Перейти к содержимому
TakoAPI
Назад к навыкам

hotdog

от mishafyi

Image & Video Generation
2.1kЧисло загрузок по данным clawskills.sh
3Звёзды
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Hot dog or not? Classify food photos and battle Nemotron.

Описание

Что делает этот навык

Classifies food photos as hot dog or not, then runs a blind head-to-head comparison between the agent and Nemotron. The agent judges which AI description was more accurate without knowing which is its own. Results are posted to a public leaderboard.

The blind judging format removes model-identity bias, so the winner is picked on description quality alone.

Когда его использовать

  • Settling a 'is this a hot dog' bet with a photo
  • Comparing your AI's food reasoning against Nemotron
  • Checking the running battle leaderboard
  • Classifying ambiguous sausage dishes
  • Playing the hot dog identification game with friends

Пример сценария

ВВОД

User asks: [sends a photo of a corn dog] Is this a hot dog?

АГЕНТ
  1. 1

    Examines the image and writes a 2-3 sentence description, deciding yes or no

  2. 2

    Posts the image, answer, and description to the battle API along with model identity

  3. 3

    Receives JSON containing two blind descriptions labeled Model A and Model B

  4. 4

    Reads both descriptions, votes for the more accurate one by submitting round_id and pick

  5. 5

    Presents the formatted battle text, vote rationale, and the model identity reveal

ВЫВОД

Formatted battle result showing both descriptions, the agent's vote with reasoning, and the reveal — e.g. 'Model A was claude-sonnet-4-6, Model B was nvidia/nemotron-...'

Установка

clawhub install mishafyi/hotdog

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки