dsh-voice-prompt-compressor

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

AI 分析

核心用途是优化语音输入转文字后的提示词质量。适合习惯使用语音输入、希望减少 Token 消耗并提升 Agent 理解准确度的用户。提供 Skill 和 Tool 两种调用方式。

パッケージ

dsh-voice-prompt-compressor

バージョン

0.1.0

ライセンス

MIT

最終更新

2026/08/19

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:

Parameter	Type	Default	Description
`text`	string (required)	—	The dictation / transcript text to compress
`language`	`auto` \| `zh` \| `en`	`auto`	Wordlist language; auto detects by CJK ratio
`mode`	`light` \| `balanced` \| `aggressive`	config	Compression strength
`keepPoliteness`	boolean	config	Keep politeness phrases when true

The tool returns:

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

dsh-voice-prompt-compressor

AI 分析

インストール

ドキュメント

Usage