# systems-thinking-leverage

systems-thinking-leverage turns a tangled problem into a mapped system with ranked intervention points, built on feedback loops and Meadows' leverage ladder.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 114 installs · ★ 203 repo stars
- Author: lyndonkl
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lyndonkl/claude/tree/HEAD/skills/systems-thinking-leverage/SKILL.md
- Updated: 2026-09-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/systems-thinking-leverage

## What it does

The skill walks a problem through five steps: set the boundary and the variables, sketch how things connect, locate candidate interventions, test the guesses, then write the strategy up. Output lands in `systems-thinking-leverage.md` with the map, the ranking and what each move is expected to change.

Two reference files hold the detail. `resources/template.md` is for a quick causal loop sketch; `resources/methodology.md` covers archetypes, several loops at once and time lags. Ranking follows Meadows' ladder, starting at parameters and buffers and climbing through rules, goals and paradigms. A rubric at `resources/evaluators/rubric_systems_thinking_leverage.json` scores the draft before you act on it.

Where the leverage is greatest, resistance tends to be greatest too, and the skill says to weigh that against what people will actually accept. It also asks about delays: tighten a feedback loop too far and the system starts to swing.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill systems-thinking-leverage -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/systems-thinking-leverage/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/systems-thinking-leverage/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill systems-thinking-leverage -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/systems-thinking-leverage/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill systems-thinking-leverage -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/systems-thinking-leverage/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lyndonkl/claude skills/systems-thinking-leverage
```

2. **Manually: put the files in place**
- File: `.github/skills/systems-thinking-leverage/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill systems-thinking-leverage -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lyndonkl/claude --path skills/systems-thinking-leverage
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/systems-thinking-leverage/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill systems-thinking-leverage -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/lyndonkl/claude/tree/HEAD/skills/systems-thinking-leverage/SKILL.md

## When to use it
- trace why an earlier fix backfired
- choose where to push inside a loop-heavy system
- separate a recurring pattern from the symptom on top
- map stocks and flows before reworking a process
- list knock-on effects before rollout

## Example prompts
- Map why churn keeps returning: draw the loops and rank the leverage points.
- Run my onboarding plan through the rubric and tell me which delays will sink it.
- Write the system map for our hiring pipeline to `systems-thinking-leverage.md`.

## Similar
- [thinking-systems](https://affpapa.org/en/nevibecode/skills/thinking-systems.md) — skill · 708 installs
- [systems-thinking](https://affpapa.org/en/nevibecode/skills/systems-thinking.md) — skill · 160 installs
- [thinking-pre-mortem](https://affpapa.org/en/nevibecode/skills/thinking-pre-mortem.md) — skill · 804 installs
- [024-context-mapping](https://affpapa.org/en/nevibecode/skills/024-context-mapping.md) — skill · 142 installs
- [leverage](https://affpapa.org/en/nevibecode/mcp/leverage.md) — MCP server
- [self-improving-agent](https://affpapa.org/en/nevibecode/skills/borghei-self-improving-agent.md) — skill · 244 installs

From the same set: [lyndonkl/claude](https://affpapa.org/en/nevibecode/by/lyndonkl/claude.md) — 49 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
