yuzh1090/dsh-voice-prompt-compressor0

dsh-voice-prompt-compressor

DSH plugin: compress verbose voice-dictation text into token-efficient prompts, fully local.

包名
dsh-voice-prompt-compressor
版本
0.1.0
许可证
MIT
最近更新
2026年8月19日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yuzh1090/dsh-voice-prompt-compressor

Usage

Skill (recommended): paste rambling voice dictation into the chat. The agent loads the voice-prompt-compressor skill, calls compress_voice_text, and presents a compressed four-section prompt (Context / Goal / Constraints / Deliverables).

Tool: the agent can call compress_voice_text directly with these parameters:

ParameterTypeDefaultDescription
textstring (required)The dictation / transcript text to compress
languageauto | zh | enautoWordlist language; auto detects by CJK ratio
modelight | balanced | aggressiveconfigCompression strength
keepPolitenessbooleanconfigKeep politeness phrases when true

The tool returns:

{
  "compressed": "…",
  "originalLength": 512,
  "compressedLength": 210,
  "estimatedTokensSaved": 76,
  "ratio": 0.59,
  "removedCategories": { "fillers": 18, "repeats": 3, "politeness": 2 }
}