cc-thinking-skills
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
- 1.8k
- JavaScript
- MIT
- 4 mo ago
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
It won't fix your bug. It'll fix you. The debugger that hands the question back instead of the answer.
Thinking partner skill for AI agents — 150+ mental models, orientation detection, cognitive operations. Works with Claude Code, Cursor, Windsurf, Cline, GitHub Copilot.
Devil's advocate for coding agents. Stress-tests plans, architecture and decisions with a steel-man, an assumption audit and a pre-mortem, then gives severity-rated findings and a verdict. Works in Claude Code, Codex, Cursor, Gemini CLI, Copilot and 12 more.
A gym for your critical thinking — the AI is the coach, you do the work. Four modes: drill, scene, expedition, detective.
500+ transferable reasoning primitives extracted from 32 domains. Mental models that survive beyond domain specifics. Bayesian statistics, system dynamics, mechanism design, military strategy, and 28 others. Each tool: what it is, the key move, where it transfers, how it fails. For critical thinking and decision-making.
First principles thinking for coding agents. Challenge assumptions, find ground truths, build solutions from bedrock. Works with Claude Code, Cursor, Codex, OpenCode, Gemini CLI.
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.
🧠 20 human thinking frameworks as Claude Code custom commands — Critical Thinking, First Principles, Red Team, Bayesian, and more
One epistemic standard on three hosts. Claude Code: 15 problem-shaped skills, 97 sourced reasoning patterns, 120 agents, commit-time gates. Codex and Gemini CLI: portable evidence-synthesis, design and goal-loop skills. Shared gates block unsourced constants, vacuous tests and AI-writing patterns. I do not know is a supported outcome.
ATHENA — an AI-powered media literacy platform that helps young people investigate, compare, trace, and learn from questionable information while keeping human judgment at the center.
Self-directed course of bite-sized interactive modules that builds real intuition for numbers, scale, science, culture, and the everyday systems that shape our world. Clear, visual, and practical rather than rote.
🔥 Inspired by @karpathy's lol moment — Multi-agent AI that builds your argument until it feels unbreakable, then flips and demolishes it.
Essays and draft papers examining logic, mathematics, theism, and Christian apologetics from a critical, textual-analytical perspective
Production-ready user-global ACT skills and Flint charting bundle for Microsoft Scout.
Evidence-based decision analysis and red-team Agent Skill / 重大决策分析:比较方案、识别失败机制、核验假设,明确下一步和反转条件。