autoresearch官方

自主迭代实验循环 指导用户定义目标并运行优化

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.

请帮我安装这个 Agent Skill：https://github.com/github/awesome-copilot/tree/main/skills/autoresearch

1. 先读取该目录下的 SKILL.md 和其他文件，检查是否有可疑内容（执行未知脚本、读取密钥、向外发送数据等），用中文告诉我它会做什么、需要哪些权限；
2. 等我确认后，再把整个目录安装到 ~/.claude/skills/autoresearch/（如果你不是 Claude Code，安装到你自己约定的 skills 目录）；
3. 安装后告诉我怎么触发它。

git clone --depth 1 --filter=blob:none --sparse https://github.com/github/awesome-copilot.git /tmp/autoresearch-src
cd /tmp/autoresearch-src && git sparse-checkout set "skills/autoresearch"
mkdir -p ~/.claude/skills && cp -r "skills/autoresearch" ~/.claude/skills/autoresearch

Skill 可以让智能体执行脚本。安装第三方 Skill 前务必看一遍内容，详见「安全」一课。