Critical Thinking For Humans — AI skill for Claude Code
A gym for your critical thinking — the AI is the coach, you do the work.
How to install Critical Thinking For Humans
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Imbad0202/critical-thinking-for-humans and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Critical Thinking For Humans does
A gym for your critical thinking — the AI is the coach, you do the work. Four modes: drill, scene, expedition, detective.
Alternatives in AI
- Multica — Make humans and AI agents work as one team — open-source and self-hostable 47.8k ★
- Oh My Claudecode — 32 specialized agents and 7 execution modes for Claude Code, with smart model routing and automatic paralleliz 10.9k ★
- Codex Plugin — 's /codex:adversarial-review command 9.6k ★
README
critical-thinking-for-humans
[](https://github.com/Imbad0202/critical-thinking-for-humans/releases/tag/v1.5.0) [](https://creativecommons.org/licenses/by-nc/4.0/) [](https://buymeacoffee.com/crucify020v)
**Last Updated:** 2026-07-25
A gym for your critical thinking. The AI is the coach; you do the work.
Three ways to play
The Web game is a third entry point, not a replacement for the original skill. All three paths share this repository as their source, but they currently have different runtimes and content breadth:
| Entry | Best for | What runs today |
|---|---|---|
| Claude Code plugin / CLI | Dynamic practice with an AI coach | Four canonical modes, 23 verified Expedition packs, and the on-disk Passport |
| Claude.ai Skill ZIP | No local install; upload and chat | Four modes and the pack library, with a copy-paste Passport instead of local files |
| Web Casebook | Players who do not use a CLI | Four fixed bilingual excerpts plus an optional server-backed zh-TW Daily case; no model call |
The portable single-file Markdown build is a compatibility variant of the chat path. It includes Drill, Scene, and Detective, but not Expedition or an on-disk Passport.
**New: bilingual Casebook + Daily Dispatch.** [`web/`](web/README.md) opens with a real domain choice instead of dropping everyone into an education case. Its UI and four fixed excerpts switch between English and Taiwan-oriented Traditional Chinese. Drill, Scene, the Forecaster excerpt of Expedition, and the two-step Detective dependency demo each have a finishable browser flow, using an original 1890s mystery setting, generated character/background art, visual-novel dialogue, original background music, answer effects, a local-first Passport, an
Related Skills
Skill Debate
Structured four-way AI debates between Claude, Sonnet, Gemini, and Codex — use for critical decisions
Nexscope Plugin
Lets multiple AI coding agents (Claude Code, Codex CLI) and humans share a single chat room over a WebSocket r
Gym Operator
AI operator skill for gym owners — sets up a Gym Operations Knowledge Base and runs your recurring gym work gr
Opus Magnum
The Great Work for Claude Code — an adaptive method for long-horizon, high-trust AI builds. Triage, elements,
Verify Before Blocking
A portable discipline that stops AI agents from turning unverified assumptions into stop-work instructions. Si
Multi Agent Protocol
A four-party collaboration protocol for running AI agent teams on real work — auditable authorization, durable
Related Agents
Swe Dev Visible Thinking Coach
Coach essays, interviews, GCSE/A-level/IB/Oxbridge, law, history, theology, English, TOK and humanities work.
Scope Reviewer
Strategic scope review — challenge assumptions about WHAT to build before design work begins. Four modes: EXPA
Tech Artist
Procedural look-dev agent for orkid — authors DSL content (terrain graphs, hypermesh recipes, ptex3d materials
