Agent skill
systems-thinker
Understand complex systems, interconnections, and emergent behaviors
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/systems-thinker
SKILL.md
Skill: systems-thinker
What I do
I analyse software and organisations as interconnected systems. I identify feedback loops, second-order effects, and leverage points to ensure that changes improve the system as a whole rather than just optimising a single part.
When to use me
- When designing distributed systems or microservices
- To analyse the root cause of systemic issues or performance bottlenecks
- When evaluating the impact of a change on downstream systems
- To identify and mitigate unintended consequences of a proposal
Core principles
- Feedback loops — Identify reinforcing (amplifying) and balancing (stabilising) loops that drive system behaviour.
- Second-order effects — Ask "and then what?" to anticipate the downstream consequences of a change.
- Leverage points — Find the small changes that can lead to large improvements in system performance.
- Emergent behaviour — Understand that complex systems exhibit behaviours that cannot be predicted by looking at individual components in isolation.
Patterns & examples
Causal Loop Diagram (Simplified):
- Action: Increase test coverage.
- Immediate Effect: More bugs found early.
- Second-order Effect: Fewer production incidents.
- Long-term Effect: Higher developer confidence and faster feature delivery (Reinforcing Loop).
System Leverage Points:
- Low Leverage: Tweaking parameters (e.g. changing a timeout value).
- Medium Leverage: Changing system structure (e.g. moving from synchronous to asynchronous communication).
- High Leverage: Changing the goals of the system (e.g. prioritising resilience over raw throughput).
Anti-patterns to avoid
- ❌ Siloed optimisation — Improving one component at the expense of the overall system (e.g. making a service extremely fast by overloading the database).
- ❌ Linear thinking — Assuming that every effect has a single, direct cause.
- ❌ Ignoring delays — Failing to account for the time it takes for a change to ripple through the system.
KB Reference
~/vaults/baphled/3. Resources/Knowledge Base/AI Development System/Skills/Thinking-Analysis/Systems Thinker.md
Related skills
critical-thinking— Foundation for system analysisretrospective— Learning from systemic failuresarchitecture— Applying systems thinking to designtrade-off-analysis— Weighing system-wide impacts
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?