DeepSeek HarnessHub
Submit plugin

xueccci/dsh-prompt-lab ↗★ 0

dsh-prompt-lab

Agent-structured prompt optimizer for DeepSeek Harness. Rewrites the composer draft into role/task/context/constraint/format with modes normal/slim/expand. Engines: local, hybrid (default), DSH, cloud API. Confirm modal with score, fill-to-draft, continue-optimize, and adopt-to-composer. DeepSeek Harness 输入栏 Agent 结构化提示词优化插件。 适合需要优化提示词结构、提升模型回复质量的DSH用户。

Agent collaboration
Package
dsh-prompt-lab
Compatibility
Unverified
Harness peer range
>=0.1.0-rc.1 <0.2.0 || >=0.1.0-rc.1 <0.2.0-0
Cordis peer range
>=4.0.0 <5.0.0 || >=4.0.0-rc.1 <5.0.0-0
Version
0.1.1
License
MIT
Last updated
Sep 22, 2026

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xueccci/dsh-prompt-lab

README

Read the full README ↗

Usage

  1. Type a draft in the composer.
  2. Click 优化 (or Ctrl/Cmd+Enter).
  3. Review the modal; edit the draft pane, 继续优化, or 回填输入.
  4. 采用 writes the draft pane back only if the composer draft is unchanged.
ModeBehavior
普通优化Rewrite into Agent structure (role/task/context/constraints/format)
精简Extract trunk: core task + hard constraints + deliverable
扩写Expand only needs the user named