Agent skill
systems-thinking
Analyze complex systems, feedback loops, and leverage points. Avoid linear thinking for complex problems.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/product-andreibesleaga-gabbe-7
SKILL.md
Systems Thinking Skill
Goal
To understand the system as a whole, specifically focusing on relationships, feedback loops, and delays, rather than looking at isolated parts. Use this when solving stubborn, recurring problems or designing robust architectures.
Steps
-
The Iceberg Model Analysis
- Events (React): What just happened? (The bug/incident)
- Patterns (Anticipate): What trends have been happening over time?
- Structures (Design): What influenced the patterns? (Architecture, Org chart, Incentives)
- Mental Models (Transform): What assumptions/beliefs keep the system in place?
-
Causal Loop Diagramming (CLD)
- Identify variables (e.g., "Code Quality", "Velocity", "Tech Debt").
- Map relationships (S = Same direction, O = Opposite direction).
- Identify Loops:
- Reinforcing (R): Exponential growth/collapse (Virtuous/Vicious cycles).
- Balancing (B): Goal-seeking/Stabilizing.
- Output: Mermaid diagram or text-based CLD.
-
Identify Leverage Points
- Where is the intervention point with the highest impact?
- Examples: Changing a buffer size (Low leverage) vs Changing the goal of the system (High leverage).
-
Archetype Matching
- Does this match a known system trap?
- Examples: "Fixes that Fail", "Shifting the Burden", "Tragedy of the Commons", "Drifting Goals".
Output Format
A strategic analysis document at docs/strategic/SYSTEM_ANALYSIS.md containing the Iceberg analyis and Causal Loop Diagrams.
Constraints
- Look for circular causality, not linear (A causes B, but B also influences A).
- Watch out for delays in the system—they cause oscillation.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?