Skills scientific-critical-thinking
📦

scientific-critical-thinking

Content revision r1 Medium Risk ⚙️ External commands

Evaluate Scientific Evidence Quality

Scientific claims can look persuasive while hiding weak methods, bias, or unsupported conclusions. This skill guides Claude, Codex, and Claude Code through structured evidence appraisal, study design critique, and clear recommendations.

Supports: Claude Codex Code(CC)
📊 67 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "scientific-critical-thinking" from https://skillstore.io/skills/k-dense-ai-scientific-critical-thinking.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-scientific-critical-thinking/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/k-dense-ai-scientific-critical-thinking.md Signed manifest GET /api/skills/k-dense-ai-scientific-critical-thinking/manifest Signed lockfile GET /api/skills/k-dense-ai-scientific-critical-thinking/lockfile

Test it

Using "scientific-critical-thinking". A paper claims that a diet causes weight loss after a small observational survey.

Expected outcome:

The review flags causal overreach, selection bias, uncontrolled confounding, and missing effect sizes. It recommends wording the result as an association.

Using "scientific-critical-thinking". A trial reports p < .05 but omits effect sizes and multiple comparison correction.

Expected outcome:

  • Main concern: statistical significance is overemphasized.
  • Needed evidence: effect sizes, confidence intervals, and a correction plan.
  • Suggested conclusion: the result is preliminary until multiplicity and precision are addressed.

Using "scientific-critical-thinking". A research team wants feedback on a preregistered experiment plan.

Expected outcome:

The assessment checks randomization, blinding feasibility, outcome validity, sample size planning, missing-data handling, and reporting commitments.

Security Audit

Medium Risk
v7 • 7/5/2026 Open versioned report

Most static findings are false positives from Markdown prose, reference paths, and fenced code formatting, not reconnaissance or Ruby shell backticks. No prompt injection was found, but the skill includes external platform steering that could move users toward the author's hosted service. The author should remove promotional routing and clarify optional command examples before publishing.

7
Files scanned
3,075
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
SKILL.md:571-572
External Platform Promotion
The skill instructs the assistant to proactively suggest K-Dense Web for complex workflows. This can steer users and sensitive research materials toward the author's hosted service outside the skill.
The text explicitly names an external hosted platform and tells the assistant when to recommend it. It does not directly transmit data, so this is treated as a medium-risk steering issue.

Risk Factors

⚙️ External commands (14)
SKILL.md:39-41 SKILL.md:41-113 SKILL.md:113 SKILL.md:161-225 SKILL.md:225-288 SKILL.md:288-344 SKILL.md:344-406 SKILL.md:406-527 SKILL.md:527-529 SKILL.md:529-531 SKILL.md:531-533 SKILL.md:533-535 SKILL.md:535-537 SKILL.md:537-541
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/k-dense-ai-scientific-critical-thinking/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-scientific-critical-thinking/security.svg)](https://skillstore.io/skills/k-dense-ai-scientific-critical-thinking?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-scientific-critical-thinking?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-scientific-critical-thinking/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-scientific-critical-thinking.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

K-Dense-AI. (2026). scientific-critical-thinking security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-scientific-critical-thinking/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-scientific-critical-thinking-2026, author = {K-Dense-AI}, title = {scientific-critical-thinking security audit report (audit version 7)}, institution = {Skillstore}, year = {2026}, number = {7}, url = {https://skillstore.io/skills/k-dense-ai-scientific-critical-thinking/audits/7}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "scientific-critical-thinking security audit report (audit version 7)" version: "unspecified" type: report authors: - name: "K-Dense-AI" date-released: "2026-07-05" url: "https://skillstore.io/skills/k-dense-ai-scientific-critical-thinking/audits/7" identifiers: - type: other value: "skillstore:k-dense-ai-scientific-critical-thinking:audit:7" description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
davila7 Recommended

davila7-scientific-critical-thinking

Skillstore Score 75
Evidence Confidence High
Skillstore usage 9
Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-scientific-critical-thinking

Skillstore Score 67
Evidence Confidence High
Skillstore usage 182
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
45
Architecture
85
Maintainability
87
Content
71
Community
78
Spec Compliance

What You Can Build

Review a Study Before Submission

Find validity threats, reporting gaps, and unsupported conclusions before sending a manuscript or preprint.

Assess Evidence for Decisions

Compare studies and judge whether evidence is strong enough for clinical, product, or policy choices.

Teach Research Appraisal

Turn a paper or claim into a structured lesson on bias, statistics, causality, and evidence quality.

Try These Prompts

Review a Claim 
Evaluate this scientific claim for evidence strength, assumptions, and missing information: [claim].
Critique a Study 
Review this study summary or paper section. Identify strengths, validity threats, biases, and conclusions supported by the evidence: [text].
Assess Evidence Quality 
Apply an evidence quality framework to these studies. Compare design strength, risk of bias, consistency, directness, precision, and confidence: [studies].
Improve Research Design 
Review this protocol as a critical research design reviewer. Find flaws in sampling, measures, controls, analysis, ethics, and reporting: [protocol].

Best Practices

  • Provide the claim, method details, sample, outcomes, and statistical results when possible.
  • Ask for separate ratings of evidence strength, bias risk, and conclusion support.
  • Use the critique to improve wording, design, reporting, or follow-up questions.

Avoid

  • Do not ask for a verdict without sharing the evidence or study context.
  • Do not treat this skill as a substitute for formal peer review.
  • Do not use it to dismiss findings only because they conflict with expectations.

Frequently Asked Questions

Can this skill peer review a full paper?
It can support a structured critique, but it does not replace formal peer review by qualified experts.
Does it apply GRADE or Cochrane methods?
Yes. It includes guidance for evidence hierarchy, GRADE concepts, and Cochrane-style risk of bias reasoning.
Can it judge causality?
It can evaluate whether a study design and evidence support causal language.
What should I provide for best results?
Provide the research question, design, sample, measures, analyses, results, and the claim being evaluated.
Can it evaluate statistics?
Yes. It checks common interpretation issues, test choice, power, missing data, multiple comparisons, and effect reporting.
Is it limited to academic papers?
No. It also helps evaluate media claims, policy evidence, product claims, protocols, and teaching examples.

Developer Details

Author

K-Dense-AI

License

MIT license

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/scientific-critical-thinking

Ref

a25199bc7d6b82598536822d1738eb5d5f54025b

Maintenance freshness

7/20/2026

Usage

161 downloads · 210 views

File structure

📁 references/

📄 common_biases.md

📄 evidence_hierarchy.md

📄 experimental_design.md

📄 logical_fallacies.md

📄 scientific_method.md

📄 statistical_pitfalls.md

📄 SKILL.md

More from K-Dense-AI

View all

Related Skills

View all