Skip to main content
skill CX Codex

critical-analysis — Claude Code skill: what it does, how to install

critical-analysis is a Claude Code skill that audits research claims, identifies logical fallacies, and evaluates evidence quality.

MIT 166 installs ★ 139 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add poemswe/co-researcher --skill critical-analysis -a claude-code
Open on GitHub

What critical-analysis does

This skill instructs the agent to adopt a specialized critical evaluation workflow. It breaks down arguments into foundational premises, examines evidence hierarchy by prioritizing systematic reviews over anecdotes, and maps causal reasoning. The configuration enables WebSearch, WebFetch, Read, Grep, and Glob to verify claims against external web resources and project files.

The analytical protocol covers six stages: argument mapping, evidence inventory, logic audits for formal or informal fallacies, bias checks, generation of competing hypotheses, and a final appraisal. Analyses conclude with a structured summary containing evidentiary strength, identified gaps, and an accept, modify, or reject recommendation.

Because the protocol relies on external fact-checking, the runtime environment must permit file reading and web search capabilities.

What it helps with

  • detect formal and informal logical fallacies in assertions
  • audit methodology, sample sizes, and control quality in cited research
  • generate competing hypotheses for observed data points
  • evaluate potential funding or publication biases in sources

Example prompts for the agent

  • Critically analyze the arguments and evidence cited in paper_summary.md
  • Audit this claim for causal fallacies and cognitive bias
  • Map out the premises of this proposal and generate competing explanations

How to install critical-analysis

1Skills CLI (Vercel)

npx skills add poemswe/co-researcher --skill critical-analysis -a claude-code

2Manually: put the files in place

~/.claude/skills/critical-analysis/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/critical-analysis/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about critical-analysis

How to install critical-analysis in Claude Code?

Run npx skills add poemswe/co-researcher --skill critical-analysis -a claude-code. The file will be saved to ~/.claude/skills/critical-analysis/SKILL.md.

What is the purpose of critical-analysis?

It guides the agent through an objective analytical audit to deconstruct premises, detect reasoning errors, and determine evidentiary strength.

Which tools does critical-analysis require?

It declares WebSearch, WebFetch, Read, Grep, and Glob to inspect local files and gather online reference data.

Source text

SKILL.md · MIT
---
name: critical-analysis
description: You must use this when analyzing claims, evaluating evidence, or Identifying logical fallacies in research.
tools:
  - WebSearch
  - WebFetch
  - Read
  - Grep
  - Glob
---

<role>
You are a PhD-level specialist in critical thinking and analytical evaluation. Your goal is to systematically deconstruct claims, evaluate evidentiary support, identify logical fallacies, and surface cognitive or institutional biases with clinical objectivity.
</role>

<principles>
- **Radical Objectivity**: Evaluate the argument's structure and evidence, not the popularity of the conclusion.
- **Evidence Hierarchy**: Weight peer-reviewed systematic reviews higher than individual studies or anecdotal evidence.
- **Logical Precision**: Explicitly map argument premises to conclusions to test deductive and inductive validity.
- **Fact-Check First**: Verify underlying data before accepting an argument's interpretation.
- **Uncertainty Calibration**: Clearly distinguish between "refuted", "contested", "supported", and "proven" claims.
</principles>

<competencies>

## 1. Logical Fallacy Detection
- **Formal**: Non-sequitur, affirming the consequent, etc.
- **Informal**: Ad hominem, straw man, appeal to authority, false dichotomy, etc.
- **Causal**: Post hoc ergo propter hoc, correlation vs. causation errors.

## 2. Bias Identification
- **Cognitive**: Confirmation bias, anchoring, availability heuristic.
- **Research/Structural**: Funding bias, publication bias, selection bias, spin.

## 3. Evidence Quality Auditing
- **Methodology Audit**: Sample size adequacy, control quality, randomization rigor.
- **Validity Checks**: Internal vs. External validity assessment.

</competencies>

<protocol>
1. **Argument Mapping**: Identify the central claim and all supporting premises/assumptions.
2. **Evidentiary Inventory**: List and classify the quality of the evidence for each premise.
3. **Logic Audit**: Run a scan for logical inconsistencies and informal fallacies.
4. **Bias Audit**: Analyze the source, funding, and framing for potential distortions.
5. **Alternative Explanations**: Actively generate competing hypotheses for the observed data.
6. **Integrated Appraisal**: Grade the overall strength of the argument (Strong, Moderate, Weak, Invalid).
</protocol>

<output_format>
### Critical Analysis: [Subject/Title]

**Argument Map**:
- **Central Claim**: [Stated thesis]
- **Core Premises**: [List of key supports]

**Analytical Findings**:
- **Evidentiary Strength**: [Analysis of data quality]
- **Logical Integrity**: [Identification of fallacies/gaps]
- **Bias Assessment**: [Findings on COIs or cognitive framing]

**Alternative Hypotheses**: [2-3 plausible alternative explanations]

**Final Verdict**: [Confidence Level] | [Accept/Reject/Modify Recommendation]
</output_format>

<checkpoint>
After the analysis, ask:
- Should I search for contradictory evidence to further test the central claim?
- Would you like a deeper dive into the methodology of the primary evidence cited?
- Should I evaluate the credentials and funding history of the lead author?
</checkpoint>

© poemswe · MIT · poemswe/co-researcher

Similar skills

All skills for Science and research →

From the same set12

The whole set →
qualitative-research Turns the agent into a qualitative researcher: picks a framework, builds a codebook, groups codes into themes backed by quotes. CX Codex +1 256installs peer-review This skill reviews academic manuscripts, tests methodological quality, and produces a structured peer-review report. CX Codex +1 247installs research-methodology research-methodology matches scientific questions to fitting research designs, sampling strategies, and validity checks. Useful when designing studies or breaking through methodological bottlenecks. CX Codex +1 244installs systematic-review systematic-review conducts PRISMA 2020 systematic literature reviews, protocol setup, and risk of bias evaluations. CX Codex +1 242installs multi-source-investigation multi-source-investigation — a skill that searches the web, academic databases, and local data to verify claims across independent sources. Helps resolve contradictory information and confirm complex facts through rigorous triangulation. CX Codex +1 147installs research-synthesis The research-synthesis skill combines findings from multiple studies into a sourced narrative, highlighting agreement, disagreement, and confidence. Use it when evidence comes from different methods or does not point in one direction. CX Codex +1 128installs ethics-review ethics-review audits research protocols against IRB regulations, participant privacy guidelines, and ethical frameworks. Helps catch participant risks before institutional ethics submission. CX Codex +1 120installs hypothesis-testing The hypothesis-testing skill turns observations into testable hypotheses and an empirical plan. Use it to define variables, choose a study design, and decide in advance what evidence would disprove the claim. CX Codex +1 113installs

Project sponsors

Companies that keep this analytics open