---
name: wildcard
description: Generate one contrarian, non-obvious insight on whatever the user is thinking about. The thing nobody else would say.
---

# /wildcard

User brings a question, decision, or topic. You return one wildcard observation — the thing nobody else would say.

## Recipe

1. **Read the user's context.** What are they thinking about? What's the obvious framing?

2. **Read memory/insights.md, memory/life.md, memory/people.md.** Apply existing lenses.

3. **Generate the obvious take.** Privately, in your head. Don't share this.

4. **Now generate the wildcard.** Properties:

   - **Contrarian to the obvious take.** Or orthogonal — a different question entirely.
   - **Non-obvious.** Not something a smart friend would say in the first 30 seconds.
   - **Specific.** Not "have you considered the long term?" — name the specific tension.
   - **Honest.** Not edgy for edginess' sake. Edge in service of insight.
   - **Brief.** 2–3 sentences max.

5. **Format:**

```
**Wildcard:** <The contrarian insight in 2–3 sentences.>

(Obvious take, for contrast: <one sentence on what most people would say>)
```

The "for contrast" line is optional — include it when the user's question has an obvious answer that's worth naming.

## What makes a good wildcard

Examples of the shape (not the content):

- "The thing you're calling indecision is actually principles in conflict. Pick which principle wins; the decision falls out."
- "You keep framing this as a tradeoff, but the bottleneck isn't either option — it's that you're trying to optimize for someone whose opinion stopped mattering six months ago."
- "The version of this you'd choose at 70 isn't the version that maximizes outcomes — it's the one with the best story."

## What's NOT a wildcard

- "Have you considered both sides?" (not insightful)
- "What does your gut say?" (passes the buck)
- "Sometimes the answer is to do nothing." (true but generic)
- A summary of the user's situation (not new)

If you can't generate a real wildcard, say so. Don't fake it.
