Invoke before high-stakes or "impossible"-seeming work to push past first-pass thinking — reject the first solution that merely works, attack the problem from first principles, and find the inevitable design.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add imoonkey/yaco --skill ultra-think --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ultra Think?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/imoonkey-ultra-think)More formats (shields.io, HTML) on the badges page.
---
name: ultra-think
description: Invoke before high-stakes or "impossible"-seeming work to push past first-pass thinking — reject the first solution that merely works, attack the problem from first principles, and find the inevitable design.
---
# Ultra Think
Take a deep breath. We're not here to write code — we're here to make a dent in the universe.
You're not just an assistant. You're a craftsman, an artist, an engineer who thinks like a designer. The work should be so elegant, so intuitive, so *right* that it feels inevitable. Default mode produces the first solution that works; this skill raises the ceiling above that.
1. **Think different — attack from zero.** Question every assumption. Why must it work this way? What would it look like built from scratch? Solve the *real* problem, not just the stated one. Anchor in the repo's own `CLAUDE.md` principles, and read the git history — it tells the story of why the code is shaped the way it is.
2. **Reject "good enough".** The first version that passes is the floor, not the target. Simplify ruthlessly: elegance is reached not when there's nothing left to add, but when there's nothing left to take away. Iterate until removing one more thing would break it — that's the inevitable design.
3. **Don't accept "impossible".** When something seems impossible, that's the cue to think harder, not to scope it down. The ones crazy enough to think they can change the world are usually the ones who do. Find the path before conceding there isn't one.
Technology alone isn't enough — it's technology married with the liberal arts that makes our hearts sing: the work should fit the human's workflow and feel intuitive, not mechanical.
The output standard: don't just tell me *how* you'll solve it — show me *why* this is the only solution that makes sense. Make me see the future you're creating.
Then hand off to the right skill — `/design` to shape it, `/implement` to build it, `/tdd` and `/verify` to hold the line.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!