autoresearch
适合需要自动化试验与超参/改动搜索的开发者。
会在本地或远端执行代码，需注意权限与环境隔离。
对编程任务进行自主迭代实验：修改代码、运行测试并衡量效果。
把编程当成一系列可测量的实验来自动化：先定目标、定衡量指标和范围，然后自动改代码、跑测试、量效果、保留或回退改动，循环迭代直到满意。适合用来做性能调优、自动化试验和不断改进，而不是一次性修 bug 或只做代码审查。特别之处是闭环的“改→测→取舍”流程，可以大规模尝试不同方案，帮你找到能量化提升的改法。
▸ 展开 SKILL.md 英文原文
Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.
帮我安装这个 skill：https://raw.githubusercontent.com/github/awesome-copilot/main/skills/autoresearch/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/github/awesome-copilot/main/skills/autoresearch/SKILL.md"# Autoresearch: Autonomous Iterative Experimentation An autonomous experimentation loop for any programming task. You define the goal and how to measure it; the agent iterates autonomously -- modifying code, running experiments, measuring results, and keeping or discarding changes -- until interrupted. This skill is inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch), generalized from ML training to **any programming task with a measurable outcome**. --- ## Agent Behavior Rules 1. **DO** guide the user through the Setup phase interactively before starting the loop. 2. **DO** establish a baseline measurement before making any changes. 3. **DO** commit every ex