SkillFeeder › 全部 Skill › Bug与质量 › typesafe-ai

用结构化提问让AI返回带置信度的类型化结果,替代脆弱的关键词匹配或LLM解析

typesafe-ai

typesafe-ai 是 SkillFeeder 收录的Agent Skill,来自 GitHub 仓库 typesafe-ai/skills,★ 2,889。用结构化提问让AI返回带置信度的类型化结果,替代脆弱的关键词匹配或LLM解析。适合构建可靠AI集成的工程师。场景是Bug与质量 · 调试排错。能做的事包括返回Choice/Noul/Score/Box四种明确类型的结果、所有答案附带校准概率,可直接用于代码逻辑、支持文本、图像与应用状态联合推理。打开 GitHub 自行安装。

打开 GitHub

仓库
typesafe-ai/skills
仓库星标
★ 2,889
场景
Bug与质量 · 调试排错
适合
构建可靠AI集成的工程师
类型
Skill

能做什么

原文简介

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or state; when replacing an LLM prompt-and-parse step, keyword matching, or a brittle heuristic with a ty

同场景推荐