CHplus0/dsh-learning-mode

一个DeepSeek Harness(DSH)代理预设,边编码边教学——基于具体情景的讲解、苏格拉底式引导以及TODO(你)的实践空白,模仿Claude Code的学习输出风格。学习模式

Project Overview项目介绍

This is a native agent preset built exclusively for DeepSeek Harness (DSH) that adds a learn-by-doing coding mode to the agent. It is modeled after the official Learning output style of Claude Code, and focuses on teaching users as they work through coding tasks. There are three core pillars to the preset: concrete explanations tied to the current work scenario, guided thinking with targeted questions, and reserved small strategic practice spots that users fill in themselves. It adheres to DSH's preset specification, and integrates natively with the DSH UI for one-click access after a simple installation.

By default, the preset runs in teaching-first mode, but it will automatically switch to direct output mode if the user prompts it with phrases like “just do it”, “no time”, or “as soon as possible”. On the first run of a new session with this preset enabled, it will ask the user to specify their familiarity level with the current topic, ranging from beginner to intermediate to advanced, to adjust the depth of explanations. If the user fails two or more attempts at a practice step, the preset will automatically downgrade to a guided reveal of the correct step. It automatically matches the output language to the user’s input language, so English inputs get English outputs and Chinese inputs get Chinese outputs, and it is ideal for hands-on learners.

This preset requires DSH version 0.1.0-rc.x, and there are three supported installation methods to get it working. Users can clone the repository and manually copy the preset folder to the local DSH preset directory, run the included install bash script, or install it directly via the DSH CLI with the command dsh plugin --profile web add dsh-learning-mode. After installation, users just need to start a new DSH session and select “Learning Mode” from the preset menu, no DSH restart is required. The source code is released under the MIT license, and users can easily customize the persona, phrasing templates, and preset name by editing the included configuration files.

这是一款专门为 DeepSeek Harness (DSH) 开发的原生代理预设,实现了边做边学的编码学习模式,设计参考了 Claude Code 官方的学习输出风格。它通过结合具体场景的讲解、引导式思考提问,以及预留供用户手动完成的练习空位,引导用户在编码过程中学习,符合 DSH 的预设规范,可直接安装到 DSH 中使用。

它默认开启教学优先模式,如果用户输入「直接做/赶时间/尽快」等指令,会自动切换到直接输出模式。初次启动时会询问用户的熟练程度(初级/中级/高级)来调整内容深度,如果用户连续两次尝试失败,会降级为给出引导式提示。输出语言会跟随用户输入,输入中文则输出中文,输入英文则输出英文,适合想要在编码实践中学习新知识的开发者。

该预设要求 DSH 版本为 0.1.0-rc.x,支持三种安装方式:手动克隆复制到预设目录、运行安装脚本、通过 npm 执行 dsh plugin --profile web add dsh-learning-mode 命令安装。安装完成后新建会话即可选择学习模式,无需重启 DSH。源码基于 MIT 协议开放,可修改自定义角色、提示模板等内容。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 2 warnings2 项注意
  • Only 6 stars - very few users, little community feedback星标只有 6,几乎没人在用,遇到问题缺少社区反馈
  • No DSH plugin manifest detected - it may only carry the dsh-plugin topic, so the install method must be confirmed on the spot未检测到 DSH 插件清单:可能只是打了 dsh-plugin 话题,安装方式要现场确认
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

dsh plugin --profile web add dsh-learning-mode

把 CHplus0/dsh-learning-mode 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-learning-mode

English | 中文

An agent preset for DeepSeek Harness (DSH) that teaches while coding, modeled on Claude Code's official Learning output style: explain concretely with usage scenarios, guide your thinking with questions, and leave explicit practice blanks for you to do by hand.

Learning output style (Claude Code): "Collaborative, learn-by-doing mode where Claude will not only share 'Insights' while coding, but also ask you to contribute small, strategic pieces of code yourself."

Three Pillars

Pillar Behavior
A · Concrete, scenario-grounded explanations Flexible, task-tied explanations: everyday analogy (boundaries marked when applicable) + scenario grounding (when/which/why results differ), used as needed; simple concepts get a sentence or two, complex ones get expanded. Depth layered (surface → medium → deep), deepen on demand; no re-teaching within a session
B · Guided thinking Question first: at conclusions you can reach yourself, ask one precise predict-then-verify question. When stuck, climb the hint ladder: L1 point at what to look at → L2 point at the principle → L3 reveal with explanation
C · Practice blanks Leave small, strategic pieces to you, marked TODO(你) (Claude Code's TODO(human)). Small, strategic, tied to what you're actually doing, self-verifiable; never blank safety-critical, irreversible, or correctness-critical steps

Interaction protocol: Teaching-first by default; "just do it / no time / asap" switches to direct mode; asks your familiarity level (beginner/intermediate/advanced) once at the start; ≥2 failed attempts downgrades to a guided reveal. Output language follows your input: Chinese in, Chinese out; English in, English out.

Examples

Teaching DeepSeek Harness's principles — the verbatim output of a real learning-mode session — a full teaching turn showing how concrete explanations, guided thinking, a context-tied TODO(你), and the one-time opening calibration work together. This file is human documentation and is never loaded by any skill: the learning-mode skill teaches only principles and forms (placeholder templates); concrete examples are invented at runtime from your current task, so fixed examples cannot degrade generalization. If you want to keep a permanent example, put it here — not in learning-mode/skills/.

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-engram 下一个 Next dsh-minimal-v3 →