360 Secure SkillHub
360 安全技能中心

Hle Reasoning Wrapper

该 Skill 将 Humanity's Last Exam 问题转换为包含 Thought/Answer 的结构化提示,并提供输出校验,确保模型按步骤推理并符合格式要求;本身不包含 LLM 调用、答案数据或正确性评分。

wanng-ide
wanng-ide
热度 64.65
最近更新 2026-05-11 17:25:49
分类:知识依赖:代码执行 / 内部调用大模型应用场景:研究 / 概念解释 / 测验

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add hle-reasoning-wrapper
Metadata
name
hle-reasoning-wrapper
description
Wraps HLE benchmark questions in a structured Chain-of-Thought (CoT) reasoning process. Use when answering HLE questions to ensure strict step-by-step logic and format compliance.

HLE Reasoning Wrapper

Enforces a structured reasoning process for Humanity's Last Exam (HLE) questions.

Usage

const hle = require('./index');
const prompt = hle.formatPrompt("What is the speed of light?");
// Use prompt with LLM
const result = hle.validateOutput(llmResponse);

Logic

  1. Format Prompt: Injects required structure (Thought/Answer).
  2. Validate Output: Ensures the model followed the structure.