poemswepoemswe/co-researcher/skills/critical-analysis/SKILL.md

critical-analysis

Skill135 starsChanged 26 days agoMITView on GitHub

You must use this when analyzing claims, evaluating evidence, or Identifying logical fallacies in research.

In this repository16 other files it gives its agents.
- llms-full.txtllms.txt
- llms.txtllms.txt
- academic-writingSkill
- ethics-reviewSkill
- grant-writingSkill
- hypothesis-testingSkill
- literature-reviewSkill
- multi-source-investigationSkill
- peer-reviewSkill
- qualitative-researchSkill
- quantitative-analysisSkill
- research-managerSkill
- research-methodologySkill
- research-synthesisSkill
- systematic-reviewSkill
- using-co-researcherSkill

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Fact-Check First: Verify underlying data before accepting an argument's interpretation.
line 20
Distinctive:
Logic Audit: Run a scan for logical inconsistencies and informal fallacies.
line 44
Distinctive:
After the analysis, ask:
line 68
Distinctive:
Should I search for contradictory evidence to further test the central claim?
line 69
Distinctive:
Should I evaluate the credentials and funding history of the lead author?
line 71

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

<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>

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free