autoresearch-with-docs

What problem does it solve?

This skill runs a perf-only AutoResearch loop grounded in local documentation, enabling automated, iterative benchmarking and decision-making against a corpus before each experiment.

Core Features & Use Cases

• Local-documents driven corpus for experiments, ensuring reproducible baselines.
• Iterative design: dispatches focused changes, evaluates impact, and keeps or reverts changes based on results.
• Branch-scoped workflow: creates autoresearch/$ARGUMENTS branches, reads configuration, and logs outcomes for auditability.

Quick Start

Initiate autoresearch by supplying a target argument and allowing the workflow to prepare state, switch to the autoresearch/$ARGUMENTS branch, and run the iterative evaluation loop.