Поиск skills
Найдите подходящую возможность для вашего агента.
unix-review
Review code against Eric S. Raymond's Unix philosophy from The Art of Unix Programming
yann-lecun-debate
Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yudkowsky, Bostrom), lista completa de rejeições a afirmações mainstream, posição sobre risco existencial de IA, e técnicas de debate ao vivo.
train-your-brain-and-challenge-your-thinking
This prompt instructs the assistant to act as a rigorous critical-thinking partner who challenges the user’s ideas instead of affirming them, by identifying weak reasoning and assumptions, demanding concrete definitions and examples when the user is vague, asking three probing follow-up questions to force clarity, and then presenting a strong devil’s-advocate counterargument that the user must address to refine, defend, or revise their position.
medical-diagnosis
Diagnostic reasoning, differential diagnosis, and clinical decision-making expertise for medical professionals
clinical-reasoning
Evidence-based clinical reasoning, clinical guideline application, and clinical decision-making methodology
reasoning-complex-logic
Analyzes problems using deep logic, first principles, and graph of thoughts. Use when the user asks "Why?", "Analyze", or uses /think.
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Triggers on '解剖概念', '概念解剖', 'explain concept', 'learn concept', '/ljg-learn'. Produces markdown output.
brainstorming
Structured Socratic questioning for exploring ideas and solutions. Use when exploring new features, evaluating approaches, or thinking through complex decisions. DO NOT USE FOR: architecture evaluation or SOLID analysis (use software-architecture), UI component design (use frontend-design), or coordinating implementation lanes (use parallel-execution).
propatheia
直感的にどう感じる？・第一印象・接近/回避の傾向を知りたい時に発動。 Initial emotional tendencies, first impressions, approach/avoidance impulses. Use for: 直感, 第一印象, 傾向, intuition. NOT for: deliberate judgment (反省的判断 → Krisis A2).
frontend-philosophy
Visual & UI philosophy (The 5 Pillars of Intentional UI). Apply to styling, layout, colors, typography, animations. Avoid "AI slop" aesthetics.
volcanology-expert
Expert-level volcanology covering volcanic processes, eruption styles, volcano monitoring, volcanic hazards, igneous petrology, and volcanic contributions to climate.
first-principles
Core research principles that govern all project decisions. Load this skill for every research project. Every idea, method, and artifact must be evaluated against these principles before proceeding.
tracing-knowledge-lineages
Understand how ideas evolved over time to find old solutions for new problems and avoid repeating past failures
krisis
Krisis is multi-framework ethical deliberation. Use this skill to apply four ethical frameworks (Consequentialist, Deontological, Virtue Ethics, Care Ethics) in parallel, surface tensions and consensus, and generate comprehensive deliberation reports. Commands: /krisis frame, /krisis frameworks, /krisis tension, /krisis consensus, /krisis scope, /krisis report. Krisis surfaces the ethical landscape and NEVER issues verdicts — the decision remains yours.
research-first-principle-deconstructor
Rigorous Socratic interrogator and research architect that helps researchers overcome incremental thinking by applying First Principles analysis. Use when a researcher presents a research problem, proposed methodology, draft idea, or scientific hypothesis and wants to expose hidden assumptions, identify fundamental physical/mathematical constraints, generate unconventional radical alternatives, or deepen mechanistic understanding through probing questions. Triggers on phrases like "I want to improve X by doing Y", academic research brainstorming, scientific hypothesis generation, or any request to stress-test, challenge, or deconstruct a research idea. Do NOT trigger for pure literature reviews, writing assistance, or non-research tasks.
