Skip to main content
Run any Skill in Manus
with one click

empirical-ai-research

Stars0
Forks1
UpdatedJuly 8, 2026 at 22:18

The empirical-research method and quality bar for AI-control experiments run through the ct CLI. Reduce uncertainty fast, iterate on qualitative plus quantitative evidence, size for power, keep splits clean, report honestly, and hold P1 observability, P2 affordance discipline, and the per-team B/R/W/M criteria. Loaded by every role.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

SKILL.md
readonly