Why treating AI as a brilliant but inexperienced junior intern - fast and knowledgeable, but requiring explicit guardrails and final QA - maximizes leverage.
Come up with good ideas about what to fix. Use when you have to fix something, but you're not sure what.
Produces a reversibility classification that triages a decision before any analysis - labeling it a reversible two-way door or a hard-to-reverse one-way door - and matches the…
Produces a binary-vote comparison matrix (every pair judged A-beats-B), a derived ranking, and a consistency check, ordering options without any criteria axis or absolute scoring.
Evaluates a decision or idea through several deliberately separated lenses in turn (facts, upside, risks, intuition, alternatives, process) so that no single mode dominates, then…
Evaluates rival causal explanations of a single case by typing each piece of within-case evidence by its diagnosticity (hoop, smoking-gun, straw-in-the-wind, doubly-decisive…
Produces a pyramid that structures a recommendation answer-first - a single governing thought on top, a small set of MECE, deliberately ordered key arguments beneath it, and…
Generates a rapid burst of questions about a problem (questions only, no answers), then ranks them for which would most change the approach and selects the single most catalytic…
Generates three off-pattern framework analyses of a topic by drawing frameworks at random, applying each regardless of fit, and harvesting the non-obvious angles the unexpected…
Produces a reference-class estimate by defining a class of similar past cases, taking their base-rate distribution of outcomes, and anchoring the forecast on that outside view…
Retrospective learning from a completed experience. Takes a project, incident, decision that played out, or time period; gathers ground truth (observations) separately from…
Produces a persona-tagged divergent idea list, ideas generated while inhabiting a chosen non-self identity to lower self-censorship and shift associations.
Generates a structured set of variations on an existing idea, product, or process by running it through seven transformation prompts (substitute, combine, adapt, modify, put to…
Good-faith adversarial scrutiny of an idea or plan. Spawns critical skeptics across relevant lenses, pairs them with an advocate defending the idea, and synthesizes the exchange…
强制 AI Agent 在执行任何高风险或实质性操作（如修改文件、执行命令、查询数据库）前进行逻辑梳理、步骤拆解。这是一种显式驱动 ReAct 循环的思想链（CoT）触发器。
Produces a stock-flow map by separating a quantity that accumulates from the inflows and outflows that change it, then reasoning about the stock's trajectory from the net flow…
Produces a three-curve transition map (a declining present H1, a contested middle H2 read in two directions, an emerging future H3) with the actor located in it.
Produces a worked three-framework analysis of a topic. Ranks the library's thinking frameworks for relevance, applies the top three so each emits its real artifact, and reconciles…
Forces Claude to pause before any high-cost task and ask: "Is there a cleverer, cheaper way to do this?" Triggers before heavy computation, large code generation, repetitive data…
Produces a veiled-decision comparison that decides a values trade-off as if the decider had an equal chance of being any affected party, under an explicit decision rule, then…
Converts a strategy, option, or contested claim into the specific conditions that would have to be true for it to be the best choice, rates each condition's confidence, and…
Produces a WOOP commitment card by working through Wish, Outcome, Obstacle, and Plan - contrasting the desired outcome against the main internal obstacle and binding an if-then…
When the user wants to review past decisions, understand why something was built a certain way, audit decision quality, or learn from past reasoning.
Control browsers via the ThinkBrowse CLI (the thinkbrowse / thinkrun command) — navigate pages, interact with elements, extract content, take screenshots.
Control browsers via ThinkBrowse MCP tools — navigate pages, interact with elements, extract content, take screenshots.
Thinkific integration. Manage Courses. Use when the user wants to interact with Thinkific data.
Recognize Senge's Systems Archetypes to diagnose recurring organizational and technical problems, identify why fixes keep failing, and design interventions that address root…
Update beliefs systematically based on new evidence using probabilistic reasoning. Use when estimating probabilities, learning from data, or making decisions under uncertainty.
Apply Herbert Simon's Bounded Rationality and satisficing to make good-enough decisions under real-world constraints.
Creatively expand ideas through interactive technique application. Generates variations, explores alternatives, pushes boundaries.
Know the boundaries of your expertise and operate within them. Use when evaluating opportunities, making decisions outside your domain, or assessing when to defer to experts.
Develop and maintain project concepts through guided questions, structured synthesis, and project sync.
Critically analyze ideas through structured techniques from multiple perspectives. Use with /thinking-critique to stress-test concepts before committing to implementation.
Classify problems by complexity domain (clear, complicated, complex, chaotic) and match approach to domain. Use for choosing methodologies, problem framing, and process design.
Systematic checklist to identify and counteract cognitive biases in decision-making. Use before major decisions, when evaluating recommendations, or when stakes are high.
Engages structured analysis to explore multiple perspectives and context dependencies before responding.
Core thinking disciplines for rigorous collaborative reasoning. Invoked by skills that need truth-convergent thinking — come prepared, name confidence, sit with fog, verify before…
Apply Kahneman's Dual-Process Theory to recognize when to trust intuition vs engage deliberate analysis.
Start with means, not goals; co-create with partners; leverage contingencies. Use for startup strategy, innovation projects, and uncertain/novel domains where planning is…
Make order-of-magnitude estimates for unknown quantities by decomposing into known or estimable factors.
Break complex problems into fundamental truths by questioning assumptions and rebuilding from irreducible components.
Enhanced root cause analysis with explicit bias guards and stopping criteria. Use for incident post-mortems, bug investigations, and process failures where standard 5 Whys might…
Approach problems backward by identifying paths to failure, then systematically avoiding them. Use for risk identification, planning, and avoiding obvious mistakes.
Systematic rational process for complex problem analysis, decision making, and risk assessment. Use for high-stakes engineering decisions, root cause analysis beyond 5 Whys, and…
Use when working in a technical domain with no existing playbook, writing new coding guidelines / review criteria / checklists from scratch, judging whether a verification method…
Review thinking ledgers for substantive reasoning evidence. Use when accepting a staged or submitted thinking ledger for non-trivial work to check problem, assumptions,…
Identify where small changes can have large effects using Donella Meadows' hierarchy of system intervention points.
For non-perishable things, future life expectancy is proportional to current age. Use for technology selection, evaluating frameworks/libraries, and predicting tool longevity.
Combine multiple mental models for richer analysis. Use for complex problems requiring multiple lenses, high-stakes decisions, or when single models leave blind spots.
Route to the right mental model based on your domain and problem type. The single entry point for all thinking skills.
Choose the right mental model for the problem at hand. Use when facing new problems, when current approaches fail, or when you need to match tool to context.
Extended thinking modes for deeper analysis. Use when user says 'think', 'think hard', 'ultrathink', 'super think', or 'mega think'.
Rapid decision-making loop for dynamic situations. Use for incident response, competitive scenarios, time-sensitive decisions, and situations requiring quick adaptation.
Evaluate decisions by what you give up, not just what you gain. Use for resource allocation, prioritization, build vs. buy choices, and technical debt evaluation.
Add accessible animated AI loading and agent-status indicators with the React thinking-orbs library. Use when a chat, copilot, voice, search, generation, or tool-running interface…
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved.
Imagine a project has failed and work backward to identify why. Use at project kickoffs, before major decisions, or when optimism may be obscuring risks.
Express confidence in ranges, update predictions with new information, and track calibration over time.
Project to your future self and ask what you would regret not doing. Use for career decisions, strategic pivots, risk-taking choices, and life-changing decisions.
Think beyond immediate consequences to second and third-order effects. Use for strategic decisions, policy changes, and avoiding unintended consequences.