Founder & CTO @ Azra Games.
Travis Boudreaux, founder and CTO of Azra Games, publishes skills that help an AI agent pressure-test plans by working backward from imagined failures, map complex systems and their feedback loops, and classify problems before choosing a response. His most-used skills also cover structured hypothesis testing for symptoms with several possible causes, Socratic questioning to surface hidden requirements, and resolving design contradictions.
Cc Thinking Skills
28 skills · 1,710 stars · MIT
Stress-test a plan by imagining it already failed, then fix the causes Find the concrete failure paths before launch and turn each into a gate or check.
Thinking Bounded Rationality Use when search or investigation could run forever.
Thinking Circle Of Competence Use when a specific claim may lack grounding.
Thinking Cynefin When the right response mode is unclear, classify the cause-effect domain first; decompose disorder.
Thinking Effectuation Under genuine uncertainty with no reliable forecast, inventory means, cap downside at affordable…
Thinking First Principles When a constraint is treated as fixed, separate physics from convention, keep only independently…
Thinking Five Whys Plus When a fault is localized and the proximate cause is known but the systemic root is not, chain ev…
Thinking Jobs To Be Done Deciding what to build or why adoption fails.
Thinking Kepner Tregoe Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice…
Thinking Lindy Effect Use when longevity of a non-perishable option matters.
Thinking Map Territory When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing…
Thinking Margin Of Safety When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to…
Thinking Model Combination When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequ…
Thinking Model Router When unsure which thinking skill fits, map domain and problem type, then return NONE or one prima…
Thinking Ooda Use under time pressure when the situation is still changing and you must act before certainty —…
Thinking Opportunity Cost Before committing scarce time, people, or money, name the best forgone use of those resources and…
Thinking Probabilistic Use when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prio…
Thinking Red Team For authorized security review of code, auth, or APIs you control, model the attacker, map the at…
Thinking Reversibility Before heavy deliberation, classify the decision as cheap or costly to undo; decide two-way doors…
Thinking Scientific Method When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest dis…
Thinking Second Order When a change has effects past the immediate fix—incentives, scale, feedback—trace consequence ch…
Thinking Socratic When a request is vague, assumption-laden, or "obvious," ask the few load-bearing questions that…
Thinking Steel Manning Before rejecting a proposal or reflexively agreeing, build the strongest faithful opposing case,…
Thinking Systems When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boun…
Thinking Theory Of Constraints When throughput or latency is pipeline-limited, identify the single binding constraint and exploi…
Thinking Thought Experiment When a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate on…
Thinking Triz When two design requirements seem mutually exclusive, name the contradiction, separate conflictin…
Thinking Via Negativa Use when the reflex is to add a feature, layer, or process.