SystemsThinking

How This Skill Approaches It

The skill runs five workflows grounded in Meadows, Senge, Forrester, and Ackoff. Iceberg walks a symptom down four layers — Events, Patterns, Structures, Mental Models — to find the cause that actually generates the behavior. CausalLoop maps the reinforcing (R) and balancing (B) feedback loops that produce a pattern, so you can see second-order effects before shipping a change. FindArchetype matches the behavior to one of ~10 canonical system archetypes (Limits to Growth, Shifting the Burden, Fixes That Fail, Tragedy of the Commons) and applies the documented intervention for that pattern. FindLeverage applies Meadows' 12 leverage points — ranked from weakest (parameters) to strongest (paradigm shifts) — to identify where intervention actually changes behavior. ConceptMap builds a Novak-style entity-relationship map for systems too tangled to hold in working memory.

In Action

What you say to your DA, and what the SystemsThinking skill actually does.

• You say "we keep getting paged for the same class of timeout, nothing we do sticks"
  → Runs the Iceberg workflow: walks from the event (6 pages in 3 weeks) through patterns (all during deploy windows), to structure (auto-scaler cold-start latency exceeds health-check timeout during deploys), to the mental model underneath (deploys are safe if tests pass — but health checks aren't in the test path). Returns a structural fix, not another retry tweak.
• You say "why does adding engineers past team size 12 slow us down instead of speeding us up"
  → Runs FindArchetype: identifies the Limits to Growth pattern — a reinforcing loop (more engineers → more output → more hiring) constrained by a balancing loop (team size → coordination cost → per-engineer output drops). Names the canonical intervention: attack the balancing constraint (coordination mechanism), not the reinforcing loop.
• You say "we're about to add a rate limit to stop abuse, what are the second-order effects"
  → Runs CausalLoop: maps users, abusers, support load, and legitimate traffic into a causal loop diagram, surfaces the balancing loop (rate limit reduces abuse) alongside the reinforcing loop (rate limit causes legitimate retries → total load increases), and recommends per-identity limits with reputation scoring over per-IP blunt limits.

Inside the Skill

The thinking, frameworks, and architecture that distinguish this skill from a generic version of the same task.

User: "Analyze the model router's feedback structure after a model swap: the router issues binding routes, the new main model declines about X% of them inline, and the delegation rate fell from A% to B%."
→ CausalLoop, then FindLeverage
→ Named R/B loops that keep work on the main model, and one leverage point naming the rule or meter to change, judged against the A%→B% figure

User: "Why does the LifeOS skill library keep accumulating overlapping skills (N now), and what structural leverage point would stop the sprawl rather than just pruning it once?"
→ Iceberg, FindArchetype, FindLeverage
→ Events to pattern to the structure that adds skills, the archetype it matches, and a structural change with a first move and a re-check date

User: "Why does a growing city keep running short of water after every reservoir expansion: feedback structure of supply, demand, pricing and drought"
→ CausalLoop, FindArchetype, FindLeverage
→ The loops and delays behind the recurring shortage, and the feasible interventions ranked by leverage

User: "A dashboard metric has shown the same frozen value for months and nobody noticed. What structure let it die silently?"
→ Iceberg, FindArchetype, FindLeverage
→ The independent failures behind the frozen value, each dated from the evidence, and a leverage point that catches the whole class of silent signal loss

Workflows & Routing · 5

Each workflow is one job the skill runs. The trigger phrases route your request to the right one — this is the skill's routing table.

1. 01
   Iceberg Intents/Iceberg.md

   iceberg model, structural cause, why does this keep happening, walk from symptom down to structure

2. 02
   CausalLoop Intents/CausalLoop.md

   causal loop, feedback loop, connection circle, map relationships, build a CLD

3. 03
   FindArchetype Intents/FindArchetype.md

   systems archetype, recognize this pattern, fixes that fail, shifting the burden, tragedy of the commons

4. 04
   FindLeverage Intents/FindLeverage.md

   leverage point, where to intervene, highest-leverage change, Meadows 12

5. 05
   ConceptMap Intents/ConceptMap.md

   concept map, map the entities, relationship map, Novak-style mapping

How to Invoke

Say any of these to your DA and LifeOS activates the SystemsThinking skill automatically:

• "systems thinking"
• "causal loop"
• "feedback loops"
• "archetypes"
• "leverage points"
• "iceberg model"
• "fix the system"
• "why does this keep happening"
• "recurring problem"
• "second-order effects"

Or invoke explicitly:

Skill("SystemsThinking")

References · 3

Auxiliary files the skill loads at runtime — frameworks, guides, configs.

• Archetypes
• Foundation
• LeveragePoints

Related Skills