Pular para o conteúdo
TakoAPI
Voltar às skills

hle-reasoning-wrapper

por wanng-ide

Health & Fitness
399Downloads informados pelo clawskills.sh
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

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

Descrição

O que esta skill faz

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.

Quando usá-la

  • 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

Exemplo de fluxo de trabalho

ENTRADA

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

AGENTE
  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

SAÍDA

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

Instalação

clawhub install wanng-ide/hle-reasoning-wrapper

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links