agent-research

What problem does it solve?

This Skill provides a structured framework for conducting long-running, exploratory research, ensuring reproducibility, clear decision history, and efficient iteration loops.

Core Features & Use Cases

• Reproducible Research: Maintains detailed logs, branches, and snapshots for transparent research processes.
• Iterative Experimentation: Facilitates rapid iteration on benchmarks, experiments, and hypotheses across multiple sessions.
• Handoff Quality: Ensures clear documentation and artifacts for human and future agent collaboration.
• Use Case: Use this skill when tasked with a complex, multi-stage investigation into model performance, requiring detailed tracking of experiments, hypotheses, and results over an extended period.

Quick Start

Initiate a new research thread by creating a dedicated branch, an experiment issue, and a research logbook.