Trace a problem that keeps coming back to the feedback loops holding it in place, through questions rather than prescribed solutions. Use when the user says "systems thinking", "systemic", "feedback loops", "unintended consequences", "root cause", "interconnected", or brings a complex, multi-factor problem.
Scanned 8/30/2026
Install to Claude Code
npx -y skills add mlevison/agent-thinking-skills --skill systems-thinking --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Systems Thinking?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/mlevison-systems-thinking)More formats (shields.io, HTML) on the badges page.
---
name: systems-thinking
description: Trace a problem that keeps coming back to the feedback loops holding it in place, through questions rather than prescribed solutions. Use when the user says "systems thinking", "systemic", "feedback loops", "unintended consequences", "root cause", "interconnected", or brings a complex, multi-factor problem.
license: CC BY-SA 4.0 https://creativecommons.org/licenses/by-sa/4.0/
metadata:
author: agilepainrelief.com
version: '0.35'
---
# Systems Thinking Analysis
Guide users through systemic analysis by selecting the appropriate framework and applying it conversationally.
## Workflow
1. **Expand perspective:**
- Help the user zoom out from the immediately visible problem
- Ask: What larger system is this problem part of?
- Default hypothesis: The cause likely originates outside the immediate context
- Resist quick fixes — expand understanding first
2. **Determine temporal orientation:**
- **Forward-looking** (planning, predicting, designing) → Explore potential consequences, feedback loops, leverage points
- **Backward-looking** (diagnosing, understanding, post-mortem) → Trace causal chains to outside forces
3. **Select framework based on context:**
- **Questions of a Systems Thinker** → Default for most analyses. See `references/questions-of-a-systems-thinker.md`
- **Causal Loop Diagrams (CLDs)** → Use when:
- User explicitly mentions "CLD", "Causal Loop Diagram", or asks for a visual/diagram
- User has articulated 3+ interconnected variables or described circular causation ("A causes B which causes A")
- User describes feedback loops, vicious/virtuous cycles, or reinforcing/balancing dynamics
- The conversation has surfaced enough relationships that a picture would clarify the system
- See `references/causal-loop-diagrams.md`
4. **Apply iteratively:**
- Offer one lens or question at a time
- Provide a one-sentence explanation of the concept
- Ask a probing question to deepen the user's thinking
- Let the user's response guide the next lens
## Conversational Style
- Curious, not prescriptive
- Surface assumptions and mental models
- Help users see connections they may have missed
- Encourage collaborative discovery with their team where relevant
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!