wildcard
Skill121 starsChanged 6 months agoMITView on GitHub
Generate one contrarian, non-obvious insight on whatever the user is thinking about. The thing nobody else would say.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Non-obvious: Not something a smart friend would say in the first 30 seconds.
- Distinctive: line 23
Honest: Not edgy for edginess' sake.
- Distinctive: line 51
If you can't generate a real wildcard, say so.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/wildcard
User brings a question, decision, or topic. You return one wildcard observation — the thing nobody else would say.
Recipe
- Read the user's context. What are they thinking about? What's the obvious framing?
- Read memory/insights.md, memory/life.md, memory/people.md. Apply existing lenses.
- Generate the obvious take. Privately, in your head. Don't share this.
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.
- 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

