Pular para o conteúdo
TakoAPI
Voltar às skills

adaptive-reasoning

por enzoricciulli

Productivity & Tasks
4.2kDownloads informados pelo clawskills.sh
6Estrelas
1Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Automatically assess task complexity and adjust reasoning level.

Descrição

O que esta skill faz

Scores every incoming request on complexity dimensions like multi-step logic, ambiguity, and code architecture, then automatically enables extended thinking when the score warrants it. Appends visual indicators (🧠 or 🧠🔥) to signal when reasoning mode is active. Runs silently as a preprocessing step with no user intervention required.

Avoids the manual overhead of toggling reasoning mode by making the decision automatically based on a consistent scoring rubric.

Quando usá-la

  • Debugging a race condition in a distributed system
  • Designing a caching strategy with conflicting constraints
  • Answering a nuanced trade-off question about system architecture
  • Quickly responding to simple lookups without wasting tokens
  • Auto-downgrading after a complex task when follow-up is trivial

Exemplo de fluxo de trabalho

ENTRADA

User asks: 'Debug why this distributed system has race conditions under load'

AGENTE
  1. 1

    Score the request on complexity dimensions: multi-step logic (+3), code architecture (+2), high stakes (+1) = score 9

  2. 2

    Threshold ≥8 met, activate extended thinking via /reasoning on

  3. 3

    Analyze concurrency patterns, shared state, and timing assumptions in the described system

  4. 4

    Produce a detailed diagnosis with root causes and remediation steps

  5. 5

    Append 🧠🔥 at the end of the response

SAÍDA

Detailed race condition analysis with identified root causes and fixes, ending with 🧠🔥

Instalação

clawhub install enzoricciulli/adaptive-reasoning

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

Links