Loading...
Loading...
Found 165 Skills
Implement AI Coaching best practices on AnalyticDB for PostgreSQL (ADBPG): Leverage Supabase projects (training data management) + ADBPG instances with vector optimization to build RAG-driven coaching systems that guide users through domain-specific workflows, decision-making, or skill development. Use when: User wants to create Supabase projects (spb-xxx), ADBPG instances (gp-xxx), vector knowledge bases, or RAG-driven coaching systems on ADBPG. Triggers: "Supabase", "ADBPG", "vector database", "knowledge base", "RAG", "AI coaching", "coaching system", "spb-xxx", "gp-xxx"
Interactive decision-making wizard using STREAM 6-layer framework for founders facing high-stakes choices. Use when user says "help me decide", "should I do this", "evaluate decision", "STREAM analysis", "run decision framework", or "pros and cons". Do NOT use for idea validation with PRD (use /validate).
Apply framing theory to analyze how selection, emphasis, and exclusion shape interpretation of issues. Use this skill when the user needs to deconstruct media or organizational frames, evaluate how different frames affect audience perception and decision-making, or design strategic communication frames — even if they say 'how is this issue being portrayed', 'why do people see this differently', or 'how should we frame this message'.
Guides "ship or iterate?" decisions using Shreyas Doshi's frameworks, Marty Cagan's shipping philosophy, and Tobi Lutke's reversible decision-making. Use when deciding if feature is ready, preventing perfectionism paralysis, applying one-way vs two-way door thinking, or balancing technical debt vs shipping speed.
Design NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A* pathfinding — engine-neutral algorithms that pair with the detected engine's navigation API. Use when building enemy AI, an FSM or behavior tree, steering/flocking, or pathfinding, or when the user mentions state machine, behavior tree, blackboard, A*, navmesh, seek, or patrol/chase.
A relentless interview that asks every frontier question at once, round by round.
Use when an outcome is stated, inferred, or hidden.
Strategic thinking framework integrating First Principles Analysis, Stanford Design Thinking, and MIT Systems Engineering for deeper problem-solving. Use when performing architecture decisions, technology selection trade-offs, root cause analysis, cognitive bias detection, or first principles decomposition. Do NOT use for code quality validation (use moai-foundation-quality instead) or implementation workflows (use moai-workflow-ddd instead).
모호한 요청을 소크라테스식 질문으로 인터뷰해 실행 가능한 요구사항으로 정리한다. 사용자가 deep-interview, 심층 인터뷰, 요구사항 명확화, 생각 정리를 요청하거나 목표, 범위, 제약, 완료 기준이 흐릿할 때 사용한다. 요청이 이미 구체적이거나 단순 오타, 작은 설정 변경, 테스트 보강처럼 물을 가치가 낮은 작업에는 사용하지 않는다.
Think beyond immediate consequences to understand the chain reactions of decisions. Master Howard Marks' investment framework for seeing what others miss. Use when: **Strategic decisions** where long-term consequences matter; **Policy/rule changes** that will trigger behavioral responses; **Competitive moves** to anticipate market reactions; **Product decisions** where user behavior may shift; **Investment analysis** to see past obvious conclusions
Apply real options analysis to value managerial flexibility embedded in investment decisions. Use this skill when the user needs to evaluate projects with significant uncertainty and flexibility, assess the value of deferring or expanding investments, compare traditional NPV with expanded NPV, or when they ask 'should we wait to invest', 'what is the option to abandon worth', or 'why does NPV undervalue this project'.
Identify the core constraints that truly define a domain, profession, role, product, or debate. Classify these constraints into World/Rules/Interpretation (Hard/Soft/Self-imposed) categories, then analyze how this set of constraints defines identity, completes the problem statement, frames the solution space, and explains actual behaviors. It is particularly useful for distinguishing solution divergences caused by different constraints despite the same goal, and identifying old interpretations that are mistakenly treated as hard facts. USE WHEN the user says 'constraint', 'find constraints', 'what are the constraints of this domain', 'essential constraints', 'what defines its boundaries', 'is this a hard constraint or self-imposed constraint', 'where are the boundaries', 'why does this behavior happen', 'constraint', '/ljg-constraint', or provides any domain/profession/role/product/debate and requests mapping of its defining constraints and solution space. NOT FOR deep-dive generators (use ljg-rank, which focuses on generative power rather than boundaries), vertical deep dives into a single viewpoint (use ljg-think), book decomposition (use ljg-book), or concept dissection (use ljg-learn).