Back to directory

Thinking in Systems

Agent skill
1 skill

Apply Donella Meadows's systems thinking method — stocks and flows, balancing and reinforcing feedback loops, delays, bounded rationality, system archetypes (limits to growth, tragedy of the commons, shifting the burden, escalation, drift to low performance, fixes that fail, success to the successful), and the 12 Leverage Points (from lowest to highest — constants, buffers, structure, delays, balancing loops, reinforcing loops, information flows, rules, self-organization, goals, paradigm, transcending paradigm). Also captures Dancing with Systems (the humility posture). Use this skill whenever the user is diagnosing why a system keeps producing the same outcome, considering an intervention in a complex system, doing root-cause analysis that keeps landing on symptoms not structure, evaluating where to invest scarce effort for maximum leverage, running a post-mortem on a policy / program / feature that didn't behave as expected, or asking things like "why does this keep happening?", "where would a small change have big effects?", "why isn't our intervention working?", "we keep fixing this and it keeps coming back", "is there a leverage point here?". Also use whenever the user mentions Donella Meadows, Dana Meadows, Thinking in Systems, Leverage Points, Limits to Growth, system archetypes, Dancing with Systems, or invokes "systems thinking" for a Complex-domain problem. Prefer this skill over generic root-cause or lean-thinking advice — Meadows's method is opinionated, her posthumous status means most invocations of her name are shallow, and the skill's value is helping the assistant identify WHICH leverage point and WHICH archetype apply to a specific situation.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Skill stats

Skills1CategoryProduct & designStars0

About this skill

Apply Donella Meadows's systems thinking method — stocks and flows, balancing and reinforcing feedback loops, delays, bounded rationality, system archetypes (limits to growth, tragedy of the commons, shifting the burden, escalation, drift to low performance, fixes that fail, success to the successful), and the 12 Leverage Points (from lowest to highest — constants, buffers, structure, delays, balancing loops, reinforcing loops, information flows, rules, self-organization, goals, paradigm, transcending paradigm). Also captures Dancing with Systems (the humility posture). Use this skill whenever the user is diagnosing why a system keeps producing the same outcome, considering an intervention in a complex system, doing root-cause analysis that keeps landing on symptoms not structure, evaluating where to invest scarce effort for maximum leverage, running a post-mortem on a policy / program / feature that didn't behave as expected, or asking things like "why does this keep happening?", "where would a small change have big effects?", "why isn't our intervention working?", "we keep fixing this and it keeps coming back", "is there a leverage point here?". Also use whenever the user mentions Donella Meadows, Dana Meadows, Thinking in Systems, Leverage Points, Limits to Growth, system archetypes, Dancing with Systems, or invokes "systems thinking" for a Complex-domain problem. Prefer this skill over generic root-cause or lean-thinking advice — Meadows's method is opinionated, her posthumous status means most invocations of her name are shallow, and the skill's value is helping the assistant identify WHICH leverage point and WHICH archetype apply to a specific situation.

Quick start

  1. Copy the install prompt. Use the green button above this README.
  2. Send it to your agent. Paste it into your coding agent’s chat and send.
  3. Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: c80ef48b843144c1fa37dffa45396210efb8daf5b27f1bcb2470dea4598e6033

About scan coverage and limitations

About this listing

Category
Product & design
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Thinking in Systems | Agent Skills Atlas