from minor limitations."
  2. Check a headline: "This article claims coffee extends lifespan — show where observational data is treated as causal and list plausible confounders."
  3. Pre-review a protocol: "My pilot is 40 participants, single site, unblinded. Where is it weakest on power and bias, and what GRADE level would the resulting evidence get?"

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/scientific-critical-thinking folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/scientific-critical-thinking/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/scientific-critical-thinking ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS/Linux, Git Bash or WSL on Windows).
  2. Clone the repository: 
    git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the Claude Code skills folder if it doesn't exist: 
    mkdir -p ~/.claude/skills
  4. Copy just this skill folder, including its references/ files: 
    cp -r scientific-agent-skills/skills/scientific-critical-thinking ~/.claude/skills/
  5. Restart Claude Code and confirm scientific-critical-thinking appears in your skill list.
  6. Try a prompt like: "Critically evaluate the experimental design in this paper."
  7. (Optional) For diagrams, also install the scientific-schematics skill and set export OPENROUTER_API_KEY=.... Note that prompts are sent to a third-party API, so avoid pasting unpublished sensitive details.
View source on GitHub ↗License: MIT