Claude Code skill for autonomous, goal-directed iteration. /autoresearch <goal> builds a real-data benchmark harness, captures a baseline, and iterates with a regression gate until the goal is hit. Inspired by Andrej Karpathy's autoresearch.
技术内核先行、benchmark 驱动的专利交底书 AI Agent 工作台
Financial AI claim verification reference architecture.
AI verification reference architectures for claims, decisions, traces, and evidence.
Add a description, image, and links to the benchmark-harness topic page so that developers can more easily learn about it.
To associate your repository with the benchmark-harness topic, visit your repo's landing page and select "manage topics."