prompt-token-efficiency

压缩并重写提示词以降低 token 用量并保持意图清晰。

把给 LLM 的提示词压缩成最短、最清晰的指令，尽量减少 token 用量但不改变输出意图。会去掉寒暄、重复和不必要叙述，优先短句子和明确步骤，优化执行性而不是让人读得漂亮。适合想降低成本或提高模型执行稳定性时使用。

# Prompt Token Efficiency

Use this skill to compress prompts while preserving intent and output quality.

## Goals

1. Minimize token count
2. Maximize clarity
3. Minimize ambiguity
4. Optimize for LLM execution, not human prose style

## Core Rules

- Keep only task-critical information.
- Remove pleasantries, repetition, and narrative framing.
- Prefer short, concrete instructions over descriptive paragraphs.
- Use explicit constraints and output format requirements.
- Use stable terminology (one term per concept).
- Replace vague words (`appropriate`, `some`, `better`) with measurable criteria.
- Put required context before optional context.
- Avoid conflicting instructions.

## Prose Co