skill-networks

When designing a skill, I first think of how it will be used. Skills are tightly focused, all signal, no noise, packages of mental models. They are the principle distilled with some specifics woven in.

Skills must not be bloated, since they are designed to compose with other skills dynamically. Similar to a knowledge graph or zettelkasten notebook, skills are index cards of functionality. They are written to be maximally effective and salient. Skills occur at many levels of abstraction:

• specific knowledge "Testing with Deno"
• specific practice "SWOT Analysis", "Technical Review"
• mental models "Multi-scale Thinking", "Pace Layers"
• techniques "Invert Foreground and Background", "Enabling Constraints", "Spread of Three Ideas", oblique strategies
• principles "Domain Driven Design", "Design for Emergence"
• abstract processes "Taking an Idea from Concept to Implementable", "Understanding what's truly motivating about an idea", "Bisecting Possibility Space", "Contrasting Multiple Models", "Representing Abstract Systems using Category Theory"

But all skills should be aware that other skills may want to compose with them and encourage the agent to consider certain kinds of skills in concert with the specific skill. Skills are condensed packets of WISDOM not just information.