sammcj avatar

Critical Thinking Logical Reasoning

This is a structured framework for analyzing arguments in written content like articles, reports, and transcripts. It pushes you to understand the claim before critiquing it, then walks through examining evidence, spotting logical fallacies, surfacing assumptions, and checking for internal consistency. The output format is practical: core issues, probing questions, and a bottom line for decision makers. What's refreshing is the explicit instruction to be charitable but rigorous, to apply a "so what" test before flagging minor flaws, and to acknowledge when arguments are actually sound rather than manufacturing criticism. It's calibrated for preserving signal over noise, which matters if you're reviewing content that others need to act on.

skills.sh installs
2.4K
GitHub stars
169
last updated
Aug 21, 2026

Install

$ npx -y skills add sammcj/agentic-coding --skill critical-thinking-logical-reasoning --agent claude-code

Installs into .claude/skills of the current project.

Files

Step back and frame the information with a lens of critical thinking and logical reasoning

Your role is to examine information, arguments, and claims using logic and reasoning, then provide clear, actionable critique.

When analysing content:

  1. Understand the argument first - Can you state it in a way the speaker would agree with? If not, you are not ready to critique.
  2. Identify the core claim(s) - What is actually being asserted? Separate conclusions from supporting points.
  3. Examine the evidence - Is it sufficient? Relevant? From credible sources?
  4. Spot logical issues - Look for fallacies, unsupported leaps, circular reasoning. Note: empirical claims need evidence; normative claims need justified principles; definitional claims need consistency.
  5. Surface hidden assumptions - What must be true for this argument to hold?
  6. Consider what is missing - Alternative explanations, contradictory evidence, unstated limitations.
  7. Assess internal consistency - Does the argument contradict itself?
  8. Consider burden of proof - Who needs to prove what? Is the evidence proportional to the claim's significance?

Structure your response as:

Sponsors

Details

Repository
github.com/sammcj/agentic-coding
Category
AI & Agent Building
First seen
Apr 16, 2026

More from sammcj/agentic-coding

All 4
1dceoy avatarspeckit-constitutiondceoy/speckit-agent-skillsCreate or update the project constitution from interactive or provided principle inputs.2.4Kskills.sh installs
2coinbase avatarauthenticate-walletcoinbase/agentic-wallet-skillsSign in to the wallet. Use when you or the user want to log in, sign in, connect, or set up the wallet, or when any wallet operation fails with authentication o2.4Kskills.sh installs
3k-dense-ai avatarscientific-brainstormingk-dense-ai/scientific-agent-skillsFacilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial rev2.4Kskills.sh installs
4k-dense-ai avatarstatistical-analysisk-dense-ai/scientific-agent-skillsGuided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted repo2.4Kskills.sh installs
5aj-geddes avatarcode-review-analysisaj-geddes/useful-ai-promptsPerform comprehensive code reviews with best practices, security checks, and constructive feedback. Use when reviewing pull requests, analyzing code quality, ch2.4Kskills.sh installs
6mapbox avatarmapbox-style-patternsmapbox/mapbox-agent-skillsCommon style patterns, layer configurations, and recipes for typical mapping scenarios including restaurant finders, real estate, data visualization, navigation2.4Kskills.sh installs