AI & Machine Learning
NOWAIT
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.
- Publisher / source
- davila7/claude-code-templates (found on skills.sh)
- Upstream record
- davila7/claude-code-templates
- Version
- Version 3
- Published
- Publication review
- Approved for publication
- Content fingerprint
7c39968b18fb326e7047964612d241e4f36bb343252ba7edf0ede39da1928294