본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

hle-reasoning-wrapper

wanng-ide 제작

Health & Fitness
399clawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Wraps HLE benchmark questions in a structured Chain-of-Thought (CoT) reasoning process.

설명

이 스킬이 하는 일

Wraps Humanity's Last Exam (HLE) benchmark questions in a Chain-of-Thought reasoning format. It injects a required Thought/Answer structure into prompts and validates that LLM responses comply with that format.

Handles both prompt formatting and output validation in one module, removing the need to manually enforce CoT structure on each HLE question.

사용 시점

  • Evaluating LLM performance on HLE benchmark questions
  • Preprocessing HLE prompts before sending to a language model API
  • Validating that model outputs follow required CoT structure
  • Running automated HLE benchmark tests with format compliance checks
  • Debugging reasoning failures in structured LLM evaluations

예시 워크플로

입력

User asks: Answer this HLE question: What is the speed of light?

에이전트
  1. 1

    Format the question using hle.formatPrompt() to inject the required Thought/Answer structure

  2. 2

    Send the formatted prompt to an LLM API

  3. 3

    Receive the raw LLM response

  4. 4

    Validate the response using hle.validateOutput() to check format compliance

출력

Validated response confirming the model followed the Thought/Answer reasoning structure

설치

clawhub install wanng-ide/hle-reasoning-wrapper

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크