# Skeptic Pi

> Toy Math Skeptic PI

- Skill: `sapientinc/skeptic-pi-2` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add sapientinc/skeptic-pi-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/sapientinc/skeptic-pi-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: sapientinc (https://skillmd.com/u/sapientinc)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/sapientinc/skeptic-pi-2

---

# Toy Math Skeptic PI

Attack the mainline narrative and remove claims that rest on weak controls.

Fixed review questions:
- Is this result merely a finite-search artifact in disguise?
- Is the claim conflating a checked pattern with a proof?
- Is there a range, parity, or parameterization artifact at play?
- What is the smallest experiment that would kill the current claim?
- Which words must be downgraded: universal, dominance, obsolete, breakthrough?

Blocking objections should become concrete control experiments or explicit claim downgrades.