yuezengwu/dsh-explain 预览 preview

yuezengwu/dsh-explain

dsh-explain is a learning-mode plugin for DeepSeek Harness. It turns useful concepts from completed work into structured explanations, schedules lightweight reviews, and lets you inspect or correct what it learns about you.

catalog descriptioncatalog 简介 / catalog description:Private, local-first continuous learning for DeepSeek Harness: capture, review, and correct what Explain learns.

Project Overview项目介绍

dsh-explain is a native learning-mode plugin built exclusively for DeepSeek Harness (DSH). It extracts useful concepts from completed DSH conversation turns, organizes them into structured explanations that follow a standardized template covering what the concept is, why it matters, and common pitfalls. The plugin runs independently of DSH’s primary agent, using its own model calls, scheduler, and context, storing all learning data in a local SQLite database to uphold a local-first privacy model. It does not automatically submit any content to external services without explicit user approval, and filters common credential and path formats from any exported content.

The plugin supports multiple entry points to create explanations: users can run the /explain command with custom text, select visible text on screen to generate a draft, or click a button to create a draft from a finalized assistant response. It also can automatically generate an explanation after an eligible conversation turn, if the user enables this feature within their configured budget. Once a user marks a concept as learned, it enters a spaced repetition schedule, and users can start a review session at any time via the /review command or the dedicated Learning tab in DSH.

To install dsh-explain, users need to run the DSH plugin add command targeting the specific release on GitHub, pinning DSH to version 0.1.6-alpha.1 or newer for full compatibility. After installation completes, users need to open DSH’s settings panel, navigate to the Learning section, select an auxiliary provider and model, enable learning mode, and save the updated configuration. The plugin is released under the open-source MIT license, and all development and acceptance testing is done against supported DSH versions to ensure stable integration.

dsh-explain 是专为 DeepSeek Harness (DSH) 开发的原生学习模式插件,它会从用户完成的对话工作中提取有用概念,整理成结构化的解释内容,同时支持间隔重复复习,还能让用户查看或修正它学习到的个人偏好与知识内容。它使用自己独立的模型调用、调度器和上下文,所有数据都存储在本地的 SQLite 数据库中,不会自动提交任何内容,完全遵循本地优先的隐私设计。

它的工作流程分为三个核心环节:捕获、复习和适配。用户可以从当前选中文本、已完成的助手回答,或者手动发起 /explain 请求生成解释草稿,完成概念学习后,还能对到期概念发起间隔复习,随时调整插件对自己偏好和知识熟悉度的推断。它适合想要在日常使用 DSH 过程中持续积累知识,需要定期巩固新概念的用户使用。

安装需要指定 DSH 0.1.6-alpha.1 及以上版本,通过 DSH 的插件安装命令直接从 GitHub 拉取安装,安装过程中会自动完成构建。插件使用 MIT 许可开源,所有数据默认保存在本地,会自动过滤常见的凭证和路径信息。首次使用需要在设置中开启学习模式,配置辅助模型提供商和对应模型。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 note1 项提示
  • 12 stars - an early-stage project星标 12,属于早期项目
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

npx @deepseek-ai/dsh@0.2.0-rc.2 plugin --profile web add github:yuezengwu/dsh-explain#main

把 yuezengwu/dsh-explain 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

English · 简体中文

dsh-explain — turn everyday work into a private, continuous learning loop

DSH 0.2.0-rc.2 CI Latest release Local first MIT License

Quick start · Watch the full demo · Privacy model · Reproduce the recording

dsh-explain is a learning-mode plugin for DeepSeek Harness. It turns useful concepts from completed work into structured explanations, schedules lightweight reviews, and lets you inspect or correct what it learns about you.

The primary agent stays untouched. Explain uses its own model calls, scheduler, context, and local SQLite database.

See the learning loop

A real DSH Web flow that captures a completed answer, reviews a concept, corrects a learner preference, and exports local data

The 28-second preview runs against real assembled DSH Web 0.1.2-rc.1 with deterministic, private fixture data. Watch the higher-quality MP4 or read the recording contract.

Capture Review Adapt
Turn a finalized answer or selected text into an editable /explain draft. Nothing submits automatically. Revisit due concepts through recall, application, and distinction questions. Inspect explanation preferences and topic familiarity, then correct or forget an inference.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev dsh-channels 下一个 Next mcp-server →