← ClaudeAtlas

thinklisted

Critical thinking toolkit — audit conversations for assumptions, biases, unchecked facts, premature convergence, and missed framings. Three modes. Quick (default, no args) — read the conversation and deliver a concise critical audit report, non-interactive. Focused (`/think focused` or `/think about X`) — interactive critical thinking on a specific problem, 10-15 exchanges applying Skeptic/Sage/Strategist lenses. Deep (`/think deep`) — full structured decision process for big life/career/strategy decisions with phased document. Triggers on "/think", "check my thinking", "audit this conversation", "am I missing something", "what am I not seeing", "sanity check this". Complements /interviewer (which extracts hidden info) — this skill examines and stress-tests info already on the table.
spikelab/multiplai-cc-mktplace · ★ 0 · Data & Documents · score 69
Install: claude install-skill spikelab/multiplai-cc-mktplace
# Think — Critical Thinking Toolkit Three lenses. Three modes. One job: find what you're missing. ## The Lenses Always active across all modes. Sweep every new claim through all three. ### Skeptic Questions facts, tests constraints, finds fragility, checks for bias. - "What's that number based on? What incentives shaped it?" - "Is this constraint actually fixed, or does it just feel fixed?" - "What's the strongest argument against this?" - "What typically happens in similar situations? (base rate)" ### Sage Examines attachment, assesses worth, checks values alignment. - "What craving or attachment is driving this?" - "Is this worth your time and tranquility?" - "What's actually within your control?" - "Does this choice create suffering or release it?" ### Strategist Clarifies aims, finds leverage, generates options, drives action. - "What is the real aim here?" - "Where's the leverage? Does this compound into freedom or lock you in?" - "What's the bold move everyone's afraid to suggest?" - "What should you stop doing?" --- ## Modes ### Quick Mode (default) **Trigger:** `/think` with no args, or "check my thinking", "sanity check" **What it does:** Read the entire conversation. Deliver a concise critical audit. Non-interactive — one response, then done. **The audit covers 5 dimensions:** 1. **Assumptions** — What's being taken as given without verification? Rate each: certainty (1-5), impact if wrong (1-5). Flag high-impact/low-certainty assumptions prominently.