eval-driven-development
@contextjet-ai · 收录于 1 周前
Use this to build or change an LLM feature the reliable way, by writing evals first and iterating against them, instead of tweaking prompts by vibes. Trigger on "how do I improve this prompt", "my changes keep breaking other things", "how do I know if this is better", "iterate on my agent", or any prompt/model/RAG change. This is test-driven development for LLMs.
适合你，如果厌倦了凭感觉调提示词，想用测试驱动的方式改进 LLM 功能
/ 通过 npx 安装 校验哈希
npx oh-my-skill add contextjet-ai/awesome-llm-observability/eval-driven-development/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- contextjet-ai/awesome-llm-observability/eval-driven-development/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify contextjet-ai/awesome-llm-observability/eval-driven-development安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
19GitHub stars
~638上下文体积 · 单文件
索引托管
评论
登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…