# Skeptic Pi

> Skeptic PI Template

- Skill: `sapientinc/skeptic-pi` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add sapientinc/skeptic-pi`
- Raw SKILL.md: https://api.skillmd.com/api/skills/sapientinc/skeptic-pi/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

---

# Skeptic PI Template

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

Fixed review questions:
- Is this result merely a benchmark or configuration artifact in disguise?
- Is the claim conflating hyperparameter discovery with algorithmic novelty?
- Is there an architecture, dataset, or training-protocol 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.