109 tagged critical thinking, measured the same way as everything else here.
Browse within: decision-making 89cognition 55gemini-cli-extension 55analysis 6aquinas 6claude-code-skills 6
tjboudreaux/cc-thinking-skills
Skill Claude CodeCodex
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
tjboudreaux/cc-thinking-skills
Skill Claude CodeCodex
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
tjboudreaux/cc-thinking-skills
Skill Claude CodeCodex
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
Skill Claude CodeCodex
A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says "help me think through X", "challenge my thinking", "what am I missing", "apply mental models to this", "play devil's advocate"…
syzkillall/comprehensive-thinking-skill
Skill Claude CodeCodex
Use when Codex must make a high-quality judgment on any complex problem, not only technical problems. Trigger when a question has high complexity, uncertainty, cost of being wrong, long-term impact, value tradeoffs, possible structural causes, or when the user asks for 全面思考, 深度理解, 系统性分析, 帮我想清楚, 从根上看, 这件事到底怎么看, 方法论…
Skill Claude CodeCodex
../../../skills/pensamiento-critico/SKILL.md.
Skill Claude CodeCodex
Deep thought roasting engine — progressively interrogates thinking to uncover fallacies, blind spots, hidden assumptions. Triggers: user says 'roast me'/'challenge my thinking'/'poke holes', describes idea with fuzzy logic, types /roast. All deep-thinking scenarios. Does NOT trigger on explicit execution-only or…
Skill Claude CodeCodex
A Japanese-language question-only tool for examining an idea through progressively deeper questions about its meaning, reasoning, assumptions, contradictions, and underlying motivation.
Skill Claude CodeCodex
A Chinese-language question-only tool for examining an idea through progressively deeper questions about its meaning, reasoning, assumptions, contradictions, and underlying motivation.
Skill Claude CodeCodex
First-principles assumption auditor. Deconstructs any decision or belief into irreducible premises, classifies each assumption (fact / convention / belief / interest-driven), ranks them by fragility × impact, and rebuilds conclusions from verified ground truth. Bilingual: responds in the user's language (Chinese or…
Skill Claude CodeCodex
Use when engaging in political argumentation, countering capitalist/authoritarian/status-quo arguments, or when user needs substantive counterarguments on economics, authority, philosophy, history, rhetoric, technology, or social topics. Provides objection handling and delivery calibration. The framework argues from a…
Skill Claude CodeCodex
Bring humanity's best thinking to bear BEFORE improvising an answer. When the user seeks counsel or takes on a substantive task that rewards real thinking, planning, or design — rather than a quick fact or a mechanical edit — this skill first reaches for the two or three most fitting proven frameworks or mental models…
ArchSightLabs/archsight-cognition
Skill Claude CodeCodex
A guide for turning a product idea into a small product requirements document, or PRD. A PRD records who the product is for, what to build first, and how to test the idea.
ArchSightLabs/archsight-cognition
Skill Claude CodeCodex
A research summary built from outside sources, such as official documents, papers, project repositories, company announcements, and reliable reporting. It records findings, source links, evidence strength, disagreements, and unknowns.
ArchSightLabs/archsight-cognition
Skill Claude CodeCodex
A research-planning template for turning a question about a product, market, user, technology, organization, or knowledge topic into a testable plan. It organizes hypotheses, sources, interviews, validation steps, timing, and deliverables.
Skill Claude CodeCodex
This skill should be used when the user asks to "decompose a problem", "apply Cartesian method", "break this down systematically", "reduce to first principles", "analyze from the ground up", "apply methodical doubt", or wants to process input through Cartesian Reductionism to decompose complex wholes into clear…
Skill Claude CodeCodex
This skill should be used when the user asks to "classify a decision", "is this a one-way or two-way door", "apply the doors framework", "triage this decision", "how much thinking does this need", "should I decide fast or slow", "apply Bezos decision framework", "Type 1 or Type 2 decision", or wants to determine how…
Skill Claude CodeCodex
This skill should be used when the user asks to "assess quality", "apply Pirsig's framework", "analyze through Metaphysics of Quality", "evaluate static vs dynamic quality", "examine value conflicts", "apply MoQ", or wants to process input through Pirsig's Metaphysics of Quality to understand value, quality, and the…
Skill Claude CodeCodex
Read any document the way a detective reads a witness statement — surface what it is NOT saying. Unlike a summarizer (which tells you what a text says), this skill exposes the subtext: hedging and weasel words, conspicuous omissions, buried leads, frequency tells, tone shifts, and non-answers. Use it on earnings…
Skill Claude CodeCodex
Find what will kill a plan before it's committed to — by assuming it already failed and working backwards to the causes. Based on Gary Klein's pre-mortem technique. Unlike generic "what are the risks?" brainstorming, this skill imagines a specific, vivid failure six months out, reasons back to the most likely causes…
Skill Claude CodeCodex
Reason past the obvious, first-order consequence to the second-, third-, and long-tail effects everyone else stops short of. Where most analysis says "X causes Y", this skill asks "and then what?" — mapping the cascade, surfacing the non-obvious winners and losers, the reflexive responses, and the effects that only…
Ludovic33Fr/product-ai-toolbox
Skill Claude CodeCodex
Utiliser avant toute décision importante pour faire jouer à l'IA le rôle d'un sceptique professionnel. Produit les trois meilleures raisons de ne pas faire ce qui est proposé, classées par force décroissante.
gagharutyunyan1993/methodology-toolkit
Skill Claude CodeCodex
Apply structured decision-making and analytical frameworks to non-trivial problems. Use when the user asks for research, strategy, diagnosis, architecture decisions, prioritization, tradeoff analysis, root cause analysis, planning under uncertainty, problem-solving approach, "how should I approach X", or for…
Skill Claude CodeCodexCursor
The scientific thinking protocol for AI agents. Use when facing complex, ambiguous, or high-stakes questions where guessing is costly — technical design decisions, architecture choices, debugging theories, data claims, security judgments, or any answer the agent is tempted to give confidently without evidence.…