Agent Skills

critical-thinking-logical-reasoning

researchsammcj2.3K installs

Critically analyse the reasoning in written content (articles, blogs, transcripts, reports), not code. Use only when explicitly asked to critically analyse or critique an argument.

Install

npx skills add https://github.com/sammcj/agentic-coding --skill critical-thinking-logical-reasoning
SKILL.md

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:

Summary

One sentence stating the core claim and your overall assessment of its strength.

Key Issues

Bullet the most significant problems, each with a brief explanation of why it matters. Where an argument is weak, briefly note how it could be strengthened - this distinguishes fixable flaws from fundamental problems. If there are no problems, omit this section.

Questions to Probe

2-5 questions that would clarify ambiguity, test key assumptions, or reveal whether the argument holds under scrutiny. Frame as questions a decision-maker should ask before acting on this reasoning.

Verdict

The actionable takeaway - what to do given this analysis.

Guidelines:

  • Assume individuals have good intentions by default; at worst, people may be misinformed or mistaken in their reasoning. Be charitable but rigorous in your critique.
  • Prioritise issues that genuinely affect the conclusion over minor technical flaws. Your purpose is to inform well-reasoned decisions, not to manufacture disagreement or nitpick.
  • Be direct. State problems plainly without hedging.
  • Critique the argument, not the person making it.
  • Critique the reasoning and logic. Do not fact-check empirical claims unless they are obviously implausible or internally contradictory.
  • Apply the 'so what' test: even if you identify a flaw, consider whether it materially affects the practical decision or conclusion at hand.
  • Acknowledge uncertainty in your own analysis. Flag where your critique depends on assumptions or where you lack domain context.
  • Distinguish between 'flawed' and 'wrong' - weak reasoning does not automatically mean false conclusions.
  • If the argument is sound, say so. Do not manufacture criticism.
  • Provide concise output, no fluff.
  • Always use Australian English spelling.

Related skills

researchmattpocock575KInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.paper-context-resolverlllllllama451KRigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing Renv-and-assets-bootstraplllllllama450KRigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full orchestration, paper interpretation, final run reporting, or generic environment setup that is not tied to a specific reproduction target.ai-research-explorelllllllama311KRigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, fair comparison, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding, narrow c

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers