systems-thinking-leverage

SKILL.md

Find high-leverage intervention points in complex systems by mapping feedback loops, identifying system archetypes, and understanding where small changes can produce large effects.

Systems thinking analyzes how interconnected components create emergent behavior through feedback loops, stocks/flows, and delays. Leverage points (Donella Meadows) are places to intervene in a system ranked by effectiveness:

Low leverage (easy but weak): Parameters (numbers, rates, constants) Medium leverage: Buffers, stock structures, delays, feedback loop strength High leverage (hard but powerful): Information flows, rules, self-organization, goals, paradigms

Use when problems involve interconnected components with feedback loops (reinforcing or balancing), delays, or emergent behavior where simple cause-effect thinking fails. Invoke when identifying leverage points for intervention (where to push for maximum effect with minimum effort), understanding why past solutions failed or had unintended consequences, analyzing system archetypes (fixes that fail, shifting the burden, tragedy of the commons, limits to growth, escalation), mapping stocks and flows (accumulations and rates of change), discovering feedback loop dynamics, finding root causes in complex adaptive systems, designing interventions that work with system structure rather than against it, or when user mentions systems thinking, leverage points, feedback loops, unintended consequences, system dynamics, causal loop diagrams, or complex systems. Apply to organizational systems (employee engagement, scaling challenges, productivity decline), product/technical systems (technical debt accumulation, performance degradation, adoption barriers), social systems (polarization, misinformation spread, community issues), environmental systems (climate, resource depletion, pollution), personal systems (habit formation, burnout, skill development), and anywhere simple linear interventions repeatedly fail while systemic patterns persist. Source: lyndonkl/claude.

View raw