Loading...
Loading...
Found 36 Skills
Priority Judgment Assistant - Help users determine priorities from chaotic to-do items and figure out what to do right now. Triggered when users say "I have a lot of things to do", "Help me sort this out", "Set priorities", "What should I do today".
Assemble a panel of experts to assess a problem from multiple professional perspectives, surface agreement and disagreement, and deliver a chaired recommendation with clear tradeoffs. Use when the user wants multi-expert judgment, a second opinion, design critique, option comparison, or a recommendation backed by distinct expert viewpoints.
Charlie Munger's Mental Lattice applied to a business idea. Spawns a team of specialist agents — Mathematician, Psychologist, Inverter, Economist, Moat Analyst — who each apply their discipline's elementary models to the idea. The lead synthesizes into a lollapalooza analysis: which forces stack, which fight you, and the honest Munger verdict. Use when the user says "munger this", "apply the lattice", "what would Charlie think", or proposes a business idea and wants multidisciplinary analysis. Works as a standalone analysis or after /office-hours.
Research on Historical Isomorphism and Standard Answers. Abstract the complex dilemma the user is facing into a structural fingerprint, search for truly isomorphic successful cases, failed cases, and counterexamples in business history, management history, technology history, career history, and institutional history. Compare the constraints, decisions, and outcomes of the parties involved, and extract recurring solutions, applicable conditions, and failure boundaries. Trigger methods: /dbs-standard-answer, /标准答案 (Standard Answer), "Who faced similar problems in history?", "Has anyone encountered this situation before?", "How did they resolve it back then?", "Is there a classic solution to this problem?", "First help me find historical analogies?", "What was the standard answer in the past?". Find structurally analogous historical cases and evidence-backed standard answers. Use when the user wants to situate a current dilemma in history, compare how others addressed it, and extract recurring mechanisms with conditions and limits.
Use when facing complex decisions, architectural trade-offs, philosophical questions, or any problem requiring deep analysis before action. Use when the user asks to "think deeply", "question assumptions", "analyze from first principles", "challenge this decision", debates between two approaches (e.g. monolith vs microservices, build vs buy, SSR vs CSR), or invokes /socrates. Also triggered when other skills need a thinking engine for rigorous pre-analysis. Even if the problem seems simple, if there are hidden assumptions worth examining, this skill applies.
Multi-framework intelligence brief. Takes any business situation, investment thesis, career decision, or strategic problem and runs it through 4-7 of 11 analytical frameworks (Feynman, Kahneman, Shannon, Tetlock, Duke, Munger, Thiel, Helmer, Christensen, Meadows, Taleb, Bezos). Each framework runs as a distinct sub-analysis producing concrete claims. Contradictions between analyses are surfaced explicitly. Synthesizes into a single brief: Core Argument, Key Insight, load-bearing conditions, failure modes with numeric probabilities, validation tests, recommended action with sizing, and the strongest dissent. Use when the user says "think through this", "analyze this for me", "help me decide", "think", "/think", or presents any complex decision, investment thesis, business question, or strategic problem that warrants structured multi-framework analysis.
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
Restaurant recommendations / What to eat / Where to eat / Coffee, bars, desserts, late-night snacks. For users asking questions like "What's good to eat nearby? / Restaurant recommendations / What's the average cost per person? / What time do you close? / Do I need a reservation? / Suitable for families or treating guests?" etc. By default, provide a "query time snapshot" (local time) and source links; do not fabricate restaurant names, addresses, business hours, average cost per person, or ratings; if information is insufficient, first ask 2-3 key questions.
Access real-time, continuously refreshed investment context through the Primary Logic External API under /v1. Use when asked to power Codex, Claude Code, OpenClaw, or custom agents with LLM-ranked relevance and impact signals from podcasts, articles and news, X/Twitter, Kalshi, Polymarket, earnings calls, filings, and other monitored sources across public and private companies for decision support or user-controlled trading workflows.
A general research briefing template for quickly organizing research questions, distilling facts and uncertainties, and providing suggestions for subsequent experiments/interviews/data extraction.
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
Use for decision-grade Abel causal reads: explain what is driving a market or company node, how two nodes connect, what changes under intervention, or how a real-world choice looks when routed through Abel proxy signals. Use when user says "Abel" or "causal" or "causality" or "drivers" or "what if" in the context of market, business, crypto, or proxy-routed questions.