Zum Hauptinhalt springen
X

dsh-prompt-lab

xueccci/dsh-prompt-lab

Agent-structured prompt optimizer for DeepSeek Harness: rewrites composer drafts into role/task/context/constraint/format with normal, slim, and expand modes, a confirm modal with score, continue-optimize, and local, hybrid, DSH, or cloud-API engines.

Installation

dsh plugin --profile web add github:xueccci/dsh-prompt-lab

README

dsh-prompt-lab

English | 中文

Agent-structured prompt optimizer for DeepSeek Harness (dsh).

Click 优化 in the composer to rewrite the current draft into an executable Agent pipeline — role / task / context / constraints / output format — then review the result in a confirm modal (original | result | five-layer chips + output score). Local rules always work offline; optional LLM polish uses the model already configured in DSH or a cloud API.

Data boundary: Local mode never leaves the machine. hybrid / DSH / cloud-API polish sends the draft and local skeleton to the configured provider.

What it does

Generic polish pluginsdsh-prompt-lab
MethodAsk the model to rewrite onceAgent ladder structure first
ModesMany strategy labels普通优化 / 精简 / 扩写
OfflineNeeds a modelLocal rules produce structured output
ConfirmSilent write-backModal + score + explicit actions
FailureHard failDegrade to local with a yellow banner

Modal actions

ActionBehavior
继续优化Re-run the same optimize pipeline on the editable draft pane
回填输入Copy the result into the draft pane for secondary editing
采用Write the draft pane back to the composer (已写入)
复制Copy the result to clipboard
取消 / EscNever touch the composer draft

Engines

EngineBehavior
仅本地Offline rules, never calls a model
hybrid (default)Local skeleton → DSH polish when provider+model resolve
仅DSHPrefer DSH; on missing model / fail → local + yellow banner
云端 APIOpenAI-compatible HTTP (DeepSeek or custom); fail → local + yellow banner

Timeouts: idle 15s / total 60s.

Install

dsh plugin --profile web add github:xueccci/dsh-prompt-lab#v0.1.1

Restart the profile’s Web process (and Ctrl+Shift+R in the browser), then verify:

dsh --profile web --dump-config | findstr dsh-prompt-lab

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

Settings

设置 → 提示词工坊
├─ 引擎:仅本地 | hybrid(默认) | 仅DSH | 云端 API
├─ 模式:普通优化 | 精简 | 扩写
├─ 云端 API:Base URL / Key / 模型 · 测试连接
├─ 推理行为:自循环 · 快捷键(默认开)
└─ 关于:xueccci · 提示词工坊 dsh 插件

Cloud API keys stay in browser localStorage and are not written to workspace files.

Development

pnpm install
pnpm build          # tsdown → lib/
pnpm check          # unit tests + syntax check

License

MIT · Independent community plugin · Not affiliated with DeepSeek AI.

See NOTICE.


提示词工坊 · dsh-prompt-lab

面向 DeepSeek Harness 的 Agent 结构化提示词优化插件

输入栏点「优化」→ 确认弹窗(原稿|结果|五层诊断 + 输出分)。左侧原稿可编辑,支持 继续优化 / 回填输入采用 写回输入框;取消 / Esc 绝不改草稿。本地规则离线可用;hybrid / DSH / 云端 API 精修失败时 降级黄条,仍可处理结果。

安装

dsh plugin --profile web add github:xueccci/dsh-prompt-lab#v0.1.1

安装后重启 Web 进程,输入栏左侧应出现 优化 按钮。

弹窗操作

操作行为
继续优化对左侧原稿再跑一轮(与「优化」同一逻辑)
回填输入右侧结果填入左侧原稿,便于二次编辑
采用左侧原稿写回输入框 + toast「已写入」
复制复制右侧结果
取消 / Esc / ×绝不改草稿

模式 / 引擎

模式行为
普通优化按 Agent 结构改写
精简提取主干(任务+硬约束+交付)
扩写只细化用户点名的需求
引擎行为
仅本地离线规则,不出机
hybrid(默认)本地骨架 → 有 provider+model 才精修
仅DSH优先 DSH;失败/无模型降级本地 + 黄条
云端 APIOpenAI 兼容 HTTP;失败降级本地 + 黄条

超时:idle 15s / 总 60s

设置

引擎 / 模式 / 云端 API(含测试连接)/ 推理行为(自循环 + 快捷键默认开)/ 关于。

数据边界

  • 本地模式:草稿不出本机
  • hybrid / DSH / 云端 API:草稿与本地骨架会发给所配置的模型服务商

开发

pnpm install && pnpm build && pnpm check

MIT · 社区独立插件 · 与 DeepSeek AI 无隶属关系。

Ähnliche Plugins