deepseek

Reasoning guidelines optimized for DeepSeek-V3 and DeepSeek-R1.

SKILL.md

GitHub

Deepseek

Reasoning guidelines optimized for DeepSeek-V3 and DeepSeek-R1.

Core Guidelines

  • Thinking Tokens: Let the model complete its internal reasoning loops. Do not limit token emissions.
  • Constraint Compliance: Formulate clear logic bounds, as DeepSeek aligns closely to structured syntax rules.
  • Coding Style: Maintain clean, minimal structures as DeepSeek excels at compact code.