A gym for your critical thinking — the AI is the coach, you do the work. Four modes: drill, scene, expedition, detective.
Critical thinking plugin for Claude Code. Three specialized agents (advocate, adversary, judge) argue, stress-test, and judge any idea using a shared argument graph, 10 reasoning traditions, and persistent memory.
🛡️ An AI-powered debate training and communication risk analysis platform. LogicShield strengthens your arguments, detects logical fallacies, and evaluates reputational risk before you publish, pitch, or perform.
Codex skill for philosophical close reading, argument evaluation, relation mapping, and research analysis
Tell coherence from truth — an LLM prompt that lays out any argument's hidden premises, alternatives, and missing evidence
94规则逻辑谬误检测引擎 | 六大领域：形式谬误/非形式谬误/修辞谬误/理科陷阱/营销号套路/对立煽动话术 | 纯Python零依赖 | MIT
Extracts the argument skeleton from any article: core claim, reasoning chain, logic gaps, and reading advice.
ThesisDefender is an adversarial multi-agent AI system that stress-tests arguments, exposes hidden assumptions, evaluates resilience, and generates stronger revisions using Google ADK, MCP, and structured agent reasoning.
An adversarial reasoning agent built for the Microsoft Agents League Hackathon. Paste any claim, and it deploys a multi-step LLM pipeline to steel-man your defense, construct a devastating attack, and expose the single weakest link in your argument using retrieved real-world evidence.
A local-NLP fallacy detector for pasted text. The model flags candidates and a human reviewer makes the final call.
An AI-powered competitive debate training platform. Practice structured debates against an intelligent opponent, receive real-time argument analysis with scoring across logic, evidence, clarity, and persuasiveness, and track your improvement over time. Supports Oxford, Lincoln-Douglas, Parliamentary, and Public Forum formats.
中文逻辑谬误分析与解说 Skill：260 条结构化知识，重建隐藏前提、核验原文证据、控制误报，支持五模式报告、长文本定位、教学评测与 Explainer 解说。
Bilingual AI workspace for examining arguments and drafting better replies.
AI reading assistant for web pages and PDFs. Explore summaries, structure, logic, and reasoning with paragraph-linked insights, powered by your AI subscriptions.
A bilingual (Chinese/English) Agent Skill for reviewing claims, evidence, and reasoning. Works with Codex, Claude Code, Cursor, Claude, ChatGPT, and Gemini.
An AI that disagrees with you, three different ways — built to pressure-test arguments before you ship them.
爆款文章可信吗？一步步拆开它的论证链 | Steelman it first, then find exactly where the argument breaks · 📮 wow.vip@foxmail.com · 🎬 https://v.douyin.com/07EjIDGVErY/
在任意网页上划选文字，右键一键分析正误：找出可能的逻辑问题、深度搜索、给出公正客观的结论。
Read Matcha legal-reasoning code as default logic: a syntax checker, a Reiter/prioritized extension solver with Lean certificates, and a Claude Code skill for neuro-symbolic argument review.
To associate your repository with the argument-analysis topic, visit your repo's landing page and select "manage topics."