Pular para o conteúdo
TakoAPI
Voltar às skills

fleet-doctrine

por jarvis-drakon

Web & Frontend Development
—Ainda sem avaliações
Sua avaliação

Resumo

Model routing strategy for multi-model AI fleet.

Descrição

O que esta skill faz

Defines which AI model to use for each type of task in a multi-model agent setup. Maps task categories to specific models: Opus for high-stakes decisions, Codex for coding, Sonnet for routine work, Gemini for vision and long context, Grok for fast secondary opinions.

Having explicit routing rules prevents expensive models from being wasted on trivial tasks and prevents weak models from handling decisions that require judgment.

Quando usá-la

  • Choosing a model when spawning a sub-agent for a code refactor
  • Setting the default model for scheduled cron jobs
  • Deciding whether to escalate a financial decision to Opus
  • Running parallel code reviews with Codex and Grok
  • Picking the right model for a document with over a million tokens

Exemplo de fluxo de trabalho

ENTRADA

User asks: which model should handle a nightly email briefing cron job?

AGENTE
  1. 1

    Check if the task is security or finance related — it is not

  2. 2

    Check if it requires complex coding — it does not

  3. 3

    Check if it needs image generation or 1M+ context — it does not

  4. 4

    Identify the task as routine and templated

  5. 5

    Apply the Sonnet routing rule for scheduled/templated work

SAÍDA

Assigns Sonnet as the model for the cron job

Instalação

clawhub install jarvis-drakon/fleet-doctrine

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

Links