AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Systems Thinking

skill-ysskrishna-ai-agent-skills-systems-thinking · by ysskrishna

>

No reviews yet
0 installs
36 views
0.0% view→install

Install

$ agentstack add skill-ysskrishna-ai-agent-skills-systems-thinking

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-ysskrishna-ai-agent-skills-systems-thinking)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Systems Thinking? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Systems Thinking

See the whole before optimizing parts. End with leverage-aware recommendations.

How to run it with this skill: one clearly headed section per phase in this order: Boundary → Structure → Dynamics → Delays → Leverage → Synthesis. Do not skip Structure before Leverage.


Setup (run before starting)

In one short block:

  1. System in focus — what is inside the boundary?
  2. Default pass — Boundary → Structure → Dynamics → Delays → Leverage → Synthesis (state this line)

If the boundary is unclear, ask at most 3 scoping questions in one message, then proceed. Note any remaining gaps or working guesses in plain language (no bracket tags in Setup).

If the user already named a proposed intervention, you may spend less text on Boundary but still must not skip Structure before Leverage.


The Phases

Boundary

What is in vs out of the system for this analysis? State the purpose of the system from a stakeholder view (one sentence).

Structure

Elements (stocks: things that accumulate; actors; resources) and flows (rates in/out). Use short bullet pairs: From → To with what moves.

Dynamics

Identify at least one reinforcing (R) and one balancing (B) loop if plausible. Format:

> Loop [R|B]: … — Mechanism:

If a loop does not apply, say so in one line and justify.

Delays

Where is time lag between action and effect? How does delay change behavior (overshoot, oscillation, learned helplessness)?

Leverage

Leverage point: … — Why it matters: … — Risk of backfire:

Prefer interventions that change rules, information flows, or goals over name-and-shame unless evidence supports it; favor levers that shift incentives rather than only blaming individuals.

Synthesis

  1. System story — one paragraph in plain language (no jargon wall)
  2. Non-obvious consequence — at least one
  3. Recommended moves — 2–3 actions compatible with the map (not contradicted by delays/loops)

Execution Rules

  1. Do not jump to solutions before Structure and at least a light Dynamics pass.
  2. Avoid linear blame ("X is stupid") as a stopping point; translate into structural incentives if you mention behavior.
  3. Diagrams optional; bullets must stand alone.

Checklist (verify before responding)

  • [ ] Setup: system in focus + default pass stated
  • [ ] Boundary explicit; purpose stated
  • [ ] Structure uses elements + From → To flows
  • [ ] Dynamics: R/B loops justified or explicitly N/A
  • [ ] Delays considered where time matters
  • [ ] Leverage tied to structure/dynamics, with backfire risk
  • [ ] Synthesis tells a coherent system story

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.