critical-thinking

Analyze arguments, detect biases, evaluate claims, and improve reasoning. Use when asked to fact-check, identify logical fallacies, evaluate arguments, analyze predictions, find root causes, or think adversarially about plans. Triggers include "evaluate this argument", "logical fallacies", "fact check", "analyze the claims", "identify biases", "devil's advocate", "red team this", "root cause".

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "critical-thinking" with this command: npx skills add spitoglou/fabric-claude-skills/spitoglou-fabric-claude-skills-critical-thinking

Critical Thinking

Rigorous analysis of arguments, claims, and reasoning.

Pattern Selection

IntentPatternWhen to Use
Claim evaluationanalyze_claimsAssess truth claims with evidence
Prediction analysisextract_predictionsIdentify and assess predictions
Extraordinary claimsextract_extraordinary_claimsClaims contradicting consensus
Controversial ideasextract_controversial_ideasContested viewpoints analysis
Error analysisanalyze_mistakesLearn from past errors
Problem findingextract_primary_problemRoot cause identification
Solution analysisextract_primary_solutionEvaluate proposed solutions
Adversarial thinkingt_red_team_thinkingFind weaknesses in plans
Decision upgradecreate_upgrade_packImprove decision-making
Novel insightsextract_alphaMost surprising/novel ideas
Thought organizationcreate_idea_compassStructure complex ideas
Mind mappingcreate_markmap_visualizationVisual thinking maps

Decision Flow

User request
    │
    ├─ "evaluate claims/fact check" ──→ analyze_claims
    ├─ "predictions/forecasts" ──→ extract_predictions
    ├─ "controversial/contested" ──→ extract_controversial_ideas
    ├─ "what went wrong/mistakes" ──→ analyze_mistakes
    ├─ "root cause/core problem" ──→ extract_primary_problem
    ├─ "red team/devil's advocate" ──→ t_red_team_thinking
    ├─ "surprising/novel insights" ──→ extract_alpha
    └─ "organize my thinking" ──→ create_idea_compass

Pattern References

See references/ for full patterns:

Output Guidelines

  • Always distinguish claims from evidence
  • Rate confidence levels explicitly
  • Identify logical fallacies by name
  • Present steelman versions of arguments before critiquing
  • Note when evidence is insufficient to conclude
  • Acknowledge uncertainty and areas of genuine disagreement

Chaining Suggestions

  • After analyze_claims → offer extract_primary_problem to find root issues
  • After t_red_team_thinking → offer create_upgrade_pack to address weaknesses
  • After extract_primary_problem → offer extract_primary_solution for solutions

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

learning-education

No summary provided by upstream source.

Repository SourceNeeds Review
Research

research-intelligence

No summary provided by upstream source.

Repository SourceNeeds Review
General

technical-documentation

No summary provided by upstream source.

Repository SourceNeeds Review
General

writing-enhancement

No summary provided by upstream source.

Repository SourceNeeds Review