Agent Skills: research-method

Run an investigation so its result is trustworthy, and write it up so it survives a hostile reader. Load this when a question needs measuring rather than deciding, when designing an experiment or benchmark, when a result looks good enough to publish, and when drafting an article or pre-registration for a technical community. Covers experiment design, deterministic verification, kill conditions, claims discipline, and the boundary between what the data supports and what it does not.

UncategorizedID: olehsvyrydov/ai-development-team/research-method

Install this agent skill to your local

pnpm dlx add-skill https://github.com/olehsvyrydov/ai-development-team/research-method

Skill Files

Browse the full folder contents for research-method.

Download Skill

Loading file tree…

Select a file to preview its contents.