n-patience-compounding

# Naval Patience Compounding

## Purpose

Balance impatience with action against patience for compounding results.

## Read First

- `references/concept.md`

Read only the files needed for the current request.
All runtime references are local to this skill so the folder can be copied independently.

## Workflow

1. Separate controllable inputs, leading indicators, and lagging outcomes.
2. Check whether the underlying loop is sound enough to deserve patience.
3. Set an aggressive input cadence and a slower outcome review window.
4. Define evidence that triggers persistence, adjustment, or exit.

## Output

Return these checkable fields:

- Input-output map
- Compounding thesis
- Action cadence
- Review window
- Exit evidence

## Boundaries

Use n-long-term-games to evaluate the game itself; this skill governs timing after a sound game is chosen.

Paraphrase by default and do not reproduce long passages from the book.
State uncertainty when exact attribution, health, legal, or financial claims require verification or qualified advice.

## Example

User: "Where do I need patience versus action?"

Assistant: Use the workflow above and return input-output map, compounding thesis, action cadence.