Skill · em Dados, IA e pesquisa

nowait-reasoning-optimizer

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…

Procedência

Antes de instalar

3 arquivos · 18,7 KB · inclui 1 script que executa: scripts/nowait_processor.py

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/skills/nowait-reasoning-optimizer/.

d=".claude/skills/nowait-reasoning-optimizer"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/productivity/nowait"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/refrences/keywords.md" "$u/refrences/keywords.md" \
  -o "$d/scripts/nowait_processor.py" "$u/scripts/nowait_processor.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.claude/skills/nowait-reasoning-optimizer/.

d="$HOME/.claude/skills/nowait-reasoning-optimizer"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/productivity/nowait"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/refrences/keywords.md" "$u/refrences/keywords.md" \
  -o "$d/scripts/nowait_processor.py" "$u/scripts/nowait_processor.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Codex

Neste projeto: instala em .agents/skills/nowait-reasoning-optimizer/.

d=".agents/skills/nowait-reasoning-optimizer"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/productivity/nowait"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/refrences/keywords.md" "$u/refrences/keywords.md" \
  -o "$d/scripts/nowait_processor.py" "$u/scripts/nowait_processor.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.agents/skills/nowait-reasoning-optimizer/.

d="$HOME/.agents/skills/nowait-reasoning-optimizer"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/productivity/nowait"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/refrences/keywords.md" "$u/refrences/keywords.md" \
  -o "$d/scripts/nowait_processor.py" "$u/scripts/nowait_processor.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Antigravity

Neste projeto: instala em .agents/skills/nowait-reasoning-optimizer/.

d=".agents/skills/nowait-reasoning-optimizer"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/productivity/nowait"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/refrences/keywords.md" "$u/refrences/keywords.md" \
  -o "$d/scripts/nowait_processor.py" "$u/scripts/nowait_processor.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.gemini/antigravity-cli/skills/nowait-reasoning-optimizer/.

d="$HOME/.gemini/antigravity-cli/skills/nowait-reasoning-optimizer"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/productivity/nowait"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/refrences/keywords.md" "$u/refrences/keywords.md" \
  -o "$d/scripts/nowait_processor.py" "$u/scripts/nowait_processor.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Peça ao Rook

Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.nowait-reasoning-optimizer

Prévia do SKILL.md

---
name: nowait-reasoning-optimizer
description: 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 …
---

# NOWAIT Reasoning Optimizer

Implements the NOWAIT technique from the paper "Wait, We Don't Need to 'Wait'! Removing Thinking Tokens Improves Reasoning Efficiency" (Wang et al., 2025).

## Overview

NOWAIT is a training-free inference-time intervention that suppresses self-reflection tokens (e.g., "Wait", "Hmm", "Alternatively") during generation, reducing chain-of-thought (CoT) trajectory length by **27-51%** without compromising model utility.

## When to Use

- Deploying R1-style reasoning models with limited compute
- Reducing inference latency for production systems
- Optimizing token costs for reasoning tasks
- Working with verbose CoT outputs that need streamlining

## Supported Models

| Model Series | Type | Token Reduction |
|--------------|------|-----------------|
| QwQ-32B | RL-based | 16-31% |
| Phi4-Reasoning-Plus | RL-based | 23-28% |
| Qwen3-32B | RL-based | 13-16% |
| Kimi-VL-A3B | Multimodal | 40-60% |
| QvQ-72B-Preview | Multimodal | 20-30% |

**Important**: NOWAIT works best with RL-based models. Distilled models (Qwen3-4B/8B/14B) show degraded performance when reflection tokens are suppressed.

## Quick Start

### 1. Basic Implementation

```python
from scripts.nowait_processor import NOWAITLogitProcessor

# Initialize processor for your model's tokenizer
…

Ver todo o marketplace