agentleFS
aws-solutionsaws-solutions/konductor/skills/argumentation-reference/SKILL.md

argumentation-reference

Skill11 starsChanged 49 days agoApache-2.0View on GitHub

Reference primer for argumentation theory — Toulmin model, fallacy taxonomy, argument scoring rubric. Use during adversarial design review to identify weak arguments and logical fallacies.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Every argument has six components:

    line 13

≈ “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

Argumentation Reference

A reference primer for argumentation theory covering Toulmin model, informal/formal fallacies (relevance, presumption, ambiguity, formal), a 0–3 scoring rubric across 5 criteria (max 15 pts), difficulty tiers (Beginner/Intermediate/Advanced/Competitive), and coaching intervention guidelines.

Toulmin Model

Every argument has six components:

  • Claim — the conclusion being argued
  • Data/Grounds — evidence supporting the claim
  • Warrant — the logical bridge from data to claim
  • Backing — support for the warrant itself
  • Qualifier — degree of certainty (always, usually, presumably)
  • Rebuttal — conditions under which the claim does not hold

A strong argument makes all six components explicit. A weak argument omits warrant or backing.

Fallacy Taxonomy

Relevance Fallacies

  • Ad hominem — attacking the person, not the argument
  • Appeal to authority — citing authority without evidence
  • Appeal to popularity — "everyone does it"
  • Red herring — distracting with irrelevant information
  • Straw man — misrepresenting the opposing argument

Presumption Fallacies

  • Begging the question — conclusion assumed in premise
  • False dichotomy — presenting only two options when more exist
  • Slippery slope — assuming one event inevitably leads to another
  • Hasty generalization — drawing broad conclusions from few examples

Ambiguity Fallacies

  • Equivocation — using a word with two meanings interchangeably
  • Amphiboly — ambiguous grammatical structure

Formal Fallacies

  • Affirming the consequent — if P then Q; Q; therefore P
  • Denying the antecedent — if P then Q; not P; therefore not Q

Scoring Rubric (0–3 per criterion, max 15)

Criterion0123
Claim clarityAbsentVagueClearPrecise + scoped
Evidence qualityNoneAnecdotalDocumentedPrimary source
Warrant validityMissingImpliedStatedLogically sound
Rebuttal acknowledgmentNoneDismissedAcknowledgedAddressed
Internal consistencyContradictionsGapsMostly consistentFully consistent

Tiers: 0–5 Beginner, 6–9 Intermediate, 10–12 Advanced, 13–15 Competitive

Coaching Interventions

  • Score < 6: Rebuild from claim. Ask: "What exactly are you claiming and what evidence supports it?"
  • Score 6–9: Strengthen warrant. Ask: "Why does this evidence support this conclusion?"
  • Score 10–12: Address rebuttals. Ask: "Under what conditions would this argument fail?"
  • Score 13–15: Challenge backing. Ask: "What supports your warrant itself?"

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.

Reviews can't be read right now.

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.